Completed
Push — master ( 443e2d...44ac5a )
by De
27s
created

comics.py (1 issue)

1
#! /usr/bin/python3
2
# vim: set expandtab tabstop=4 shiftwidth=4 :
3
"""Module to retrieve webcomics"""
4
5
from comic_abstract import GenericComic, get_date_for_comic
6
import re
7
from datetime import date, timedelta
8
import datetime
9
from urlfunctions import get_soup_at_url, urljoin_wrapper,\
10
    convert_iri_to_plain_ascii_uri, load_json_at_url, urlopen_wrapper
11
import json
12
import locale
13
import urllib
14
15
DEFAULT_LOCAL = 'en_GB.UTF-8'
16
17
18
class Xkcd(GenericComic):
19
    """Class to retrieve Xkcd comics."""
20
    name = 'xkcd'
21
    long_name = 'xkcd'
22
    url = 'http://xkcd.com'
23
24
    @classmethod
25
    def get_next_comic(cls, last_comic):
26
        """Generator to get the next comic. Implementation of GenericComic's abstract method."""
27
        json_url = urljoin_wrapper(cls.url, 'info.0.json')
28
        first_num = last_comic['num'] if last_comic else 0
29
        last_num = load_json_at_url(json_url)['num']
30
31
        for num in range(first_num + 1, last_num + 1):
32
            comic = cls.get_comic_info(num)
33
            if comic is not None:
34
                yield comic
35
36
    @classmethod
37
    def get_comic_info(cls, num):
38
        """Get information about a particular comics."""
39
        if num == 404:
40
            return None
41
        json_url = urljoin_wrapper(cls.url, '%d/info.0.json' % num)
42
        comic_json = load_json_at_url(json_url)
43
        assert comic_json['num'] == num, json_url
44
        return {
45
            'json_url': json_url,
46
            'num': num,
47
            'url': urljoin_wrapper(cls.url, str(num)),
48
            'prefix': '%d-' % num,
49
            'img': [comic_json['img']],
50
            'day': int(comic_json['day']),
51
            'month': int(comic_json['month']),
52
            'year': int(comic_json['year']),
53
            'link': comic_json['link'],
54
            'news': comic_json['news'],
55
            'safe_title': comic_json['safe_title'],
56
            'transcript': comic_json['transcript'],
57
            'alt': comic_json['alt'],
58
            'title': comic_json['title'],
59
        }
60
61
62
# Helper functions corresponding to get_url_from_link/get_url_from_archive_element
63
64
65
@classmethod
66
def get_href(cls, link):
67
    """Implementation of get_url_from_link/get_url_from_archive_element."""
68
    return link['href']
69
70
71
@classmethod
72
def join_cls_url_to_href(cls, link):
73
    """Implementation of get_url_from_link/get_url_from_archive_element."""
74
    return urljoin_wrapper(cls.url, link['href'])
75
76
77
class GenericNavigableComic(GenericComic):
78
    """Generic class for "navigable" comics : with first/next arrows.
79
80
    This class applies to comic where previous and next comics can be
81
    accessed from a given comic. Once given a starting point (either
82
    the first comic or the last comic retrieved), it will handle the
83
    navigation, the retrieval of the soup object and the setting of
84
    the 'url' attribute on retrieved comics. This limits a lot the
85
    amount of boilerplate code in the different implementation classes.
86
87
    The method `get_next_comic` methods is implemented in terms of new
88
    more specialized methods to be implemented/overridden:
89
        - get_first_comic_link
90
        - get_navi_link
91
        - get_comic_info
92
        - get_url_from_link
93
    """
94
    _categories = ('NAVIGABLE', )
95
96
    @classmethod
97
    def get_first_comic_link(cls):
98
        """Get link to first comics.
99
100
        Sometimes this can be retrieved of any comic page, sometimes on
101
        the archive page, sometimes it doesn't exist at all and one has
102
        to iterate backward to find it before hardcoding the result found.
103
        """
104
        raise NotImplementedError
105
106
    @classmethod
107
    def get_navi_link(cls, last_soup, next_):
108
        """Get link to next (or previous - for dev purposes) comic."""
109
        raise NotImplementedError
110
111
    @classmethod
112
    def get_comic_info(cls, soup, link):
113
        """Get information about a particular comics."""
114
        raise NotImplementedError
115
116
    @classmethod
117
    def get_url_from_link(cls, link):
118
        """Get url corresponding to a link. Default implementation is similar to get_href."""
119
        return link['href']
120
121
    @classmethod
122
    def get_next_link(cls, last_soup):
123
        """Get link to next comic."""
124
        link = cls.get_navi_link(last_soup, True)
125
        cls.log("Next link is %s" % link)
126
        return link
127
128
    @classmethod
129
    def get_prev_link(cls, last_soup):
130
        """Get link to previous comic."""
131
        link = cls.get_navi_link(last_soup, False)
132
        cls.log("Prev link is %s" % link)
133
        return link
134
135
    @classmethod
136
    def get_next_comic(cls, last_comic):
137
        """Generic implementation of get_next_comic for navigable comics."""
138
        url = last_comic['url'] if last_comic else None
139
        cls.log("starting 'get_next_comic' from %s" % url)
140
        next_comic = \
141
            cls.get_next_link(get_soup_at_url(url)) \
142
            if url else \
143
            cls.get_first_comic_link()
144
        cls.log("next/first comic will be %s (url is %s)" % (str(next_comic), url))
145
        # cls.check_navigation(url)
146
        while next_comic:
147
            prev_url, url = url, cls.get_url_from_link(next_comic)
148
            if prev_url == url:
149
                cls.log("got same url %s" % url)
150
                break
151
            cls.log("about to get %s (%s)" % (url, str(next_comic)))
152
            soup = get_soup_at_url(url)
153
            comic = cls.get_comic_info(soup, next_comic)
154
            if comic is not None:
155
                assert 'url' not in comic
156
                comic['url'] = url
157
                yield comic
158
            next_comic = cls.get_next_link(soup)
159
            cls.log("next comic will be %s" % str(next_comic))
160
161
    @classmethod
162
    def check_first_link(cls):
163
        """Check that navigation to first comic seems to be working - for dev purposes."""
164
        cls.log("about to check first link")
165
        ok = True
166
        firstlink = cls.get_first_comic_link()
167
        if firstlink is None:
168
            print("From %s : no first link" % cls.url)
169
            ok = False
170
        else:
171
            firsturl = cls.get_url_from_link(firstlink)
172
            try:
173
                get_soup_at_url(firsturl)
174
            except urllib.error.HTTPError:
175
                print("From %s : invalid first url" % cls.url)
176
                ok = False
177
        cls.log("checked first link -> returned %d" % ok)
178
        return ok
179
180
    @classmethod
181
    def check_prev_next_links(cls, url):
182
        """Check that navigation to prev/next from a given URL seems to be working - for dev purposes."""
183
        cls.log("about to check prev/next from %s" % url)
184
        ok = True
185
        if url is None:
186
            prevlink, nextlink = None, None
187
        else:
188
            soup = get_soup_at_url(url)
189
            prevlink, nextlink = cls.get_prev_link(soup), cls.get_next_link(soup)
190
        if prevlink is None and nextlink is None:
191
            print("From %s : no previous nor next" % url)
192
            ok = False
193
        else:
194
            if prevlink:
195
                prevurl = cls.get_url_from_link(prevlink)
196
                prevsoup = get_soup_at_url(prevurl)
197
                prevnextlink = cls.get_next_link(prevsoup)
198
                prevnext = cls.get_url_from_link(prevnextlink) if prevnextlink is not None else "NO URL"
199
                if prevnext != url:
200
                    print("From %s, going backward then forward leads to %s" % (url, prevnext))
201
                    ok = False
202
            if nextlink:
203
                nexturl = cls.get_url_from_link(nextlink)
204
                if nexturl != url:
205
                    nextsoup = get_soup_at_url(nexturl)
206
                    nextprevlink = cls.get_prev_link(nextsoup)
207
                    nextprev = cls.get_url_from_link(nextprevlink) if nextprevlink is not None else "NO URL"
208
                    if nextprev != url:
209
                        print("From %s, going forward then backward leads to %s" % (url, nextprev))
210
                        ok = False
211
        cls.log("checked prev/next from %s -> returned %d" % (url, ok))
212
        return ok
213
214
    @classmethod
215
    def check_navigation(cls, url):
216
        """Check that navigation functions seem to be working - for dev purposes."""
217
        cls.log("about to check navigation from %s" % url)
218
        first = cls.check_first_link()
219
        prevnext = cls.check_prev_next_links(url)
220
        ok = first and prevnext
221
        cls.log("checked navigation from %s -> returned %d" % (url, ok))
222
        return ok
223
224
225
class GenericListableComic(GenericComic):
226
    """Generic class for "listable" comics : with a list of comics (aka 'archive')
227
228
    The method `get_next_comic` methods is implemented in terms of new
229
    more specialized methods to be implemented/overridden:
230
        - get_archive_elements
231
        - get_url_from_archive_element
232
        - get_comic_info
233
    """
234
    _categories = ('LISTABLE', )
235
236
    @classmethod
237
    def get_archive_elements(cls):
238
        """Get the archive elements (iterable)."""
239
        raise NotImplementedError
240
241
    @classmethod
242
    def get_url_from_archive_element(cls, archive_elt):
243
        """Get url corresponding to an archive element."""
244
        raise NotImplementedError
245
246
    @classmethod
247
    def get_comic_info(cls, soup, archive_elt):
248
        """Get information about a particular comics."""
249
        raise NotImplementedError
250
251
    @classmethod
252
    def get_next_comic(cls, last_comic):
253
        """Generic implementation of get_next_comic for listable comics."""
254
        waiting_for_url = last_comic['url'] if last_comic else None
255
        archive_elts = list(cls.get_archive_elements())
256
        for archive_elt in archive_elts:
257
            url = cls.get_url_from_archive_element(archive_elt)
258
            cls.log("considering %s" % url)
259
            if waiting_for_url is None:
260
                cls.log("about to get %s (%s)" % (url, str(archive_elt)))
261
                soup = get_soup_at_url(url)
262
                comic = cls.get_comic_info(soup, archive_elt)
263
                if comic is not None:
264
                    assert 'url' not in comic
265
                    comic['url'] = url
266
                    yield comic
267
            elif waiting_for_url == url:
268
                waiting_for_url = None
269
        if waiting_for_url is not None:
270
            print("Did not find %s in the %d comics: there might be a problem" %
271
                  (waiting_for_url, len(archive_elts)))
272
273
# Helper functions corresponding to get_first_comic_link/get_navi_link
274
275
276
@classmethod
277
def get_link_rel_next(cls, last_soup, next_):
278
    """Implementation of get_navi_link."""
279
    return last_soup.find('link', rel='next' if next_ else 'prev')
280
281
282
@classmethod
283
def get_a_rel_next(cls, last_soup, next_):
284
    """Implementation of get_navi_link."""
285
    return last_soup.find('a', rel='next' if next_ else 'prev')
286
287
288
@classmethod
289
def get_a_navi_navinext(cls, last_soup, next_):
290
    """Implementation of get_navi_link."""
291
    # ComicPress (WordPress plugin)
292
    return last_soup.find('a', class_='navi navi-next' if next_ else 'navi navi-prev')
293
294
295
@classmethod
296
def get_a_navi_comicnavnext_navinext(cls, last_soup, next_):
297
    """Implementation of get_navi_link."""
298
    return last_soup.find('a', class_='navi comic-nav-next navi-next' if next_ else 'navi comic-nav-previous navi-prev')
299
300
301
@classmethod
302
def get_a_comicnavbase_comicnavnext(cls, last_soup, next_):
303
    """Implementation of get_navi_link."""
304
    return last_soup.find('a', class_='comic-nav-base comic-nav-next' if next_ else 'comic-nav-base comic-nav-previous')
305
306
307
@classmethod
308
def get_a_navi_navifirst(cls):
309
    """Implementation of get_first_comic_link."""
310
    # ComicPress (WordPress plugin)
311
    return get_soup_at_url(cls.url).find('a', class_='navi navi-first')
312
313
314
@classmethod
315
def get_div_navfirst_a(cls):
316
    """Implementation of get_first_comic_link."""
317
    return get_soup_at_url(cls.url).find('div', class_="nav-first").find('a')
318
319
320
@classmethod
321
def get_a_comicnavbase_comicnavfirst(cls):
322
    """Implementation of get_first_comic_link."""
323
    return get_soup_at_url(cls.url).find('a', class_='comic-nav-base comic-nav-first')
324
325
326
@classmethod
327
def simulate_first_link(cls):
328
    """Implementation of get_first_comic_link creating a link-like object from
329
    an URL provided by the class.
330
331
    Note: The first URL can easily be found using :
332
    `get_first_comic_link = navigate_to_first_comic`.
333
    """
334
    return {'href': cls.first_url}
335
336
337
@classmethod
338
def navigate_to_first_comic(cls):
339
    """Implementation of get_first_comic_link navigating from a user provided
340
    URL to the first comic.
341
342
    Sometimes, the first comic cannot be reached directly so to start
343
    from the first comic one has to go to the previous comic until
344
    there is no previous comics. Once this URL is reached, it
345
    is better to hardcode it but for development purposes, it
346
    is convenient to have an automatic way to find it.
347
348
    Then, the URL found can easily be used via `simulate_first_link`.
349
    """
350
    try:
351
        url = cls.first_url
352
    except AttributeError:
353
        url = input("Get starting URL: ")
354
    print(url)
355
    comic = cls.get_prev_link(get_soup_at_url(url))
356
    while comic:
357
        url = cls.get_url_from_link(comic)
358
        print(url)
359
        comic = cls.get_prev_link(get_soup_at_url(url))
360
    return {'href': url}
361
362
363
class GenericEmptyComic(GenericComic):
364
    """Generic class for comics where nothing is to be done.
365
366
    It can be useful to deactivate temporarily comics that do not work
367
    properly by replacing `def MyComic(GenericWhateverComic)` with
368
    `def MyComic(GenericEmptyComic, GenericWhateverComic)`."""
369
    _categories = ('EMPTY', )
370
371
    @classmethod
372
    def get_next_comic(cls, last_comic):
373
        """Implementation of get_next_comic returning no comics."""
374
        cls.log("comic is considered as empty - returning no comic")
375
        return []
376
377
378
class GenericComicNotWorking(GenericEmptyComic):
379
    """Subclass of GenericEmptyComic used when comic is not working.
380
381
    This is more explicit than GenericEmptyComic as it hilights that
382
    only the implementation is not working and it can be fixed."""
383
    _categories = ('NOTWORKING', )
384
385
386
class GenericUnavailableComic(GenericEmptyComic):
387
    """Subclass of GenericEmptyComic used when a comic is not available.
388
389
    This is more explicit than GenericEmptyComic as it hilights that
390
    the source of the comic is not available but we expect it to be back
391
    soonish. See also GenericDeletedComic."""
392
    _categories = ('UNAVAILABLE', )
393
394
395
class GenericDeletedComic(GenericEmptyComic):
396
    """Subclass of GenericEmptyComic used when a comic does not exist anymore.
397
398
    This is more explicit than GenericEmptyComic as it hilights that
399
    the source of the comic does not exist anymore and it probably cannot
400
    be fixed. Corresponding classes are kept as we can still use the
401
    downloaded data. See also GenericUnavailableComic."""
402
    _categories = ('DELETED', )
403
404
405
class ExtraFabulousComics(GenericNavigableComic):
406
    """Class to retrieve Extra Fabulous Comics."""
407
    # Also on https://extrafabulouscomics.tumblr.com
408
    name = 'efc'
409
    long_name = 'Extra Fabulous Comics'
410
    url = 'http://extrafabulouscomics.com'
411
    _categories = ('EFC', )
412
    get_navi_link = get_link_rel_next
413
    get_first_comic_link = simulate_first_link
414
    first_url = 'http://extrafabulouscomics.com/comic/buttfly/'
415
416
    @classmethod
417
    def get_comic_info(cls, soup, link):
418
        """Get information about a particular comics."""
419
        img_src_re = re.compile('^%s/wp-content/uploads/' % cls.url)
420
        imgs = soup.find_all('img', src=img_src_re)
421
        title = soup.find('meta', property='og:title')['content']
422
        date_str = soup.find('meta', property='article:published_time')['content'][:10]
423
        day = string_to_date(date_str, "%Y-%m-%d")
424
        return {
425
            'title': title,
426
            'img': [i['src'] for i in imgs],
427
            'month': day.month,
428
            'year': day.year,
429
            'day': day.day,
430
            'prefix': title + '-'
431
        }
432
433
434
class GenericLeMondeBlog(GenericNavigableComic):
435
    """Generic class to retrieve comics from Le Monde blogs."""
436
    _categories = ('LEMONDE', 'FRANCAIS')
437
    get_navi_link = get_link_rel_next
438
    get_first_comic_link = simulate_first_link
439
    first_url = NotImplemented
440
441
    @classmethod
442
    def get_comic_info(cls, soup, link):
443
        """Get information about a particular comics."""
444
        url2 = soup.find('link', rel='shortlink')['href']
445
        title = soup.find('meta', property='og:title')['content']
446
        date_str = soup.find("span", class_="entry-date").string
447
        day = string_to_date(date_str, "%d %B %Y", "fr_FR.utf8")
448
        imgs = soup.find_all('meta', property='og:image')
449
        return {
450
            'title': title,
451
            'url2': url2,
452
            'img': [convert_iri_to_plain_ascii_uri(i['content']) for i in imgs],
453
            'month': day.month,
454
            'year': day.year,
455
            'day': day.day,
456
        }
457
458
459
class ZepWorld(GenericLeMondeBlog):
460
    """Class to retrieve Zep World comics."""
461
    name = "zep"
462
    long_name = "Zep World"
463
    url = "http://zepworld.blog.lemonde.fr"
464
    first_url = "http://zepworld.blog.lemonde.fr/2014/10/31/bientot-le-blog-de-zep/"
465
466
467
class Vidberg(GenericLeMondeBlog):
468
    """Class to retrieve Vidberg comics."""
469
    name = 'vidberg'
470
    long_name = "Vidberg - l'actu en patates"
471
    url = "http://vidberg.blog.lemonde.fr"
472
    # Not the first but I didn't find an efficient way to retrieve it
473
    first_url = "http://vidberg.blog.lemonde.fr/2012/02/09/revue-de-campagne-la-campagne-du-modem-semballe/"
474
475
476
class Plantu(GenericLeMondeBlog):
477
    """Class to retrieve Plantu comics."""
478
    name = 'plantu'
479
    long_name = "Plantu"
480
    url = "http://plantu.blog.lemonde.fr"
481
    first_url = "http://plantu.blog.lemonde.fr/2014/10/28/stress-test-a-bruxelles/"
482
483
484
class XavierGorce(GenericLeMondeBlog):
485
    """Class to retrieve Xavier Gorce comics."""
486
    name = 'gorce'
487
    long_name = "Xavier Gorce"
488
    url = "http://xaviergorce.blog.lemonde.fr"
489
    first_url = "http://xaviergorce.blog.lemonde.fr/2015/01/09/distinction/"
490
491
492
class CartooningForPeace(GenericLeMondeBlog):
493
    """Class to retrieve Cartooning For Peace comics."""
494
    name = 'forpeace'
495
    long_name = "Cartooning For Peace"
496
    url = "http://cartooningforpeace.blog.lemonde.fr"
497
    first_url = "http://cartooningforpeace.blog.lemonde.fr/2014/12/15/bado/"
498
499
500
class Aurel(GenericLeMondeBlog):
501
    """Class to retrieve Aurel comics."""
502
    name = 'aurel'
503
    long_name = "Aurel"
504
    url = "http://aurel.blog.lemonde.fr"
505
    first_url = "http://aurel.blog.lemonde.fr/2014/09/29/le-senat-repasse-a-droite/"
506
507
508
class LesCulottees(GenericLeMondeBlog):
509
    """Class to retrieve Les Culottees comics."""
510
    name = 'culottees'
511
    long_name = 'Les Culottees'
512
    url = "http://lesculottees.blog.lemonde.fr"
513
    first_url = "http://lesculottees.blog.lemonde.fr/2016/01/11/clementine-delait-femme-a-barbe/"
514
515
516
class UneAnneeAuLycee(GenericLeMondeBlog):
517
    """Class to retrieve Une Annee Au Lycee comics."""
518
    name = 'lycee'
519
    long_name = 'Une Annee au Lycee'
520
    url = 'http://uneanneeaulycee.blog.lemonde.fr'
521
    first_url = "http://uneanneeaulycee.blog.lemonde.fr/2016/06/13/la-semaine-du-bac-est-arrivee/"
522
523
524 View Code Duplication
class Rall(GenericComicNotWorking, GenericNavigableComic):
525
    """Class to retrieve Ted Rall comics."""
526
    # Also on http://www.gocomics.com/tedrall
527
    name = 'rall'
528
    long_name = "Ted Rall"
529
    url = "http://rall.com/comic"
530
    _categories = ('RALL', )
531
    get_navi_link = get_link_rel_next
532
    get_first_comic_link = simulate_first_link
533
    # Not the first but I didn't find an efficient way to retrieve it
534
    first_url = "http://rall.com/2014/01/30/los-angeles-times-cartoon-well-miss-those-california-flowers"
535
536
    @classmethod
537
    def get_comic_info(cls, soup, link):
538
        """Get information about a particular comics."""
539
        title = soup.find('meta', property='og:title')['content']
540
        author = soup.find("span", class_="author vcard").find("a").string
541
        date_str = soup.find("span", class_="entry-date").string
542
        day = string_to_date(date_str, "%B %d, %Y")
543
        desc = soup.find('meta', property='og:description')['content']
544
        imgs = soup.find('div', class_='entry-content').find_all('img')
545
        imgs = imgs[:-7]  # remove social media buttons
546
        return {
547
            'title': title,
548
            'author': author,
549
            'month': day.month,
550
            'year': day.year,
551
            'day': day.day,
552
            'description': desc,
553
            'img': [i['src'] for i in imgs],
554
        }
555
556
557
class Dilem(GenericNavigableComic):
558
    """Class to retrieve Ali Dilem comics."""
559
    name = 'dilem'
560
    long_name = 'Ali Dilem'
561
    url = 'http://information.tv5monde.com/dilem'
562
    _categories = ('FRANCAIS', )
563
    get_url_from_link = join_cls_url_to_href
564
    get_first_comic_link = simulate_first_link
565
    first_url = "http://information.tv5monde.com/dilem/2004-06-26"
566
567
    @classmethod
568
    def get_navi_link(cls, last_soup, next_):
569
        """Get link to next or previous comic."""
570
        # prev is next / next is prev
571
        li = last_soup.find('li', class_='prev' if next_ else 'next')
572
        return li.find('a') if li else None
573
574
    @classmethod
575
    def get_comic_info(cls, soup, link):
576
        """Get information about a particular comics."""
577
        short_url = soup.find('link', rel='shortlink')['href']
578
        title = soup.find('meta', attrs={'name': 'twitter:title'})['content']
579
        imgs = soup.find_all('meta', property='og:image')
580
        date_str = soup.find('span', property='dc:date')['content']
581
        date_str = date_str[:10]
582
        day = string_to_date(date_str, "%Y-%m-%d")
583
        return {
584
            'short_url': short_url,
585
            'title': title,
586
            'img': [i['content'] for i in imgs],
587
            'day': day.day,
588
            'month': day.month,
589
            'year': day.year,
590
        }
591
592
593
class SpaceAvalanche(GenericNavigableComic):
594
    """Class to retrieve Space Avalanche comics."""
595
    name = 'avalanche'
596
    long_name = 'Space Avalanche'
597
    url = 'http://www.spaceavalanche.com'
598
    get_navi_link = get_link_rel_next
599
600
    @classmethod
601
    def get_first_comic_link(cls):
602
        """Get link to first comics."""
603
        return {'href': "http://www.spaceavalanche.com/2009/02/02/irish-sea/", 'title': "Irish Sea"}
604
605
    @classmethod
606
    def get_comic_info(cls, soup, link):
607
        """Get information about a particular comics."""
608
        url_date_re = re.compile('.*/([0-9]*)/([0-9]*)/([0-9]*)/.*$')
609
        title = link['title']
610
        url = cls.get_url_from_link(link)
611
        year, month, day = [int(s)
612
                            for s in url_date_re.match(url).groups()]
613
        imgs = soup.find("div", class_="entry").find_all("img")
614
        return {
615
            'title': title,
616
            'day': day,
617
            'month': month,
618
            'year': year,
619
            'img': [i['src'] for i in imgs],
620
        }
621
622
623
class ZenPencils(GenericNavigableComic):
624
    """Class to retrieve ZenPencils comics."""
625
    # Also on http://zenpencils.tumblr.com
626
    # Also on http://www.gocomics.com/zen-pencils
627
    name = 'zenpencils'
628
    long_name = 'Zen Pencils'
629
    url = 'http://zenpencils.com'
630
    _categories = ('ZENPENCILS', )
631
    get_navi_link = get_link_rel_next
632
    get_first_comic_link = simulate_first_link
633
    first_url = "http://zenpencils.com/comic/1-ralph-waldo-emerson-make-them-cry/"
634
635
    @classmethod
636
    def get_comic_info(cls, soup, link):
637
        """Get information about a particular comics."""
638
        imgs = soup.find('div', id='comic').find_all('img')
639
        # imgs2 = soup.find_all('meta', property='og:image')
640
        post = soup.find('div', class_='post-content')
641
        author = post.find("span", class_="post-author").find("a").string
642
        title = soup.find('h2', class_='post-title').string
643
        date_str = post.find('span', class_='post-date').string
644
        day = string_to_date(date_str, "%B %d, %Y")
645
        assert imgs
646
        assert all(i['alt'] == i['title'] for i in imgs)
647
        assert all(i['alt'] in (title, "") for i in imgs)
648
        return {
649
            'title': title,
650
            'author': author,
651
            'day': day.day,
652
            'month': day.month,
653
            'year': day.year,
654
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
655
        }
656
657
658
class ItsTheTie(GenericDeletedComic, GenericNavigableComic):
659
    """Class to retrieve It's the tie comics."""
660
    # Also on http://itsthetie.tumblr.com
661
    # Also on https://tapastic.com/series/itsthetie
662
    name = 'tie'
663
    long_name = "It's the tie"
664
    url = "http://itsthetie.com"
665
    _categories = ('TIE', )
666
    get_first_comic_link = get_div_navfirst_a
667
    get_navi_link = get_a_rel_next
668
669
    @classmethod
670
    def get_comic_info(cls, soup, link):
671
        """Get information about a particular comics."""
672
        title = soup.find('h1', class_='comic-title').find('a').string
673
        date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string
674
        day = string_to_date(date_str, "%B %d, %Y")
675
        # Bonus images may or may not be in meta og:image.
676
        imgs = soup.find_all('meta', property='og:image')
677
        imgs_src = [i['content'] for i in imgs]
678
        bonus = soup.find_all('img', attrs={'data-oversrc': True})
679
        bonus_src = [b['data-oversrc'] for b in bonus]
680
        all_imgs_src = imgs_src + [s for s in bonus_src if s not in imgs_src]
681
        all_imgs_src = [s for s in all_imgs_src if not s.endswith("/2016/01/bonus-panel.png")]
682
        tag_meta = soup.find('meta', property='article:tag')
683
        tags = tag_meta['content'] if tag_meta else ""
684
        return {
685
            'title': title,
686
            'month': day.month,
687
            'year': day.year,
688
            'day': day.day,
689
            'img': all_imgs_src,
690
            'tags': tags,
691
        }
692
693
694 View Code Duplication
class PenelopeBagieu(GenericNavigableComic):
695
    """Class to retrieve comics from Penelope Bagieu's blog."""
696
    name = 'bagieu'
697
    long_name = 'Ma vie est tout a fait fascinante (Bagieu)'
698
    url = 'http://www.penelope-jolicoeur.com'
699
    _categories = ('FRANCAIS', )
700
    get_navi_link = get_link_rel_next
701
    get_first_comic_link = simulate_first_link
702
    first_url = 'http://www.penelope-jolicoeur.com/2007/02/ma-vie-mon-oeuv.html'
703
704
    @classmethod
705
    def get_comic_info(cls, soup, link):
706
        """Get information about a particular comics."""
707
        date_str = soup.find('h2', class_='date-header').string
708
        day = string_to_date(date_str, "%A %d %B %Y", "fr_FR.utf8")
709
        imgs = soup.find('div', class_='entry-body').find_all('img')
710
        title = soup.find('h3', class_='entry-header').string
711
        return {
712
            'title': title,
713
            'img': [i['src'] for i in imgs],
714
            'month': day.month,
715
            'year': day.year,
716
            'day': day.day,
717
        }
718
719
720 View Code Duplication
class OneOneOneOneComic(GenericComicNotWorking, GenericNavigableComic):
721
    """Class to retrieve 1111 Comics."""
722
    # Also on http://comics1111.tumblr.com
723
    # Also on https://tapastic.com/series/1111-Comics
724
    name = '1111'
725
    long_name = '1111 Comics'
726
    url = 'http://www.1111comics.me'
727
    _categories = ('ONEONEONEONE', )
728
    get_first_comic_link = get_div_navfirst_a
729
    get_navi_link = get_link_rel_next
730
731
    @classmethod
732
    def get_comic_info(cls, soup, link):
733
        """Get information about a particular comics."""
734
        title = soup.find('h1', class_='comic-title').find('a').string
735
        date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string
736
        day = string_to_date(date_str, "%B %d, %Y")
737
        imgs = soup.find_all('meta', property='og:image')
738
        return {
739
            'title': title,
740
            'month': day.month,
741
            'year': day.year,
742
            'day': day.day,
743
            'img': [i['content'] for i in imgs],
744
        }
745
746
747 View Code Duplication
class AngryAtNothing(GenericDeletedComic, GenericNavigableComic):
748
    """Class to retrieve Angry at Nothing comics."""
749
    # Also on http://tapastic.com/series/Comics-yeah-definitely-comics-
750
    # Also on http://angryatnothing.tumblr.com
751
    name = 'angry'
752
    long_name = 'Angry At Nothing'
753
    url = 'http://www.angryatnothing.net'
754
    get_first_comic_link = get_div_navfirst_a
755
    get_navi_link = get_a_rel_next
756
757
    @classmethod
758
    def get_comic_info(cls, soup, link):
759
        """Get information about a particular comics."""
760
        title = soup.find('h1', class_='comic-title').find('a').string
761
        date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string
762
        day = string_to_date(date_str, "%B %d, %Y")
763
        imgs = soup.find_all('meta', property='og:image')
764
        return {
765
            'title': title,
766
            'month': day.month,
767
            'year': day.year,
768
            'day': day.day,
769
            'img': [i['content'] for i in imgs],
770
        }
771
772
773
class NeDroid(GenericNavigableComic):
774
    """Class to retrieve NeDroid comics."""
775
    name = 'nedroid'
776
    long_name = 'NeDroid'
777
    url = 'http://nedroid.com'
778
    get_first_comic_link = get_div_navfirst_a
779
    get_navi_link = get_link_rel_next
780
    get_url_from_link = join_cls_url_to_href
781
782 View Code Duplication
    @classmethod
783
    def get_comic_info(cls, soup, link):
784
        """Get information about a particular comics."""
785
        short_url_re = re.compile('^%s/\\?p=([0-9]*)' % cls.url)
786
        short_url = cls.get_url_from_link(soup.find('link', rel='shortlink'))
787
        num = int(short_url_re.match(short_url).groups()[0])
788
        imgs = soup.find('div', id='comic').find_all('img')
789
        assert len(imgs) == 1, imgs
790
        title = imgs[0]['alt']
791
        title2 = imgs[0]['title']
792
        return {
793
            'short_url': short_url,
794
            'title': title,
795
            'title2': title2,
796
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
797
            'num': num,
798
        }
799
800
801
class Garfield(GenericNavigableComic):
802
    """Class to retrieve Garfield comics."""
803
    # Also on http://www.gocomics.com/garfield
804
    name = 'garfield'
805
    long_name = 'Garfield'
806
    url = 'https://garfield.com'
807
    _categories = ('GARFIELD', )
808
    get_first_comic_link = simulate_first_link
809
    first_url = 'https://garfield.com/comic/1978/06/19'
810
811
    @classmethod
812
    def get_navi_link(cls, last_soup, next_):
813
        """Get link to next or previous comic."""
814
        return last_soup.find('a', class_='comic-arrow-right' if next_ else 'comic-arrow-left')
815
816
    @classmethod
817
    def get_comic_info(cls, soup, link):
818
        """Get information about a particular comics."""
819
        url = cls.get_url_from_link(link)
820
        date_re = re.compile('^%s/comic/([0-9]*)/([0-9]*)/([0-9]*)' % cls.url)
821
        year, month, day = [int(s) for s in date_re.match(url).groups()]
822
        imgs = soup.find('div', class_='comic-display').find_all('img', class_='img-responsive')
823
        return {
824
            'month': month,
825
            'year': year,
826
            'day': day,
827
            'img': [i['src'] for i in imgs],
828
        }
829
830
831 View Code Duplication
class Dilbert(GenericNavigableComic):
832
    """Class to retrieve Dilbert comics."""
833
    # Also on http://www.gocomics.com/dilbert-classics
834
    name = 'dilbert'
835
    long_name = 'Dilbert'
836
    url = 'http://dilbert.com'
837
    get_url_from_link = join_cls_url_to_href
838
    get_first_comic_link = simulate_first_link
839
    first_url = 'http://dilbert.com/strip/1989-04-16'
840
841
    @classmethod
842
    def get_navi_link(cls, last_soup, next_):
843
        """Get link to next or previous comic."""
844
        link = last_soup.find('div', class_='nav-comic nav-right' if next_ else 'nav-comic nav-left')
845
        return link.find('a') if link else None
846
847
    @classmethod
848
    def get_comic_info(cls, soup, link):
849
        """Get information about a particular comics."""
850
        title = soup.find('meta', property='og:title')['content']
851
        imgs = soup.find_all('meta', property='og:image')
852
        desc = soup.find('meta', property='og:description')['content']
853
        date_str = soup.find('meta', property='article:publish_date')['content']
854
        day = string_to_date(date_str, "%B %d, %Y")
855
        author = soup.find('meta', property='article:author')['content']
856
        tags = soup.find('meta', property='article:tag')['content']
857
        return {
858
            'title': title,
859
            'description': desc,
860
            'img': [i['content'] for i in imgs],
861
            'author': author,
862
            'tags': tags,
863
            'day': day.day,
864
            'month': day.month,
865
            'year': day.year
866
        }
867
868
869
class VictimsOfCircumsolar(GenericDeletedComic, GenericNavigableComic):
870
    """Class to retrieve VictimsOfCircumsolar comics."""
871
    # Also on https://victimsofcomics.tumblr.com
872
    name = 'circumsolar'
873
    long_name = 'Victims Of Circumsolar'
874
    url = 'http://www.victimsofcircumsolar.com'
875
    get_navi_link = get_a_navi_comicnavnext_navinext
876
    get_first_comic_link = simulate_first_link
877
    first_url = 'http://www.victimsofcircumsolar.com/comic/modern-addiction'
878
879
    @classmethod
880
    def get_comic_info(cls, soup, link):
881
        """Get information about a particular comics."""
882
        # Date is on the archive page
883
        title = soup.find_all('meta', property='og:title')[-1]['content']
884
        desc = soup.find_all('meta', property='og:description')[-1]['content']
885
        imgs = soup.find('div', id='comic').find_all('img')
886
        assert all(i['title'] == i['alt'] == title for i in imgs)
887
        return {
888
            'title': title,
889
            'description': desc,
890
            'img': [i['src'] for i in imgs],
891
        }
892
893
894
class ThreeWordPhrase(GenericNavigableComic):
895
    """Class to retrieve Three Word Phrase comics."""
896
    # Also on http://www.threewordphrase.tumblr.com
897
    name = 'threeword'
898
    long_name = 'Three Word Phrase'
899
    url = 'http://threewordphrase.com'
900
    get_url_from_link = join_cls_url_to_href
901
902
    @classmethod
903
    def get_first_comic_link(cls):
904
        """Get link to first comics."""
905
        return get_soup_at_url(cls.url).find('img', src='/firstlink.gif').parent
906
907
    @classmethod
908
    def get_navi_link(cls, last_soup, next_):
909
        """Get link to next or previous comic."""
910
        link = last_soup.find('img', src='/nextlink.gif' if next_ else '/prevlink.gif').parent
911
        return None if link.get('href') is None else link
912
913
    @classmethod
914
    def get_comic_info(cls, soup, link):
915
        """Get information about a particular comics."""
916
        title = soup.find('title')
917
        imgs = [img for img in soup.find_all('img')
918
                if not img['src'].endswith(
919
                    ('link.gif', '32.png', 'twpbookad.jpg',
920
                     'merchad.jpg', 'header.gif', 'tipjar.jpg'))]
921
        return {
922
            'title': title.string if title else None,
923
            'title2': '  '.join(img.get('alt') for img in imgs if img.get('alt')),
924
            'img': [urljoin_wrapper(cls.url, img['src']) for img in imgs],
925
        }
926
927
928
class DeadlyPanel(GenericComicNotWorking, GenericNavigableComic):  # Not working on my machine
929
    """Class to retrieve Deadly Panel comics."""
930
    # Also on https://tapastic.com/series/deadlypanel
931
    # Also on https://deadlypanel.tumblr.com
932
    name = 'deadly'
933
    long_name = 'Deadly Panel'
934
    url = 'http://www.deadlypanel.com'
935
    get_first_comic_link = get_a_navi_navifirst
936
    get_navi_link = get_a_navi_comicnavnext_navinext
937
938
    @classmethod
939
    def get_comic_info(cls, soup, link):
940
        """Get information about a particular comics."""
941
        imgs = soup.find('div', id='comic').find_all('img')
942
        assert all(i['alt'] == i['title'] for i in imgs)
943
        return {
944
            'img': [i['src'] for i in imgs],
945
        }
946
947
948 View Code Duplication
class TheGentlemanArmchair(GenericNavigableComic):
949
    """Class to retrieve The Gentleman Armchair comics."""
950
    name = 'gentlemanarmchair'
951
    long_name = 'The Gentleman Armchair'
952
    url = 'http://thegentlemansarmchair.com'
953
    get_first_comic_link = get_a_navi_navifirst
954
    get_navi_link = get_link_rel_next
955
956
    @classmethod
957
    def get_comic_info(cls, soup, link):
958
        """Get information about a particular comics."""
959
        title = soup.find('h2', class_='post-title').string
960
        author = soup.find("span", class_="post-author").find("a").string
961
        date_str = soup.find('span', class_='post-date').string
962
        day = string_to_date(date_str, "%B %d, %Y")
963
        imgs = soup.find('div', id='comic').find_all('img')
964
        return {
965
            'img': [i['src'] for i in imgs],
966
            'title': title,
967
            'author': author,
968
            'month': day.month,
969
            'year': day.year,
970
            'day': day.day,
971
        }
972
973
974 View Code Duplication
class ImogenQuest(GenericNavigableComic):
975
    """Class to retrieve Imogen Quest comics."""
976
    # Also on http://imoquest.tumblr.com
977
    name = 'imogen'
978
    long_name = 'Imogen Quest'
979
    url = 'http://imogenquest.net'
980
    get_first_comic_link = get_div_navfirst_a
981
    get_navi_link = get_a_rel_next
982
983
    @classmethod
984
    def get_comic_info(cls, soup, link):
985
        """Get information about a particular comics."""
986
        title = soup.find('h2', class_='post-title').string
987
        author = soup.find("span", class_="post-author").find("a").string
988
        date_str = soup.find('span', class_='post-date').string
989
        day = string_to_date(date_str, '%B %d, %Y')
990
        imgs = soup.find('div', class_='comicpane').find_all('img')
991
        assert all(i['alt'] == i['title'] for i in imgs)
992
        title2 = imgs[0]['title']
993
        return {
994
            'day': day.day,
995
            'month': day.month,
996
            'year': day.year,
997
            'img': [i['src'] for i in imgs],
998
            'title': title,
999
            'title2': title2,
1000
            'author': author,
1001
        }
1002
1003
1004
class MyExtraLife(GenericNavigableComic):
1005
    """Class to retrieve My Extra Life comics."""
1006
    name = 'extralife'
1007
    long_name = 'My Extra Life'
1008
    url = 'http://www.myextralife.com'
1009
    get_navi_link = get_link_rel_next
1010
1011
    @classmethod
1012
    def get_first_comic_link(cls):
1013
        """Get link to first comics."""
1014
        return get_soup_at_url(cls.url).find('a', class_='comic_nav_link first_comic_link')
1015
1016
    @classmethod
1017
    def get_comic_info(cls, soup, link):
1018
        """Get information about a particular comics."""
1019
        title = soup.find("h1", class_="comic_title").string
1020
        date_str = soup.find("span", class_="comic_date").string
1021
        day = string_to_date(date_str, "%B %d, %Y")
1022
        imgs = soup.find_all("img", class_="comic")
1023
        assert all(i['alt'] == i['title'] == title for i in imgs)
1024
        return {
1025
            'title': title,
1026
            'img': [i['src'] for i in imgs if i["src"]],
1027
            'day': day.day,
1028
            'month': day.month,
1029
            'year': day.year
1030
        }
1031
1032
1033
class SaturdayMorningBreakfastCereal(GenericNavigableComic):
1034
    """Class to retrieve Saturday Morning Breakfast Cereal comics."""
1035
    # Also on http://www.gocomics.com/saturday-morning-breakfast-cereal
1036
    # Also on http://smbc-comics.tumblr.com
1037
    name = 'smbc'
1038
    long_name = 'Saturday Morning Breakfast Cereal'
1039
    url = 'http://www.smbc-comics.com'
1040
    _categories = ('SMBC', )
1041
    get_navi_link = get_a_rel_next
1042
1043
    @classmethod
1044
    def get_first_comic_link(cls):
1045
        """Get link to first comics."""
1046
        return get_soup_at_url(cls.url).find('a', rel='start')
1047
1048
    @classmethod
1049
    def get_comic_info(cls, soup, link):
1050
        """Get information about a particular comics."""
1051
        image1 = soup.find('img', id='cc-comic')
1052
        image_url1 = image1['src']
1053
        aftercomic = soup.find('div', id='aftercomic')
1054
        image_url2 = aftercomic.find('img')['src'] if aftercomic else ''
1055
        imgs = [image_url1] + ([image_url2] if image_url2 else [])
1056
        date_str = soup.find('div', class_='cc-publishtime').contents[0]
1057
        day = string_to_date(date_str, "%B %d, %Y")
1058
        return {
1059
            'title': image1['title'],
1060
            'img': [convert_iri_to_plain_ascii_uri(urljoin_wrapper(cls.url, i)) for i in imgs],
1061
            'day': day.day,
1062
            'month': day.month,
1063
            'year': day.year
1064
        }
1065
1066
1067 View Code Duplication
class PerryBibleFellowship(GenericListableComic):  # Is now navigable too
1068
    """Class to retrieve Perry Bible Fellowship comics."""
1069
    name = 'pbf'
1070
    long_name = 'Perry Bible Fellowship'
1071
    url = 'http://pbfcomics.com'
1072
    get_url_from_archive_element = join_cls_url_to_href
1073
1074
    @classmethod
1075
    def get_archive_elements(cls):
1076
        soup = get_soup_at_url(cls.url)
1077
        thumbnails = soup.find('div', id='all_thumbnails')
1078
        return reversed(thumbnails.find_all('a'))
1079
1080
    @classmethod
1081
    def get_comic_info(cls, soup, link):
1082
        """Get information about a particular comics."""
1083
        name = soup.find('meta', property='og:title')['content']
1084
        imgs = soup.find_all('meta', property='og:image')
1085
        assert len(imgs) == 1, imgs
1086
        return {
1087
            'name': name,
1088
            'img': [i['content'] for i in imgs],
1089
        }
1090
1091
1092
class Mercworks(GenericNavigableComic):
1093
    """Class to retrieve Mercworks comics."""
1094
    # Also on http://mercworks.tumblr.com
1095
    name = 'mercworks'
1096
    long_name = 'Mercworks'
1097
    url = 'http://mercworks.net'
1098
    get_first_comic_link = get_a_comicnavbase_comicnavfirst
1099
    get_navi_link = get_link_rel_next
1100
1101
    @classmethod
1102
    def get_comic_info(cls, soup, link):
1103
        """Get information about a particular comics."""
1104
        title = soup.find('meta', property='og:title')['content']
1105
        metadesc = soup.find('meta', property='og:description')
1106
        desc = metadesc['content'] if metadesc else ""
1107
        date_str = soup.find('meta', property='article:published_time')['content'][:10]
1108
        day = string_to_date(date_str, "%Y-%m-%d")
1109
        imgs = soup.find_all('meta', property='og:image')
1110
        return {
1111
            'img': [i['content'] for i in imgs],
1112
            'title': title,
1113
            'desc': desc,
1114
            'day': day.day,
1115
            'month': day.month,
1116
            'year': day.year
1117
        }
1118
1119
1120
class BerkeleyMews(GenericListableComic):
1121
    """Class to retrieve Berkeley Mews comics."""
1122
    # Also on http://mews.tumblr.com
1123
    # Also on http://www.gocomics.com/berkeley-mews
1124
    name = 'berkeley'
1125
    long_name = 'Berkeley Mews'
1126
    url = 'http://www.berkeleymews.com'
1127
    _categories = ('BERKELEY', )
1128
    get_url_from_archive_element = get_href
1129
    comic_num_re = re.compile('%s/\\?p=([0-9]*)$' % url)
1130
1131
    @classmethod
1132
    def get_archive_elements(cls):
1133
        archive_url = urljoin_wrapper(cls.url, "?page_id=2")
1134
        return reversed(get_soup_at_url(archive_url).find_all('a', href=cls.comic_num_re))
1135
1136
    @classmethod
1137
    def get_comic_info(cls, soup, link):
1138
        """Get information about a particular comics."""
1139
        comic_date_re = re.compile('.*/([0-9]*)-([0-9]*)-([0-9]*)-.*')
1140
        url = cls.get_url_from_archive_element(link)
1141
        num = int(cls.comic_num_re.match(url).groups()[0])
1142
        img = soup.find('div', id='comic').find('img')
1143
        assert all(i['alt'] == i['title'] for i in [img])
1144
        title2 = img['title']
1145
        img_url = img['src']
1146
        year, month, day = [int(s) for s in comic_date_re.match(img_url).groups()]
1147
        return {
1148
            'num': num,
1149
            'title': link.string,
1150
            'title2': title2,
1151
            'img': [img_url],
1152
            'year': year,
1153
            'month': month,
1154
            'day': day,
1155
        }
1156
1157
1158
class GenericBouletCorp(GenericNavigableComic):
1159
    """Generic class to retrieve BouletCorp comics in different languages."""
1160
    # Also on https://bouletcorp.tumblr.com
1161
    _categories = ('BOULET', )
1162
    get_navi_link = get_link_rel_next
1163
1164
    @classmethod
1165
    def get_first_comic_link(cls):
1166
        """Get link to first comics."""
1167
        return get_soup_at_url(cls.url).find('div', id='centered_nav').find_all('a')[0]
1168
1169
    @classmethod
1170
    def get_comic_info(cls, soup, link):
1171
        """Get information about a particular comics."""
1172
        url = cls.get_url_from_link(link)
1173
        date_re = re.compile('^%s/([0-9]*)/([0-9]*)/([0-9]*)/' % cls.url)
1174
        year, month, day = [int(s) for s in date_re.match(url).groups()]
1175
        imgs = soup.find('div', id='notes').find('div', class_='storycontent').find_all('img')
1176
        texts = '  '.join(t for t in (i.get('title') for i in imgs) if t)
1177
        title = soup.find('title').string
1178
        return {
1179
            'img': [convert_iri_to_plain_ascii_uri(i['src']) for i in imgs if i.get('src') is not None],
1180
            'title': title,
1181
            'texts': texts,
1182
            'year': year,
1183
            'month': month,
1184
            'day': day,
1185
        }
1186
1187
1188
class BouletCorp(GenericBouletCorp):
1189
    """Class to retrieve BouletCorp comics."""
1190
    name = 'boulet'
1191
    long_name = 'Boulet Corp'
1192
    url = 'http://www.bouletcorp.com'
1193
    _categories = ('FRANCAIS', )
1194
1195
1196
class BouletCorpEn(GenericBouletCorp):
1197
    """Class to retrieve EnglishBouletCorp comics."""
1198
    name = 'boulet_en'
1199
    long_name = 'Boulet Corp English'
1200
    url = 'http://english.bouletcorp.com'
1201
1202
1203 View Code Duplication
class AmazingSuperPowers(GenericNavigableComic):
1204
    """Class to retrieve Amazing Super Powers comics."""
1205
    name = 'asp'
1206
    long_name = 'Amazing Super Powers'
1207
    url = 'http://www.amazingsuperpowers.com'
1208
    get_first_comic_link = get_a_navi_navifirst
1209
    get_navi_link = get_a_navi_navinext
1210
1211
    @classmethod
1212
    def get_comic_info(cls, soup, link):
1213
        """Get information about a particular comics."""
1214
        author = soup.find("span", class_="post-author").find("a").string
1215
        date_str = soup.find('span', class_='post-date').string
1216
        day = string_to_date(date_str, "%B %d, %Y")
1217
        imgs = soup.find('div', id='comic').find_all('img')
1218
        title = ' '.join(i['title'] for i in imgs)
1219
        assert all(i['alt'] == i['title'] for i in imgs)
1220
        return {
1221
            'title': title,
1222
            'author': author,
1223
            'img': [img['src'] for img in imgs],
1224
            'day': day.day,
1225
            'month': day.month,
1226
            'year': day.year
1227
        }
1228
1229
1230
class ToonHole(GenericNavigableComic):
1231
    """Class to retrieve Toon Holes comics."""
1232
    # Also on http://tapastic.com/series/TOONHOLE
1233
    name = 'toonhole'
1234
    long_name = 'Toon Hole'
1235
    url = 'http://www.toonhole.com'
1236
    get_first_comic_link = get_a_comicnavbase_comicnavfirst
1237
    get_navi_link = get_a_comicnavbase_comicnavnext
1238
1239
    @classmethod
1240
    def get_comic_info(cls, soup, link):
1241
        """Get information about a particular comics."""
1242
        date_str = soup.find('div', class_='entry-meta').contents[0].strip()
1243
        day = string_to_date(date_str, "%B %d, %Y")
1244
        imgs = soup.find('div', id='comic').find_all('img')
1245
        if imgs:
1246
            img = imgs[0]
1247
            title = img['alt']
1248
            assert img['title'] == title
1249
        else:
1250
            title = ""
1251
        return {
1252
            'title': title,
1253
            'month': day.month,
1254
            'year': day.year,
1255
            'day': day.day,
1256
            'img': [convert_iri_to_plain_ascii_uri(i['src']) for i in imgs],
1257
        }
1258
1259
1260
class Channelate(GenericNavigableComic):
1261
    """Class to retrieve Channelate comics."""
1262
    name = 'channelate'
1263
    long_name = 'Channelate'
1264
    url = 'http://www.channelate.com'
1265
    get_first_comic_link = get_div_navfirst_a
1266
    get_navi_link = get_link_rel_next
1267
    get_url_from_link = join_cls_url_to_href
1268
1269
    @classmethod
1270
    def get_comic_info(cls, soup, link):
1271
        """Get information about a particular comics."""
1272
        author = soup.find("span", class_="post-author").find("a").string
1273
        date_str = soup.find('span', class_='post-date').string
1274
        day = string_to_date(date_str, '%Y/%m/%d')
1275
        title = soup.find('meta', property='og:title')['content']
1276
        post = soup.find('div', id='comic')
1277
        imgs = post.find_all('img') if post else []
1278
        extra_url = None
1279
        extra_div = soup.find('div', id='extrapanelbutton')
1280
        if extra_div:
1281
            extra_url = extra_div.find('a')['href']
1282
            extra_soup = get_soup_at_url(extra_url)
1283
            extra_imgs = extra_soup.find_all('img', class_='extrapanelimage')
1284
            imgs.extend(extra_imgs)
1285
        return {
1286
            'url_extra': extra_url,
1287
            'title': title,
1288
            'author': author,
1289
            'month': day.month,
1290
            'year': day.year,
1291
            'day': day.day,
1292
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
1293
        }
1294
1295
1296
class CyanideAndHappiness(GenericNavigableComic):
1297
    """Class to retrieve Cyanide And Happiness comics."""
1298
    name = 'cyanide'
1299
    long_name = 'Cyanide and Happiness'
1300
    url = 'http://explosm.net'
1301
    _categories = ('NSFW', )
1302
    get_url_from_link = join_cls_url_to_href
1303
1304
    @classmethod
1305
    def get_first_comic_link(cls):
1306
        """Get link to first comics."""
1307
        return get_soup_at_url(cls.url).find('a', title='Oldest comic')
1308
1309
    @classmethod
1310
    def get_navi_link(cls, last_soup, next_):
1311
        """Get link to next or previous comic."""
1312
        link = last_soup.find('a', class_='next-comic' if next_ else 'previous-comic ')
1313
        return None if link.get('href') is None else link
1314
1315
    @classmethod
1316
    def get_comic_info(cls, soup, link):
1317
        """Get information about a particular comics."""
1318
        url2 = soup.find('meta', property='og:url')['content']
1319
        num = int(url2.split('/')[-2])
1320
        date_str = soup.find('h3').find('a').string
1321
        day = string_to_date(date_str, '%Y.%m.%d')
1322
        author = soup.find('small', class_="author-credit-name").string
1323
        assert author.startswith('by ')
1324
        author = author[3:]
1325
        imgs = soup.find_all('img', id='main-comic')
1326
        return {
1327
            'num': num,
1328
            'author': author,
1329
            'month': day.month,
1330
            'year': day.year,
1331
            'day': day.day,
1332
            'prefix': '%d-' % num,
1333
            'img': [convert_iri_to_plain_ascii_uri(urljoin_wrapper(cls.url, i['src'])) for i in imgs]
1334
        }
1335
1336
1337
class MrLovenstein(GenericComic):
1338
    """Class to retrieve Mr Lovenstein comics."""
1339
    # Also on https://tapastic.com/series/MrLovenstein
1340
    name = 'mrlovenstein'
1341
    long_name = 'Mr. Lovenstein'
1342
    url = 'http://www.mrlovenstein.com'
1343
1344
    @classmethod
1345
    def get_next_comic(cls, last_comic):
1346
        """Generator to get the next comic. Implementation of GenericComic's abstract method."""
1347
        # TODO: more info from http://www.mrlovenstein.com/archive
1348
        comic_num_re = re.compile('^/comic/([0-9]*)$')
1349
        nums = [int(comic_num_re.match(link['href']).groups()[0])
1350
                for link in get_soup_at_url(cls.url).find_all('a', href=comic_num_re)]
1351
        first, last = min(nums), max(nums)
1352
        if last_comic:
1353
            first = last_comic['num'] + 1
1354
        for num in range(first, last + 1):
1355
            url = urljoin_wrapper(cls.url, '/comic/%d' % num)
1356
            soup = get_soup_at_url(url)
1357
            imgs = list(
1358
                reversed(soup.find_all('img', src=re.compile('^/images/comics/'))))
1359
            description = soup.find('meta', attrs={'name': 'description'})['content']
1360
            yield {
1361
                'url': url,
1362
                'num': num,
1363
                'texts': '  '.join(t for t in (i.get('title') for i in imgs) if t),
1364
                'img': [urljoin_wrapper(url, i['src']) for i in imgs],
1365
                'description': description,
1366
            }
1367
1368
1369
class DinosaurComics(GenericListableComic):
1370
    """Class to retrieve Dinosaur Comics comics."""
1371
    name = 'dinosaur'
1372
    long_name = 'Dinosaur Comics'
1373
    url = 'http://www.qwantz.com'
1374
    get_url_from_archive_element = get_href
1375
    comic_link_re = re.compile('^%s/index.php\\?comic=([0-9]*)$' % url)
1376
1377
    @classmethod
1378
    def get_archive_elements(cls):
1379
        archive_url = urljoin_wrapper(cls.url, 'archive.php')
1380
        # first link is random -> skip it
1381
        return reversed(get_soup_at_url(archive_url).find_all('a', href=cls.comic_link_re)[1:])
1382
1383
    @classmethod
1384
    def get_comic_info(cls, soup, link):
1385
        """Get information about a particular comics."""
1386 View Code Duplication
        url = cls.get_url_from_archive_element(link)
1387
        num = int(cls.comic_link_re.match(url).groups()[0])
1388
        date_str = link.string
1389
        text = link.next_sibling.string
1390
        day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y")
1391
        comic_img_re = re.compile('^%s/comics/' % cls.url)
1392
        img = soup.find('img', src=comic_img_re)
1393
        return {
1394
            'month': day.month,
1395
            'year': day.year,
1396
            'day': day.day,
1397
            'img': [img.get('src')],
1398
            'title': img.get('title'),
1399
            'text': text,
1400
            'num': num,
1401
        }
1402
1403
1404
class ButterSafe(GenericListableComic):
1405
    """Class to retrieve Butter Safe comics."""
1406
    name = 'butter'
1407
    long_name = 'ButterSafe'
1408
    url = 'http://buttersafe.com'
1409
    get_url_from_archive_element = get_href
1410
    comic_link_re = re.compile('^%s/([0-9]*)/([0-9]*)/([0-9]*)/.*' % url)
1411
1412
    @classmethod
1413
    def get_archive_elements(cls):
1414
        archive_url = urljoin_wrapper(cls.url, 'archive/')
1415
        return reversed(get_soup_at_url(archive_url).find_all('a', href=cls.comic_link_re))
1416
1417
    @classmethod
1418
    def get_comic_info(cls, soup, link):
1419
        """Get information about a particular comics."""
1420
        url = cls.get_url_from_archive_element(link)
1421
        title = link.string
1422
        year, month, day = [int(s) for s in cls.comic_link_re.match(url).groups()]
1423
        img = soup.find('div', id='comic').find('img')
1424
        assert img['alt'] == title
1425
        return {
1426
            'title': title,
1427
            'day': day,
1428
            'month': month,
1429
            'year': year,
1430
            'img': [img['src']],
1431
        }
1432
1433
1434
class CalvinAndHobbes(GenericComic):
1435
    """Class to retrieve Calvin and Hobbes comics."""
1436
    # Also on http://www.gocomics.com/calvinandhobbes/
1437
    name = 'calvin'
1438
    long_name = 'Calvin and Hobbes'
1439
    # This is not through any official webpage but eh...
1440
    url = 'http://marcel-oehler.marcellosendos.ch/comics/ch/'
1441
1442
    @classmethod
1443
    def get_next_comic(cls, last_comic):
1444
        """Generator to get the next comic. Implementation of GenericComic's abstract method."""
1445
        last_date = get_date_for_comic(
1446
            last_comic) if last_comic else date(1985, 11, 1)
1447
        link_re = re.compile('^([0-9]*)/([0-9]*)/')
1448
        img_re = re.compile('')
1449
        for link in get_soup_at_url(cls.url).find_all('a', href=link_re):
1450
            url = link['href']
1451
            year, month = link_re.match(url).groups()
1452 View Code Duplication
            if date(int(year), int(month), 1) + timedelta(days=31) >= last_date:
1453
                img_re = re.compile('^%s%s([0-9]*)' % (year, month))
1454
                month_url = urljoin_wrapper(cls.url, url)
1455
                for img in get_soup_at_url(month_url).find_all('img', src=img_re):
1456
                    img_src = img['src']
1457
                    day = int(img_re.match(img_src).groups()[0])
1458
                    comic_date = date(int(year), int(month), day)
1459
                    if comic_date > last_date:
1460
                        yield {
1461
                            'url': month_url,
1462
                            'year': int(year),
1463
                            'month': int(month),
1464
                            'day': int(day),
1465
                            'img': ['%s%s/%s/%s' % (cls.url, year, month, img_src)],
1466
                        }
1467
                        last_date = comic_date
1468
1469
1470
class AbstruseGoose(GenericListableComic):
1471
    """Class to retrieve AbstruseGoose Comics."""
1472
    name = 'abstruse'
1473
    long_name = 'Abstruse Goose'
1474
    url = 'http://abstrusegoose.com'
1475
    get_url_from_archive_element = get_href
1476
    comic_url_re = re.compile('^%s/([0-9]*)$' % url)
1477
    comic_img_re = re.compile('^%s/strips/.*' % url)
1478
1479
    @classmethod
1480
    def get_archive_elements(cls):
1481
        archive_url = urljoin_wrapper(cls.url, 'archive')
1482
        return get_soup_at_url(archive_url).find_all('a', href=cls.comic_url_re)
1483
1484
    @classmethod
1485
    def get_comic_info(cls, soup, archive_elt):
1486
        comic_url = cls.get_url_from_archive_element(archive_elt)
1487
        num = int(cls.comic_url_re.match(comic_url).groups()[0])
1488
        return {
1489
            'num': num,
1490
            'title': archive_elt.string,
1491
            'img': [soup.find('img', src=cls.comic_img_re)['src']]
1492
        }
1493
1494
1495
class PhDComics(GenericNavigableComic):
1496
    """Class to retrieve PHD Comics."""
1497
    name = 'phd'
1498
    long_name = 'PhD Comics'
1499
    url = 'http://phdcomics.com/comics/archive.php'
1500
1501
    @classmethod
1502
    def get_first_comic_link(cls):
1503
        """Get link to first comics."""
1504
        soup = get_soup_at_url(cls.url)
1505
        img = soup.find('img', src='http://phdcomics.com/comics/images/first_button.gif')
1506
        return None if img is None else img.parent
1507
1508
    @classmethod
1509
    def get_navi_link(cls, last_soup, next_):
1510
        """Get link to next or previous comic."""
1511
        url = 'http://phdcomics.com/comics/images/%s_button.gif' % ('next' if next_ else 'prev')
1512
        img = last_soup.find('img', src=url)
1513
        return None if img is None else img.parent
1514
1515
    @classmethod
1516
    def get_comic_info(cls, soup, link):
1517
        """Get information about a particular comics."""
1518
        title = soup.find('meta', attrs={'name': 'twitter:title'})['content']
1519
        imgs = soup.find_all('meta', property='og:image')
1520
        return {
1521
            'img': [i['content'] for i in imgs],
1522
            'title': title,
1523
        }
1524
1525
1526
class Quarktees(GenericNavigableComic):
1527
    """Class to retrieve the Quarktees comics."""
1528
    name = 'quarktees'
1529
    long_name = 'Quarktees'
1530
    url = 'http://www.quarktees.com/blogs/news'
1531
    get_url_from_link = join_cls_url_to_href
1532
    get_first_comic_link = simulate_first_link
1533
    first_url = 'http://www.quarktees.com/blogs/news/12486621-coming-soon'
1534
1535
    @classmethod
1536
    def get_navi_link(cls, last_soup, next_):
1537
        """Get link to next or previous comic."""
1538
        return last_soup.find('a', id='article-next' if next_ else 'article-prev')
1539
1540
    @classmethod
1541
    def get_comic_info(cls, soup, link):
1542
        """Get information about a particular comics."""
1543
        title = soup.find('meta', property='og:title')['content']
1544
        article = soup.find('div', class_='single-article')
1545
        imgs = article.find_all('img')
1546
        return {
1547
            'title': title,
1548
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
1549
        }
1550
1551
1552
class OverCompensating(GenericNavigableComic):
1553
    """Class to retrieve the Over Compensating comics."""
1554
    name = 'compensating'
1555
    long_name = 'Over Compensating'
1556
    url = 'http://www.overcompensating.com'
1557
    get_url_from_link = join_cls_url_to_href
1558
1559
    @classmethod
1560
    def get_first_comic_link(cls):
1561
        """Get link to first comics."""
1562
        return get_soup_at_url(cls.url).find('a', href=re.compile('comic=1$'))
1563
1564
    @classmethod
1565
    def get_navi_link(cls, last_soup, next_):
1566
        """Get link to next or previous comic."""
1567
        return last_soup.find('a', title='next comic' if next_ else 'go back already')
1568
1569
    @classmethod
1570
    def get_comic_info(cls, soup, link):
1571
        """Get information about a particular comics."""
1572
        img_src_re = re.compile('^/oc/comics/.*')
1573
        comic_num_re = re.compile('.*comic=([0-9]*)$')
1574
        comic_url = cls.get_url_from_link(link)
1575
        num = int(comic_num_re.match(comic_url).groups()[0])
1576
        img = soup.find('img', src=img_src_re)
1577
        return {
1578
            'num': num,
1579
            'img': [urljoin_wrapper(comic_url, img['src'])],
1580
            'title': img.get('title')
1581
        }
1582
1583
1584
class Oglaf(GenericNavigableComic):
1585
    """Class to retrieve Oglaf comics."""
1586
    name = 'oglaf'
1587
    long_name = 'Oglaf [NSFW]'
1588
    url = 'http://oglaf.com'
1589
    _categories = ('NSFW', )
1590
    get_url_from_link = join_cls_url_to_href
1591
1592
    @classmethod
1593
    def get_first_comic_link(cls):
1594
        """Get link to first comics."""
1595
        return get_soup_at_url(cls.url).find("div", id="st").parent
1596
1597
    @classmethod
1598
    def get_navi_link(cls, last_soup, next_):
1599
        """Get link to next or previous comic."""
1600
        div = last_soup.find("div", id="nx" if next_ else "pvs")
1601
        return div.parent if div else None
1602
1603
    @classmethod
1604
    def get_comic_info(cls, soup, link):
1605
        """Get information about a particular comics."""
1606
        title = soup.find('title').string
1607
        title_imgs = soup.find('div', id='tt').find_all('img')
1608
        assert len(title_imgs) == 1, title_imgs
1609
        strip_imgs = soup.find_all('img', id='strip')
1610
        assert len(strip_imgs) == 1, strip_imgs
1611
        imgs = title_imgs + strip_imgs
1612
        desc = ' '.join(i['title'] for i in imgs)
1613
        return {
1614
            'title': title,
1615
            'img': [i['src'] for i in imgs],
1616
            'description': desc,
1617
        }
1618
1619
1620
class ScandinaviaAndTheWorld(GenericNavigableComic):
1621
    """Class to retrieve Scandinavia And The World comics."""
1622
    name = 'satw'
1623
    long_name = 'Scandinavia And The World'
1624
    url = 'http://satwcomic.com'
1625
    get_first_comic_link = simulate_first_link
1626
    first_url = 'http://satwcomic.com/sweden-denmark-and-norway'
1627
1628
    @classmethod
1629
    def get_navi_link(cls, last_soup, next_):
1630
        """Get link to next or previous comic."""
1631
        return last_soup.find('a', accesskey='n' if next_ else 'p')
1632
1633
    @classmethod
1634
    def get_comic_info(cls, soup, link):
1635
        """Get information about a particular comics."""
1636
        title = soup.find('meta', attrs={'name': 'twitter:label1'})['content']
1637
        desc = soup.find('meta', property='og:description')['content']
1638
        imgs = soup.find_all('img', itemprop="image")
1639
        return {
1640
            'title': title,
1641
            'description': desc,
1642
            'img': [i['src'] for i in imgs],
1643
        }
1644
1645
1646
class SomethingOfThatIlk(GenericDeletedComic):
1647
    """Class to retrieve the Something Of That Ilk comics."""
1648
    name = 'somethingofthatilk'
1649
    long_name = 'Something Of That Ilk'
1650
    url = 'http://www.somethingofthatilk.com'
1651
1652
1653
class MonkeyUser(GenericNavigableComic):
1654
    """Class to retrieve Monkey User comics."""
1655
    name = 'monkeyuser'
1656
    long_name = 'Monkey User'
1657
    url = 'http://www.monkeyuser.com'
1658
    get_first_comic_link = simulate_first_link
1659
    first_url = 'http://www.monkeyuser.com/2016/project-lifecycle/'
1660
    get_url_from_link = join_cls_url_to_href
1661
1662
    @classmethod
1663
    def get_navi_link(cls, last_soup, next_):
1664
        """Get link to next or previous comic."""
1665
        div = last_soup.find('div', title='next' if next_ else 'previous')
1666
        return None if div is None else div.find('a')
1667
1668
    @classmethod
1669
    def get_comic_info(cls, soup, link):
1670
        """Get information about a particular comics."""
1671
        title = soup.find('meta', property='og:title')['content']
1672
        desc = soup.find('meta', property='og:description')['content']
1673
        imgs = soup.find_all('meta', property='og:image')
1674
        date_str = soup.find('span', class_='post-date').find('time').string
1675
        day = string_to_date(date_str, "%d %b %Y")
1676
        return {
1677
            'month': day.month,
1678
            'year': day.year,
1679
            'day': day.day,
1680
            'img': [i['content'] for i in imgs],
1681
            'title': title,
1682
            'description': desc,
1683
        }
1684
1685
1686
class InfiniteMonkeyBusiness(GenericNavigableComic):
1687
    """Class to retrieve InfiniteMonkeyBusiness comics."""
1688
    name = 'monkey'
1689
    long_name = 'Infinite Monkey Business'
1690
    url = 'http://infinitemonkeybusiness.net'
1691
    get_navi_link = get_a_navi_comicnavnext_navinext
1692
    get_first_comic_link = simulate_first_link
1693
    first_url = 'http://infinitemonkeybusiness.net/comic/pillory/'
1694
1695
    @classmethod
1696
    def get_comic_info(cls, soup, link):
1697
        """Get information about a particular comics."""
1698
        title = soup.find('meta', property='og:title')['content']
1699
        imgs = soup.find('div', id='comic').find_all('img')
1700
        return {
1701
            'title': title,
1702
            'img': [i['src'] for i in imgs],
1703
        }
1704
1705
1706
class Wondermark(GenericListableComic):
1707
    """Class to retrieve the Wondermark comics."""
1708
    name = 'wondermark'
1709
    long_name = 'Wondermark'
1710
    url = 'http://wondermark.com'
1711
    get_url_from_archive_element = get_href
1712
1713
    @classmethod
1714
    def get_archive_elements(cls):
1715
        archive_url = urljoin_wrapper(cls.url, 'archive/')
1716
        return reversed(get_soup_at_url(archive_url).find_all('a', rel='bookmark'))
1717
1718
    @classmethod
1719
    def get_comic_info(cls, soup, link):
1720
        """Get information about a particular comics."""
1721
        date_str = soup.find('div', class_='postdate').find('em').string
1722
        day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y")
1723
        div = soup.find('div', id='comic')
1724
        if div:
1725
            img = div.find('img')
1726
            img_src = [img['src']]
1727
            alt = img['alt']
1728
            assert alt == img['title']
1729
            title = soup.find('meta', property='og:title')['content']
1730
        else:
1731
            img_src = []
1732
            alt = ''
1733
            title = ''
1734
        return {
1735
            'month': day.month,
1736
            'year': day.year,
1737
            'day': day.day,
1738
            'img': img_src,
1739
            'title': title,
1740
            'alt': alt,
1741
            'tags': ' '.join(t.string for t in soup.find('div', class_='postmeta').find_all('a', rel='tag')),
1742
        }
1743
1744
1745
class WarehouseComic(GenericNavigableComic):
1746
    """Class to retrieve Warehouse Comic comics."""
1747
    name = 'warehouse'
1748
    long_name = 'Warehouse Comic'
1749
    url = 'http://warehousecomic.com'
1750
    get_first_comic_link = get_a_navi_navifirst
1751
    get_navi_link = get_link_rel_next
1752
1753
    @classmethod
1754
    def get_comic_info(cls, soup, link):
1755
        """Get information about a particular comics."""
1756
        title = soup.find('h2', class_='post-title').string
1757
        date_str = soup.find('span', class_='post-date').string
1758
        day = string_to_date(date_str, "%B %d, %Y")
1759
        imgs = soup.find('div', id='comic').find_all('img')
1760
        return {
1761
            'img': [i['src'] for i in imgs],
1762
            'title': title,
1763
            'day': day.day,
1764
            'month': day.month,
1765
            'year': day.year,
1766
        }
1767
1768
1769
class JustSayEh(GenericNavigableComic):
1770
    """Class to retrieve Just Say Eh comics."""
1771
    # Also on http//tapastic.com/series/Just-Say-Eh
1772
    name = 'justsayeh'
1773
    long_name = 'Just Say Eh'
1774
    url = 'http://www.justsayeh.com'
1775
    get_first_comic_link = get_a_navi_navifirst
1776
    get_navi_link = get_a_navi_comicnavnext_navinext
1777
1778
    @classmethod
1779
    def get_comic_info(cls, soup, link):
1780
        """Get information about a particular comics."""
1781
        title = soup.find('h2', class_='post-title').string
1782
        imgs = soup.find("div", id="comic").find_all("img")
1783
        assert all(i['alt'] == i['title'] for i in imgs)
1784
        alt = imgs[0]['alt']
1785
        return {
1786
            'img': [i['src'] for i in imgs],
1787
            'title': title,
1788
            'alt': alt,
1789
        }
1790
1791
1792 View Code Duplication
class MouseBearComedy(GenericComicNotWorking):  # Website has changed
1793
    """Class to retrieve Mouse Bear Comedy comics."""
1794
    # Also on http://mousebearcomedy.tumblr.com
1795
    name = 'mousebear'
1796
    long_name = 'Mouse Bear Comedy'
1797
    url = 'http://www.mousebearcomedy.com'
1798
    get_first_comic_link = get_a_navi_navifirst
1799
    get_navi_link = get_a_navi_comicnavnext_navinext
1800
1801
    @classmethod
1802
    def get_comic_info(cls, soup, link):
1803
        """Get information about a particular comics."""
1804
        title = soup.find('h2', class_='post-title').string
1805
        author = soup.find("span", class_="post-author").find("a").string
1806
        date_str = soup.find("span", class_="post-date").string
1807
        day = string_to_date(date_str, '%B %d, %Y')
1808
        imgs = soup.find("div", id="comic").find_all("img")
1809
        assert all(i['alt'] == i['title'] == title for i in imgs)
1810
        return {
1811
            'day': day.day,
1812
            'month': day.month,
1813
            'year': day.year,
1814
            'img': [i['src'] for i in imgs],
1815
            'title': title,
1816
            'author': author,
1817
        }
1818
1819
1820 View Code Duplication
class BigFootJustice(GenericNavigableComic):
1821
    """Class to retrieve Big Foot Justice comics."""
1822
    # Also on http://tapastic.com/series/bigfoot-justice
1823
    name = 'bigfoot'
1824
    long_name = 'Big Foot Justice'
1825
    url = 'http://bigfootjustice.com'
1826
    get_first_comic_link = get_a_navi_navifirst
1827
    get_navi_link = get_a_navi_comicnavnext_navinext
1828
1829
    @classmethod
1830
    def get_comic_info(cls, soup, link):
1831
        """Get information about a particular comics."""
1832
        imgs = soup.find('div', id='comic').find_all('img')
1833
        assert all(i['title'] == i['alt'] for i in imgs)
1834
        title = ' '.join(i['title'] for i in imgs)
1835
        return {
1836
            'img': [i['src'] for i in imgs],
1837
            'title': title,
1838
        }
1839
1840
1841
class RespawnComic(GenericNavigableComic):
1842
    """Class to retrieve Respawn Comic."""
1843
    # Also on https://respawncomic.tumblr.com
1844
    name = 'respawn'
1845
    long_name = 'Respawn Comic'
1846
    url = 'http://respawncomic.com '
1847
    _categories = ('RESPAWN', )
1848
    get_navi_link = get_a_rel_next
1849
    get_first_comic_link = simulate_first_link
1850
    first_url = 'http://respawncomic.com/comic/c0001/'
1851
1852
    @classmethod
1853
    def get_comic_info(cls, soup, link):
1854
        """Get information about a particular comics."""
1855
        title = soup.find('meta', property='og:title')['content']
1856
        author = soup.find('meta', attrs={'name': 'shareaholic:article_author_name'})['content']
1857
        date_str = soup.find('meta', attrs={'name': 'shareaholic:article_published_time'})['content']
1858
        date_str = date_str[:10]
1859
        day = string_to_date(date_str, "%Y-%m-%d")
1860
        imgs = soup.find_all('meta', property='og:image')
1861
        skip_imgs = {
1862
            'http://respawncomic.com/wp-content/uploads/2016/03/site/HAROLD2.png',
1863
            'http://respawncomic.com/wp-content/uploads/2016/03/site/DEVA.png'
1864
        }
1865
        return {
1866
            'title': title,
1867
            'author': author,
1868
            'day': day.day,
1869
            'month': day.month,
1870
            'year': day.year,
1871
            'img': [i['content'] for i in imgs if i['content'] not in skip_imgs],
1872
        }
1873
1874
1875
class SafelyEndangered(GenericNavigableComic):
1876
    """Class to retrieve Safely Endangered comics."""
1877
    # Also on http://tumblr.safelyendangered.com
1878
    name = 'endangered'
1879
    long_name = 'Safely Endangered'
1880
    url = 'http://www.safelyendangered.com'
1881
    get_navi_link = get_link_rel_next
1882
    get_first_comic_link = simulate_first_link
1883
    first_url = 'http://www.safelyendangered.com/comic/ignored/'
1884
1885
    @classmethod
1886
    def get_comic_info(cls, soup, link):
1887
        """Get information about a particular comics."""
1888
        title = soup.find('h2', class_='post-title').string
1889
        date_str = soup.find('span', class_='post-date').string
1890
        day = string_to_date(date_str, '%B %d, %Y')
1891
        imgs = soup.find('div', id='comic').find_all('img')
1892
        alt = imgs[0]['alt']
1893
        assert all(i['alt'] == i['title'] for i in imgs)
1894
        return {
1895
            'day': day.day,
1896
            'month': day.month,
1897
            'year': day.year,
1898
            'img': [i['src'] for i in imgs],
1899
            'title': title,
1900
            'alt': alt,
1901
        }
1902
1903
1904 View Code Duplication
class PicturesInBoxes(GenericNavigableComic):
1905
    """Class to retrieve Pictures In Boxes comics."""
1906
    # Also on https://picturesinboxescomic.tumblr.com
1907
    name = 'picturesinboxes'
1908
    long_name = 'Pictures in Boxes'
1909
    url = 'http://www.picturesinboxes.com'
1910
    get_navi_link = get_a_navi_navinext
1911
    get_first_comic_link = simulate_first_link
1912
    first_url = 'http://www.picturesinboxes.com/2013/10/26/tetris/'
1913
1914
    @classmethod
1915
    def get_comic_info(cls, soup, link):
1916
        """Get information about a particular comics."""
1917
        title = soup.find('h2', class_='post-title').string
1918
        author = soup.find("span", class_="post-author").find("a").string
1919
        date_str = soup.find('span', class_='post-date').string
1920
        day = string_to_date(date_str, '%B %d, %Y')
1921
        imgs = soup.find('div', class_='comicpane').find_all('img')
1922
        assert imgs
1923
        assert all(i['title'] == i['alt'] == title for i in imgs)
1924
        return {
1925
            'day': day.day,
1926
            'month': day.month,
1927
            'year': day.year,
1928
            'img': [i['src'] for i in imgs],
1929
            'title': title,
1930
            'author': author,
1931
        }
1932
1933
1934
class Penmen(GenericComicNotWorking, GenericNavigableComic):
1935
    """Class to retrieve Penmen comics."""
1936
    name = 'penmen'
1937
    long_name = 'Penmen'
1938
    url = 'http://penmen.com'
1939
    get_navi_link = get_link_rel_next
1940
    get_first_comic_link = simulate_first_link
1941
    first_url = 'http://penmen.com/index.php/2016/09/12/penmen-announces-grin-big-brand-clothing/'
1942
1943
    @classmethod
1944
    def get_comic_info(cls, soup, link):
1945
        """Get information about a particular comics."""
1946
        title = soup.find('title').string
1947
        imgs = soup.find('div', class_='entry-content').find_all('img')
1948
        short_url = soup.find('link', rel='shortlink')['href']
1949
        tags = ' '.join(t.string for t in soup.find_all('a', rel='tag'))
1950
        date_str = soup.find('time')['datetime'][:10]
1951
        day = string_to_date(date_str, "%Y-%m-%d")
1952
        return {
1953
            'title': title,
1954
            'short_url': short_url,
1955
            'img': [i['src'] for i in imgs],
1956
            'tags': tags,
1957
            'month': day.month,
1958
            'year': day.year,
1959
            'day': day.day,
1960
        }
1961
1962
1963
class TheDoghouseDiaries(GenericDeletedComic, GenericNavigableComic):
1964
    """Class to retrieve The Dog House Diaries comics."""
1965
    name = 'doghouse'
1966
    long_name = 'The Dog House Diaries'
1967
    url = 'http://thedoghousediaries.com'
1968
1969
    @classmethod
1970
    def get_first_comic_link(cls):
1971
        """Get link to first comics."""
1972
        return get_soup_at_url(cls.url).find('a', id='firstlink')
1973
1974
    @classmethod
1975
    def get_navi_link(cls, last_soup, next_):
1976
        """Get link to next or previous comic."""
1977
        return last_soup.find('a', id='nextlink' if next_ else 'previouslink')
1978
1979
    @classmethod
1980
    def get_comic_info(cls, soup, link):
1981
        """Get information about a particular comics."""
1982
        comic_img_re = re.compile('^dhdcomics/.*')
1983
        img = soup.find('img', src=comic_img_re)
1984
        comic_url = cls.get_url_from_link(link)
1985
        return {
1986
            'title': soup.find('h2', id='titleheader').string,
1987
            'title2': soup.find('div', id='subtext').string,
1988
            'alt': img.get('title'),
1989
            'img': [urljoin_wrapper(comic_url, img['src'].strip())],
1990
            'num': int(comic_url.split('/')[-1]),
1991
        }
1992
1993
1994
class InvisibleBread(GenericListableComic):
1995
    """Class to retrieve Invisible Bread comics."""
1996
    # Also on http://www.gocomics.com/invisible-bread
1997
    name = 'invisiblebread'
1998
    long_name = 'Invisible Bread'
1999
    url = 'http://invisiblebread.com'
2000
2001
    @classmethod
2002
    def get_archive_elements(cls):
2003
        archive_url = urljoin_wrapper(cls.url, 'archives/')
2004
        return reversed(get_soup_at_url(archive_url).find_all('td', class_='archive-title'))
2005
2006
    @classmethod
2007
    def get_url_from_archive_element(cls, td):
2008
        return td.find('a')['href']
2009
2010 View Code Duplication
    @classmethod
2011
    def get_comic_info(cls, soup, td):
2012
        """Get information about a particular comics."""
2013
        url = cls.get_url_from_archive_element(td)
2014
        title = td.find('a').string
2015
        month_and_day = td.previous_sibling.string
2016
        link_re = re.compile('^%s/([0-9]+)/' % cls.url)
2017
        year = link_re.match(url).groups()[0]
2018
        date_str = month_and_day + ' ' + year
2019
        day = string_to_date(date_str, '%b %d %Y')
2020
        imgs = [soup.find('div', id='comic').find('img')]
2021
        assert len(imgs) == 1, imgs
2022
        assert all(i['title'] == i['alt'] == title for i in imgs)
2023
        return {
2024
            'month': day.month,
2025
            'year': day.year,
2026
            'day': day.day,
2027
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
2028
            'title': title,
2029
        }
2030
2031
2032
class DiscoBleach(GenericDeletedComic):
2033
    """Class to retrieve Disco Bleach Comics."""
2034
    name = 'discobleach'
2035
    long_name = 'Disco Bleach'
2036
    url = 'http://discobleach.com'
2037
2038
2039
class TubeyToons(GenericDeletedComic):
2040
    """Class to retrieve TubeyToons comics."""
2041
    # Also on http://tapastic.com/series/Tubey-Toons
2042
    # Also on https://tubeytoons.tumblr.com
2043
    name = 'tubeytoons'
2044
    long_name = 'Tubey Toons'
2045
    url = 'http://tubeytoons.com'
2046
    _categories = ('TUNEYTOONS', )
2047
2048
2049 View Code Duplication
class CompletelySeriousComics(GenericNavigableComic):
2050
    """Class to retrieve Completely Serious comics."""
2051
    name = 'completelyserious'
2052
    long_name = 'Completely Serious Comics'
2053
    url = 'http://completelyseriouscomics.com'
2054
    get_first_comic_link = get_a_navi_navifirst
2055
    get_navi_link = get_a_navi_navinext
2056
2057
    @classmethod
2058
    def get_comic_info(cls, soup, link):
2059
        """Get information about a particular comics."""
2060
        title = soup.find('h2', class_='post-title').string
2061
        author = soup.find('span', class_='post-author').contents[1].string
2062
        date_str = soup.find('span', class_='post-date').string
2063
        day = string_to_date(date_str, '%B %d, %Y')
2064
        imgs = soup.find('div', class_='comicpane').find_all('img')
2065
        assert imgs
2066
        alt = imgs[0]['title']
2067
        assert all(i['title'] == i['alt'] == alt for i in imgs)
2068
        return {
2069
            'month': day.month,
2070
            'year': day.year,
2071
            'day': day.day,
2072
            'img': [i['src'] for i in imgs],
2073
            'title': title,
2074
            'alt': alt,
2075
            'author': author,
2076
        }
2077
2078
2079 View Code Duplication
class PoorlyDrawnLines(GenericListableComic):
2080
    """Class to retrieve Poorly Drawn Lines comics."""
2081
    # Also on http://pdlcomics.tumblr.com
2082
    name = 'poorlydrawn'
2083
    long_name = 'Poorly Drawn Lines'
2084
    url = 'https://www.poorlydrawnlines.com'
2085
    _categories = ('POORLYDRAWN', )
2086
    get_url_from_archive_element = get_href
2087
2088
    @classmethod
2089
    def get_comic_info(cls, soup, link):
2090
        """Get information about a particular comics."""
2091
        imgs = soup.find('div', class_='post').find_all('img')
2092
        assert len(imgs) <= 1, imgs
2093
        return {
2094
            'img': [i['src'] for i in imgs],
2095
            'title': imgs[0].get('title', "") if imgs else "",
2096
        }
2097
2098
    @classmethod
2099
    def get_archive_elements(cls):
2100
        archive_url = urljoin_wrapper(cls.url, 'archive')
2101
        url_re = re.compile('^%s/comic/.' % cls.url)
2102
        return reversed(get_soup_at_url(archive_url).find_all('a', href=url_re))
2103
2104
2105
class LoadingComics(GenericNavigableComic):
2106
    """Class to retrieve Loading Artist comics."""
2107
    name = 'loadingartist'
2108
    long_name = 'Loading Artist'
2109
    url = 'http://www.loadingartist.com/latest'
2110
2111
    @classmethod
2112
    def get_first_comic_link(cls):
2113
        """Get link to first comics."""
2114
        return get_soup_at_url(cls.url).find('a', title="First")
2115
2116
    @classmethod
2117
    def get_navi_link(cls, last_soup, next_):
2118
        """Get link to next or previous comic."""
2119
        return last_soup.find('a', title='Next' if next_ else 'Previous')
2120
2121
    @classmethod
2122
    def get_comic_info(cls, soup, link):
2123
        """Get information about a particular comics."""
2124
        title = soup.find('h1').string
2125
        date_str = soup.find('span', class_='date').string.strip()
2126
        day = string_to_date(date_str, "%B %d, %Y")
2127
        imgs = soup.find('div', class_='comic').find_all('img', alt='', title='')
2128
        return {
2129
            'title': title,
2130
            'img': [i['src'] for i in imgs],
2131
            'month': day.month,
2132
            'year': day.year,
2133
            'day': day.day,
2134
        }
2135
2136
2137 View Code Duplication
class ChuckleADuck(GenericNavigableComic):
2138
    """Class to retrieve Chuckle-A-Duck comics."""
2139
    name = 'chuckleaduck'
2140
    long_name = 'Chuckle-A-duck'
2141
    url = 'http://chuckleaduck.com'
2142
    get_first_comic_link = get_div_navfirst_a
2143
    get_navi_link = get_link_rel_next
2144
2145
    @classmethod
2146
    def get_comic_info(cls, soup, link):
2147
        """Get information about a particular comics."""
2148
        date_str = soup.find('span', class_='post-date').string
2149
        day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y")
2150
        author = soup.find('span', class_='post-author').string
2151
        div = soup.find('div', id='comic')
2152
        imgs = div.find_all('img') if div else []
2153
        title = imgs[0]['title'] if imgs else ""
2154
        assert all(i['title'] == i['alt'] == title for i in imgs)
2155
        return {
2156
            'month': day.month,
2157
            'year': day.year,
2158
            'day': day.day,
2159
            'img': [i['src'] for i in imgs],
2160
            'title': title,
2161
            'author': author,
2162
        }
2163
2164
2165
class DepressedAlien(GenericNavigableComic):
2166
    """Class to retrieve Depressed Alien Comics."""
2167
    name = 'depressedalien'
2168
    long_name = 'Depressed Alien'
2169
    url = 'http://depressedalien.com'
2170
    get_url_from_link = join_cls_url_to_href
2171
2172
    @classmethod
2173
    def get_first_comic_link(cls):
2174
        """Get link to first comics."""
2175
        return get_soup_at_url(cls.url).find('img', attrs={'name': 'beginArrow'}).parent
2176
2177
    @classmethod
2178
    def get_navi_link(cls, last_soup, next_):
2179
        """Get link to next or previous comic."""
2180
        return last_soup.find('img', attrs={'name': 'rightArrow' if next_ else 'leftArrow'}).parent
2181
2182
    @classmethod
2183
    def get_comic_info(cls, soup, link):
2184
        """Get information about a particular comics."""
2185
        title = soup.find('meta', attrs={'name': 'twitter:title'})['content']
2186
        imgs = soup.find_all('meta', property='og:image')
2187
        return {
2188
            'title': title,
2189
            'img': [i['content'] for i in imgs],
2190
        }
2191
2192
2193 View Code Duplication
class TurnOffUs(GenericListableComic):
2194
    """Class to retrieve TurnOffUs comics."""
2195
    name = 'turnoffus'
2196
    long_name = 'Turn Off Us'
2197
    url = 'http://turnoff.us'
2198
    get_url_from_archive_element = join_cls_url_to_href
2199
2200
    @classmethod
2201
    def get_archive_elements(cls):
2202
        archive_url = urljoin_wrapper(cls.url, 'all')
2203
        post_list = get_soup_at_url(archive_url).find('ul', class_='post-list')
2204
        return reversed(post_list.find_all('a', class_='post-link'))
2205
2206
    @classmethod
2207
    def get_comic_info(cls, soup, archive_elt):
2208
        """Get information about a particular comics."""
2209
        title = soup.find('meta', property='og:title')['content']
2210
        imgs = soup.find_all('meta', property='og:image')
2211
        return {
2212
            'title': title,
2213
            'img': [i['content'] for i in imgs],
2214
        }
2215
2216
2217
class ThingsInSquares(GenericListableComic):
2218
    """Class to retrieve Things In Squares comics."""
2219
    # This can be retrieved in other languages
2220
    # Also on https://tapastic.com/series/Things-in-Squares
2221
    name = 'squares'
2222
    long_name = 'Things in squares'
2223
    url = 'http://www.thingsinsquares.com'
2224
2225
    @classmethod
2226
    def get_comic_info(cls, soup, tr):
2227
        """Get information about a particular comics."""
2228
        _, td2, td3 = tr.find_all('td')
2229
        a = td2.find('a')
2230
        date_str = td3.string
2231
        day = string_to_date(date_str, "%m.%d.%y")
2232
        title = a.string
2233
        title2 = soup.find('meta', property='og:title')['content']
2234
        desc = soup.find('meta', property='og:description')
2235
        description = desc['content'] if desc else ''
2236
        tags = ' '.join(t['content'] for t in soup.find_all('meta', property='article:tag'))
2237
        imgs = soup.find_all('meta', property='og:image')
2238
        return {
2239
            'day': day.day,
2240
            'month': day.month,
2241
            'year': day.year,
2242
            'title': title,
2243
            'title2': title2,
2244
            'description': description,
2245
            'tags': tags,
2246
            'img': [i['content'] for i in imgs],
2247
        }
2248
2249
    @classmethod
2250
    def get_url_from_archive_element(cls, tr):
2251
        _, td2, __ = tr.find_all('td')
2252
        return td2.find('a')['href']
2253
2254
    @classmethod
2255
    def get_archive_elements(cls):
2256
        archive_url = urljoin_wrapper(cls.url, 'archive-2')
2257
        return reversed(get_soup_at_url(archive_url).find('tbody').find_all('tr'))
2258
2259
2260 View Code Duplication
class HappleTea(GenericNavigableComic):
2261
    """Class to retrieve Happle Tea Comics."""
2262
    name = 'happletea'
2263
    long_name = 'Happle Tea'
2264
    url = 'http://www.happletea.com'
2265
    get_first_comic_link = get_a_navi_navifirst
2266
    get_navi_link = get_link_rel_next
2267
2268
    @classmethod
2269
    def get_comic_info(cls, soup, link):
2270
        """Get information about a particular comics."""
2271
        imgs = soup.find('div', id='comic').find_all('img')
2272
        post = soup.find('div', class_='post-content')
2273
        title = post.find('h2', class_='post-title').string
2274
        author = post.find('a', rel='author').string
2275
        date_str = post.find('span', class_='post-date').string
2276
        day = string_to_date(date_str, "%B %d, %Y")
2277
        assert all(i['alt'] == i['title'] for i in imgs)
2278
        return {
2279
            'title': title,
2280
            'img': [i['src'] for i in imgs],
2281
            'alt': ''.join(i['alt'] for i in imgs),
2282
            'month': day.month,
2283
            'year': day.year,
2284
            'day': day.day,
2285
            'author': author,
2286
        }
2287
2288
2289
class RockPaperScissors(GenericNavigableComic):
2290
    """Class to retrieve Rock Paper Scissors comics."""
2291
    name = 'rps'
2292
    long_name = 'Rock Paper Scissors'
2293
    url = 'http://rps-comics.com'
2294
    get_first_comic_link = get_a_navi_navifirst
2295
    get_navi_link = get_link_rel_next
2296
2297
    @classmethod
2298
    def get_comic_info(cls, soup, link):
2299
        """Get information about a particular comics."""
2300
        title = soup.find('title').string
2301
        imgs = soup.find_all('meta', property='og:image')
2302
        short_url = soup.find('link', rel='shortlink')['href']
2303
        transcript = soup.find('div', id='transcript-content').string
2304
        return {
2305
            'title': title,
2306
            'transcript': transcript,
2307
            'short_url': short_url,
2308
            'img': [i['content'] for i in imgs],
2309
        }
2310
2311
2312
class FatAwesomeComics(GenericNavigableComic):
2313
    """Class to retrieve Fat Awesome Comics."""
2314
    # Also on http://fatawesomecomedy.tumblr.com
2315
    name = 'fatawesome'
2316
    long_name = 'Fat Awesome'
2317
    url = 'http://fatawesome.com/comics'
2318
    get_navi_link = get_a_rel_next
2319
    get_first_comic_link = simulate_first_link
2320
    first_url = 'http://fatawesome.com/shortbus/'
2321
2322
    @classmethod
2323
    def get_comic_info(cls, soup, link):
2324
        """Get information about a particular comics."""
2325
        title = soup.find('meta', attrs={'name': 'twitter:title'})['content']
2326
        description = soup.find('meta', attrs={'name': 'description'})['content']
2327
        tags_prop = soup.find('meta', property='article:tag')
2328
        tags = tags_prop['content'] if tags_prop else ""
2329
        date_str = soup.find('meta', property='article:published_time')['content'][:10]
2330
        day = string_to_date(date_str, "%Y-%m-%d")
2331
        imgs = soup.find_all('img', attrs={'data-recalc-dims': "1"})
2332
        assert len(imgs) == 1, imgs
2333
        return {
2334
            'title': title,
2335
            'description': description,
2336
            'tags': tags,
2337
            'alt': "".join(i['alt'] for i in imgs),
2338
            'img': [i['src'].rsplit('?', 1)[0] for i in imgs],
2339
            'month': day.month,
2340
            'year': day.year,
2341
            'day': day.day,
2342
        }
2343
2344
2345
class PeterLauris(GenericNavigableComic):
2346
    """Class to retrieve Peter Lauris comics."""
2347
    name = 'peterlauris'
2348
    long_name = 'Peter Lauris'
2349
    url = 'http://peterlauris.com/comics'
2350
    get_navi_link = get_a_rel_next
2351
    get_first_comic_link = simulate_first_link
2352
    first_url = 'http://peterlauris.com/comics/just-in-case/'
2353
2354
    @classmethod
2355
    def get_comic_info(cls, soup, link):
2356
        """Get information about a particular comics."""
2357
        title = soup.find('meta', attrs={'name': 'twitter:title'})['content']
2358
        date_str = soup.find('meta', property='article:published_time')['content'][:10]
2359
        day = string_to_date(date_str, "%Y-%m-%d")
2360
        imgs = soup.find_all('meta', property='og:image')
2361
        return {
2362
            'title': title,
2363
            'img': [i['content'] for i in imgs],
2364
            'month': day.month,
2365
            'year': day.year,
2366
            'day': day.day,
2367
        }
2368
2369
2370
class JuliasDrawings(GenericListableComic):
2371
    """Class to retrieve Julia's Drawings."""
2372
    name = 'julia'
2373
    long_name = "Julia's Drawings"
2374
    url = 'https://drawings.jvns.ca'
2375
    get_url_from_archive_element = get_href
2376
2377
    @classmethod
2378
    def get_archive_elements(cls):
2379
        articles = get_soup_at_url(cls.url).find_all('article', class_='li post')
2380
        return [art.find('a') for art in reversed(articles)]
2381
2382
    @classmethod
2383
    def get_comic_info(cls, soup, archive_elt):
2384
        """Get information about a particular comics."""
2385
        date_str = soup.find('meta', property='og:article:published_time')['content'][:10]
2386
        day = string_to_date(date_str, "%Y-%m-%d")
2387
        title = soup.find('h3', class_='p-post-title').string
2388
        imgs = soup.find('section', class_='post-content').find_all('img')
2389
        return {
2390
            'title': title,
2391
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
2392
            'month': day.month,
2393
            'year': day.year,
2394
            'day': day.day,
2395
        }
2396
2397
2398
class AnythingComic(GenericListableComic):
2399
    """Class to retrieve Anything Comics."""
2400
    # Also on http://tapastic.com/series/anything
2401
    name = 'anythingcomic'
2402
    long_name = 'Anything Comic'
2403
    url = 'http://www.anythingcomic.com'
2404
2405
    @classmethod
2406
    def get_archive_elements(cls):
2407
        archive_url = urljoin_wrapper(cls.url, 'archive/')
2408
        # The first 2 <tr>'s do not correspond to comics
2409
        return get_soup_at_url(archive_url).find('table', id='chapter_table').find_all('tr')[2:]
2410
2411
    @classmethod
2412
    def get_url_from_archive_element(cls, tr):
2413
        """Get url corresponding to an archive element."""
2414
        _, td_comic, td_date, _ = tr.find_all('td')
2415
        link = td_comic.find('a')
2416
        return urljoin_wrapper(cls.url, link['href'])
2417
2418 View Code Duplication
    @classmethod
2419
    def get_comic_info(cls, soup, tr):
2420
        """Get information about a particular comics."""
2421
        td_num, td_comic, td_date, _ = tr.find_all('td')
2422
        num = int(td_num.string)
2423
        link = td_comic.find('a')
2424
        title = link.string
2425
        imgs = soup.find_all('img', id='comic_image')
2426
        date_str = td_date.string
2427
        day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y, %I:%M %p")
2428
        assert len(imgs) == 1, imgs
2429
        assert all(i.get('alt') == i.get('title') for i in imgs)
2430
        return {
2431
            'num': num,
2432
            'title': title,
2433
            'alt': imgs[0].get('alt', ''),
2434
            'img': [i['src'] for i in imgs],
2435
            'month': day.month,
2436
            'year': day.year,
2437
            'day': day.day,
2438
        }
2439
2440
2441 View Code Duplication
class LonnieMillsap(GenericNavigableComic):
2442
    """Class to retrieve Lonnie Millsap's comics."""
2443
    name = 'millsap'
2444
    long_name = 'Lonnie Millsap'
2445
    url = 'http://www.lonniemillsap.com'
2446
    get_navi_link = get_link_rel_next
2447
    get_first_comic_link = simulate_first_link
2448
    first_url = 'http://www.lonniemillsap.com/?p=42'
2449
2450
    @classmethod
2451
    def get_comic_info(cls, soup, link):
2452
        """Get information about a particular comics."""
2453
        title = soup.find('h2', class_='post-title').string
2454
        post = soup.find('div', class_='post-content')
2455
        author = post.find("span", class_="post-author").find("a").string
2456
        date_str = post.find("span", class_="post-date").string
2457
        day = string_to_date(date_str, "%B %d, %Y")
2458
        imgs = post.find("div", class_="entry").find_all("img")
2459
        return {
2460
            'title': title,
2461
            'author': author,
2462
            'img': [i['src'] for i in imgs],
2463
            'month': day.month,
2464
            'year': day.year,
2465
            'day': day.day,
2466
        }
2467
2468
2469
class LinsEditions(GenericNavigableComic):
2470
    """Class to retrieve L.I.N.S. Editions comics."""
2471
    # Also on https://linscomics.tumblr.com
2472
    # Now on https://warandpeas.com
2473
    name = 'lins'
2474
    long_name = 'L.I.N.S. Editions'
2475
    url = 'https://linsedition.com'
2476
    _categories = ('LINS', )
2477
    get_navi_link = get_link_rel_next
2478
    get_first_comic_link = simulate_first_link
2479
    first_url = 'https://linsedition.com/2011/09/07/l-i-n-s/'
2480
2481
    @classmethod
2482
    def get_comic_info(cls, soup, link):
2483
        """Get information about a particular comics."""
2484
        title = soup.find('meta', property='og:title')['content']
2485
        imgs = soup.find_all('meta', property='og:image')
2486
        date_str = soup.find('meta', property='article:published_time')['content'][:10]
2487
        day = string_to_date(date_str, "%Y-%m-%d")
2488
        return {
2489
            'title': title,
2490
            'img': [i['content'] for i in imgs],
2491
            'month': day.month,
2492
            'year': day.year,
2493
            'day': day.day,
2494
        }
2495
2496
2497
class ThorsThundershack(GenericNavigableComic):
2498
    """Class to retrieve Thor's Thundershack comics."""
2499
    # Also on http://tapastic.com/series/Thors-Thundershac
2500
    name = 'thor'
2501
    long_name = 'Thor\'s Thundershack'
2502
    url = 'http://www.thorsthundershack.com'
2503
    _categories = ('THOR', )
2504
    get_url_from_link = join_cls_url_to_href
2505
2506
    @classmethod
2507
    def get_first_comic_link(cls):
2508
        """Get link to first comics."""
2509
        return get_soup_at_url(cls.url).find('a', class_='first navlink')
2510
2511
    @classmethod
2512
    def get_navi_link(cls, last_soup, next_):
2513
        """Get link to next or previous comic."""
2514
        for link in last_soup.find_all('a', rel='next' if next_ else 'prev'):
2515
            if link['href'] != '/comic':
2516
                return link
2517
        return None
2518
2519
    @classmethod
2520
    def get_comic_info(cls, soup, link):
2521
        """Get information about a particular comics."""
2522
        title = soup.find('meta', attrs={'name': 'description'})["content"]
2523
        description = soup.find('div', itemprop='articleBody').text
2524
        author = soup.find('span', itemprop='author copyrightHolder').string
2525
        imgs = soup.find_all('img', itemprop='image')
2526
        assert all(i['title'] == i['alt'] for i in imgs)
2527
        alt = imgs[0]['alt'] if imgs else ""
2528
        date_str = soup.find('time', itemprop='datePublished')["datetime"]
2529
        day = string_to_date(date_str, "%Y-%m-%d %H:%M:%S")
2530
        return {
2531
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
2532
            'month': day.month,
2533
            'year': day.year,
2534
            'day': day.day,
2535
            'author': author,
2536
            'title': title,
2537
            'alt': alt,
2538
            'description': description,
2539
        }
2540
2541
2542
class GerbilWithAJetpack(GenericNavigableComic):
2543
    """Class to retrieve GerbilWithAJetpack comics."""
2544
    name = 'gerbil'
2545
    long_name = 'Gerbil With A Jetpack'
2546
    url = 'http://gerbilwithajetpack.com'
2547
    get_first_comic_link = get_a_navi_navifirst
2548
    get_navi_link = get_a_rel_next
2549
2550
    @classmethod
2551
    def get_comic_info(cls, soup, link):
2552
        """Get information about a particular comics."""
2553
        title = soup.find('h2', class_='post-title').string
2554
        author = soup.find("span", class_="post-author").find("a").string
2555
        date_str = soup.find("span", class_="post-date").string
2556
        day = string_to_date(date_str, "%B %d, %Y")
2557
        imgs = soup.find("div", id="comic").find_all("img")
2558
        alt = imgs[0]['alt']
2559
        assert all(i['alt'] == i['title'] == alt for i in imgs)
2560
        return {
2561
            'img': [i['src'] for i in imgs],
2562
            'title': title,
2563
            'alt': alt,
2564
            'author': author,
2565
            'day': day.day,
2566
            'month': day.month,
2567
            'year': day.year
2568
        }
2569
2570
2571 View Code Duplication
class EveryDayBlues(GenericDeletedComic, GenericNavigableComic):
2572
    """Class to retrieve EveryDayBlues Comics."""
2573
    name = "blues"
2574
    long_name = "Every Day Blues"
2575
    url = "http://everydayblues.net"
2576
    get_first_comic_link = get_a_navi_navifirst
2577
    get_navi_link = get_link_rel_next
2578
2579
    @classmethod
2580
    def get_comic_info(cls, soup, link):
2581
        """Get information about a particular comics."""
2582
        title = soup.find("h2", class_="post-title").string
2583
        author = soup.find("span", class_="post-author").find("a").string
2584
        date_str = soup.find("span", class_="post-date").string
2585
        day = string_to_date(date_str, "%d. %B %Y", "de_DE.utf8")
2586
        imgs = soup.find("div", id="comic").find_all("img")
2587
        assert all(i['alt'] == i['title'] == title for i in imgs)
2588
        assert len(imgs) <= 1, imgs
2589
        return {
2590
            'img': [i['src'] for i in imgs],
2591
            'title': title,
2592
            'author': author,
2593
            'day': day.day,
2594
            'month': day.month,
2595
            'year': day.year
2596
        }
2597
2598
2599 View Code Duplication
class BiterComics(GenericNavigableComic):
2600
    """Class to retrieve Biter Comics."""
2601
    name = "biter"
2602
    long_name = "Biter Comics"
2603
    url = "http://www.bitercomics.com"
2604
    get_first_comic_link = get_a_navi_navifirst
2605
    get_navi_link = get_link_rel_next
2606
2607
    @classmethod
2608
    def get_comic_info(cls, soup, link):
2609
        """Get information about a particular comics."""
2610
        title = soup.find("h1", class_="entry-title").string
2611
        author = soup.find("span", class_="author vcard").find("a").string
2612
        date_str = soup.find("span", class_="entry-date").string
2613
        day = string_to_date(date_str, "%B %d, %Y")
2614
        imgs = soup.find("div", id="comic").find_all("img")
2615
        assert all(i['alt'] == i['title'] for i in imgs)
2616
        assert len(imgs) == 1, imgs
2617
        alt = imgs[0]['alt']
2618
        return {
2619
            'img': [i['src'] for i in imgs],
2620
            'title': title,
2621
            'alt': alt,
2622
            'author': author,
2623
            'day': day.day,
2624
            'month': day.month,
2625
            'year': day.year
2626
        }
2627
2628
2629 View Code Duplication
class TheAwkwardYeti(GenericNavigableComic):
2630
    """Class to retrieve The Awkward Yeti comics."""
2631
    # Also on http://www.gocomics.com/the-awkward-yeti
2632
    # Also on http://larstheyeti.tumblr.com
2633
    # Also on https://tapastic.com/series/TheAwkwardYeti
2634
    name = 'yeti'
2635
    long_name = 'The Awkward Yeti'
2636
    url = 'http://theawkwardyeti.com'
2637
    _categories = ('YETI', )
2638
    get_first_comic_link = get_a_navi_navifirst
2639
    get_navi_link = get_link_rel_next
2640
2641
    @classmethod
2642
    def get_comic_info(cls, soup, link):
2643
        """Get information about a particular comics."""
2644
        title = soup.find('h2', class_='post-title').string
2645
        date_str = soup.find("span", class_="post-date").string
2646
        day = string_to_date(date_str, "%B %d, %Y")
2647
        imgs = soup.find("div", id="comic").find_all("img")
2648
        assert all(idx > 0 or i['alt'] == i['title'] for idx, i in enumerate(imgs))
2649
        return {
2650
            'img': [i['src'] for i in imgs],
2651
            'title': title,
2652
            'day': day.day,
2653
            'month': day.month,
2654
            'year': day.year
2655
        }
2656
2657
2658
class PleasantThoughts(GenericNavigableComic):
2659
    """Class to retrieve Pleasant Thoughts comics."""
2660
    name = 'pleasant'
2661
    long_name = 'Pleasant Thoughts'
2662
    url = 'http://pleasant-thoughts.com'
2663
    get_first_comic_link = get_a_navi_navifirst
2664
    get_navi_link = get_link_rel_next
2665
2666
    @classmethod
2667
    def get_comic_info(cls, soup, link):
2668
        """Get information about a particular comics."""
2669
        post = soup.find('div', class_='post-content')
2670
        title = post.find('h2', class_='post-title').string
2671
        imgs = post.find("div", class_="entry").find_all("img")
2672
        return {
2673
            'title': title,
2674
            'img': [i['src'] for i in imgs],
2675
        }
2676
2677
2678 View Code Duplication
class MisterAndMe(GenericNavigableComic):
2679
    """Class to retrieve Mister & Me Comics."""
2680
    # Also on http://www.gocomics.com/mister-and-me
2681
    # Also on https://tapastic.com/series/Mister-and-Me
2682
    name = 'mister'
2683
    long_name = 'Mister & Me'
2684
    url = 'http://www.mister-and-me.com'
2685
    get_first_comic_link = get_a_comicnavbase_comicnavfirst
2686
    get_navi_link = get_link_rel_next
2687
2688
    @classmethod
2689
    def get_comic_info(cls, soup, link):
2690
        """Get information about a particular comics."""
2691
        title = soup.find('h2', class_='post-title').string
2692
        author = soup.find("span", class_="post-author").find("a").string
2693
        date_str = soup.find("span", class_="post-date").string
2694
        day = string_to_date(date_str, "%B %d, %Y")
2695
        imgs = soup.find("div", id="comic").find_all("img")
2696
        assert all(i['alt'] == i['title'] for i in imgs)
2697
        assert len(imgs) <= 1, imgs
2698
        alt = imgs[0]['alt'] if imgs else ""
2699
        return {
2700
            'img': [i['src'] for i in imgs],
2701
            'title': title,
2702
            'alt': alt,
2703
            'author': author,
2704
            'day': day.day,
2705
            'month': day.month,
2706
            'year': day.year
2707
        }
2708
2709
2710
class LastPlaceComics(GenericNavigableComic):
2711
    """Class to retrieve Last Place Comics."""
2712
    name = 'lastplace'
2713
    long_name = 'Last Place Comics'
2714
    url = "http://lastplacecomics.com"
2715
    get_first_comic_link = get_a_comicnavbase_comicnavfirst
2716
    get_navi_link = get_link_rel_next
2717
2718
    @classmethod
2719
    def get_comic_info(cls, soup, link):
2720
        """Get information about a particular comics."""
2721
        title = soup.find('h2', class_='post-title').string
2722
        author = soup.find("span", class_="post-author").find("a").string
2723
        date_str = soup.find("span", class_="post-date").string
2724
        day = string_to_date(date_str, "%B %d, %Y")
2725
        imgs = soup.find("div", id="comic").find_all("img")
2726
        assert all(i['alt'] == i['title'] for i in imgs)
2727
        assert len(imgs) <= 1, imgs
2728
        alt = imgs[0]['alt'] if imgs else ""
2729
        return {
2730
            'img': [i['src'] for i in imgs],
2731
            'title': title,
2732
            'alt': alt,
2733
            'author': author,
2734
            'day': day.day,
2735
            'month': day.month,
2736
            'year': day.year
2737
        }
2738
2739
2740 View Code Duplication
class TalesOfAbsurdity(GenericNavigableComic):
2741
    """Class to retrieve Tales Of Absurdity comics."""
2742
    # Also on http://tapastic.com/series/Tales-Of-Absurdity
2743
    # Also on http://talesofabsurdity.tumblr.com
2744
    name = 'absurdity'
2745
    long_name = 'Tales of Absurdity'
2746
    url = 'http://talesofabsurdity.com'
2747
    _categories = ('ABSURDITY', )
2748
    get_first_comic_link = get_a_navi_navifirst
2749
    get_navi_link = get_a_navi_comicnavnext_navinext
2750
2751
    @classmethod
2752
    def get_comic_info(cls, soup, link):
2753
        """Get information about a particular comics."""
2754
        title = soup.find('h2', class_='post-title').string
2755
        author = soup.find("span", class_="post-author").find("a").string
2756
        date_str = soup.find("span", class_="post-date").string
2757
        day = string_to_date(date_str, "%B %d, %Y")
2758
        imgs = soup.find("div", id="comic").find_all("img")
2759
        assert all(i['alt'] == i['title'] for i in imgs)
2760
        alt = imgs[0]['alt'] if imgs else ""
2761
        return {
2762
            'img': [i['src'] for i in imgs],
2763
            'title': title,
2764
            'alt': alt,
2765
            'author': author,
2766
            'day': day.day,
2767
            'month': day.month,
2768
            'year': day.year
2769
        }
2770
2771
2772 View Code Duplication
class EndlessOrigami(GenericComicNotWorking, GenericNavigableComic):  # Nav not working
2773
    """Class to retrieve Endless Origami Comics."""
2774
    name = "origami"
2775
    long_name = "Endless Origami"
2776
    url = "http://endlessorigami.com"
2777
    get_first_comic_link = get_a_navi_navifirst
2778
    get_navi_link = get_link_rel_next
2779
2780
    @classmethod
2781
    def get_comic_info(cls, soup, link):
2782
        """Get information about a particular comics."""
2783
        title = soup.find('h2', class_='post-title').string
2784
        author = soup.find("span", class_="post-author").find("a").string
2785
        date_str = soup.find("span", class_="post-date").string
2786
        day = string_to_date(date_str, "%B %d, %Y")
2787
        imgs = soup.find("div", id="comic").find_all("img")
2788
        assert all(i['alt'] == i['title'] for i in imgs)
2789
        alt = imgs[0]['alt'] if imgs else ""
2790
        return {
2791
            'img': [i['src'] for i in imgs],
2792
            'title': title,
2793
            'alt': alt,
2794
            'author': author,
2795
            'day': day.day,
2796
            'month': day.month,
2797
            'year': day.year
2798
        }
2799
2800
2801 View Code Duplication
class PlanC(GenericNavigableComic):
2802
    """Class to retrieve Plan C comics."""
2803
    name = 'planc'
2804
    long_name = 'Plan C'
2805
    url = 'http://www.plancomic.com'
2806
    get_first_comic_link = get_a_navi_navifirst
2807
    get_navi_link = get_a_navi_comicnavnext_navinext
2808
2809
    @classmethod
2810
    def get_comic_info(cls, soup, link):
2811
        """Get information about a particular comics."""
2812
        title = soup.find('h2', class_='post-title').string
2813
        date_str = soup.find("span", class_="post-date").string
2814
        day = string_to_date(date_str, "%B %d, %Y")
2815
        imgs = soup.find('div', id='comic').find_all('img')
2816
        return {
2817
            'title': title,
2818
            'img': [i['src'] for i in imgs],
2819
            'month': day.month,
2820
            'year': day.year,
2821
            'day': day.day,
2822
        }
2823
2824
2825 View Code Duplication
class BuniComic(GenericNavigableComic):
2826
    """Class to retrieve Buni Comics."""
2827
    name = 'buni'
2828
    long_name = 'BuniComics'
2829
    url = 'http://www.bunicomic.com'
2830
    get_first_comic_link = get_a_comicnavbase_comicnavfirst
2831
    get_navi_link = get_link_rel_next
2832
2833
    @classmethod
2834
    def get_comic_info(cls, soup, link):
2835
        """Get information about a particular comics."""
2836
        imgs = soup.find('div', id='comic').find_all('img')
2837
        assert all(i['alt'] == i['title'] for i in imgs)
2838
        assert len(imgs) == 1, imgs
2839
        return {
2840
            'img': [i['src'] for i in imgs],
2841
            'title': imgs[0]['title'],
2842
        }
2843
2844
2845 View Code Duplication
class GenericCommitStrip(GenericNavigableComic):
2846
    """Generic class to retrieve Commit Strips in different languages."""
2847
    get_navi_link = get_a_rel_next
2848
    get_first_comic_link = simulate_first_link
2849
    first_url = NotImplemented
2850
2851
    @classmethod
2852
    def get_comic_info(cls, soup, link):
2853
        """Get information about a particular comics."""
2854
        desc = soup.find('meta', property='og:description')['content']
2855
        title = soup.find('meta', property='og:title')['content']
2856
        imgs = soup.find('div', class_='entry-content').find_all('img')
2857
        title2 = ' '.join(i.get('title', '') for i in imgs)
2858
        return {
2859
            'title': title,
2860
            'title2': title2,
2861
            'description': desc,
2862
            'img': [urljoin_wrapper(cls.url, convert_iri_to_plain_ascii_uri(i['src'])) for i in imgs],
2863
        }
2864
2865
2866
class CommitStripFr(GenericCommitStrip):
2867
    """Class to retrieve Commit Strips in French."""
2868
    name = 'commit_fr'
2869
    long_name = 'Commit Strip (Fr)'
2870
    url = 'http://www.commitstrip.com/fr'
2871
    _categories = ('FRANCAIS', )
2872
    first_url = 'http://www.commitstrip.com/fr/2012/02/22/interview/'
2873
2874
2875
class CommitStripEn(GenericCommitStrip):
2876
    """Class to retrieve Commit Strips in English."""
2877
    name = 'commit_en'
2878
    long_name = 'Commit Strip (En)'
2879
    url = 'http://www.commitstrip.com/en'
2880
    first_url = 'http://www.commitstrip.com/en/2012/02/22/interview/'
2881
2882
2883 View Code Duplication
class GenericBoumerie(GenericNavigableComic):
2884
    """Generic class to retrieve Boumeries comics in different languages."""
2885
    # Also on http://boumeries.tumblr.com
2886
    get_first_comic_link = get_a_navi_navifirst
2887
    get_navi_link = get_link_rel_next
2888
    date_format = NotImplemented
2889
    lang = NotImplemented
2890
2891
    @classmethod
2892
    def get_comic_info(cls, soup, link):
2893
        """Get information about a particular comics."""
2894
        title = soup.find('h2', class_='post-title').string
2895
        short_url = soup.find('link', rel='shortlink')['href']
2896
        author = soup.find("span", class_="post-author").find("a").string
2897
        date_str = soup.find('span', class_='post-date').string
2898
        day = string_to_date(date_str, cls.date_format, cls.lang)
2899
        imgs = soup.find('div', id='comic').find_all('img')
2900
        assert all(i['alt'] == i['title'] for i in imgs)
2901
        return {
2902
            'short_url': short_url,
2903
            'img': [i['src'] for i in imgs],
2904
            'title': title,
2905
            'author': author,
2906
            'month': day.month,
2907
            'year': day.year,
2908
            'day': day.day,
2909
        }
2910
2911
2912
class BoumerieEn(GenericBoumerie):
2913
    """Class to retrieve Boumeries comics in English."""
2914
    name = 'boumeries_en'
2915
    long_name = 'Boumeries (En)'
2916
    url = 'http://comics.boumerie.com'
2917
    _categories = ('BOUMERIES', )
2918
    date_format = "%B %d, %Y"
2919
    lang = 'en_GB.UTF-8'
2920
2921
2922
class BoumerieFr(GenericBoumerie):
2923
    """Class to retrieve Boumeries comics in French."""
2924
    name = 'boumeries_fr'
2925
    long_name = 'Boumeries (Fr)'
2926
    url = 'http://bd.boumerie.com'
2927
    _categories = ('BOUMERIES', 'FRANCAIS')
2928
    date_format = "%B %d, %Y"  # Used to be "%A, %d %B %Y"
2929
    lang = "fr_FR.utf8"
2930
2931
2932 View Code Duplication
class UnearthedComics(GenericNavigableComic):
2933
    """Class to retrieve Unearthed comics."""
2934
    # Also on http://tapastic.com/series/UnearthedComics
2935
    # Also on https://unearthedcomics.tumblr.com
2936
    name = 'unearthed'
2937
    long_name = 'Unearthed Comics'
2938
    url = 'http://unearthedcomics.com'
2939
    _categories = ('UNEARTHED', )
2940
    get_navi_link = get_link_rel_next
2941
    get_first_comic_link = simulate_first_link
2942
    first_url = 'http://unearthedcomics.com/comics/world-with-turn-signals/'
2943
2944
    @classmethod
2945
    def get_comic_info(cls, soup, link):
2946
        """Get information about a particular comics."""
2947
        short_url = soup.find('link', rel='shortlink')['href']
2948
        title_elt = soup.find('h1') or soup.find('h2')
2949
        title = title_elt.string if title_elt else ""
2950
        desc = soup.find('meta', property='og:description')
2951
        date_str = soup.find('time', class_='published updated hidden')['datetime']
2952
        day = string_to_date(date_str, "%Y-%m-%d")
2953
        post = soup.find('div', class_="entry content entry-content type-portfolio")
2954
        imgs = post.find_all('img')
2955
        return {
2956
            'title': title,
2957
            'description': desc,
2958
            'url2': short_url,
2959
            'img': [i['src'] for i in imgs],
2960
            'month': day.month,
2961
            'year': day.year,
2962
            'day': day.day,
2963
        }
2964
2965
2966 View Code Duplication
class Optipess(GenericNavigableComic):
2967
    """Class to retrieve Optipess comics."""
2968
    name = 'optipess'
2969
    long_name = 'Optipess'
2970
    url = 'http://www.optipess.com'
2971
    get_first_comic_link = get_a_navi_navifirst
2972
    get_navi_link = get_link_rel_next
2973
2974
    @classmethod
2975
    def get_comic_info(cls, soup, link):
2976
        """Get information about a particular comics."""
2977
        title = soup.find('h2', class_='post-title').string
2978
        author = soup.find("span", class_="post-author").find("a").string
2979
        comic = soup.find('div', id='comic')
2980
        imgs = comic.find_all('img') if comic else []
2981
        alt = imgs[0]['title'] if imgs else ""
2982
        assert all(i['alt'] == i['title'] == alt for i in imgs)
2983
        date_str = soup.find('span', class_='post-date').string
2984
        day = string_to_date(date_str, "%B %d, %Y")
2985
        return {
2986
            'title': title,
2987
            'alt': alt,
2988
            'author': author,
2989
            'img': [i['src'] for i in imgs],
2990
            'month': day.month,
2991
            'year': day.year,
2992
            'day': day.day,
2993
        }
2994
2995
2996
class PainTrainComic(GenericNavigableComic):
2997
    """Class to retrieve Pain Train Comics."""
2998
    name = 'paintrain'
2999
    long_name = 'Pain Train Comics'
3000
    url = 'http://paintraincomic.com'
3001
    get_first_comic_link = get_a_navi_navifirst
3002
    get_navi_link = get_link_rel_next
3003
3004
    @classmethod
3005
    def get_comic_info(cls, soup, link):
3006
        """Get information about a particular comics."""
3007
        title = soup.find('h2', class_='post-title').string
3008
        short_url = soup.find('link', rel='shortlink')['href']
3009
        short_url_re = re.compile('^%s/\\?p=([0-9]*)' % cls.url)
3010
        num = int(short_url_re.match(short_url).groups()[0])
3011
        imgs = soup.find('div', id='comic').find_all('img')
3012
        alt = imgs[0]['title']
3013
        assert all(i['alt'] == i['title'] == alt for i in imgs)
3014
        date_str = soup.find('span', class_='post-date').string
3015
        day = string_to_date(date_str, "%d/%m/%Y")
3016
        return {
3017
            'short_url': short_url,
3018
            'num': num,
3019
            'img': [i['src'] for i in imgs],
3020
            'month': day.month,
3021
            'year': day.year,
3022
            'day': day.day,
3023
            'alt': alt,
3024
            'title': title,
3025
        }
3026
3027
3028
class MoonBeard(GenericNavigableComic):
3029
    """Class to retrieve MoonBeard comics."""
3030
    # Also on http://squireseses.tumblr.com
3031
    # Also on http://www.webtoons.com/en/comedy/moon-beard/list?title_no=471
3032
    name = 'moonbeard'
3033
    long_name = 'Moon Beard'
3034
    url = 'http://moonbeard.com'
3035
    _categories = ('MOONBEARD', )
3036
    get_first_comic_link = get_a_navi_navifirst
3037
    get_navi_link = get_a_navi_navinext
3038
3039
    @classmethod
3040
    def get_comic_info(cls, soup, link):
3041
        """Get information about a particular comics."""
3042
        title = soup.find('h2', class_='post-title').string
3043
        short_url = soup.find('link', rel='shortlink')['href']
3044
        short_url_re = re.compile('^%s/\\?p=([0-9]*)' % cls.url)
3045
        num = int(short_url_re.match(short_url).groups()[0])
3046
        imgs = soup.find('div', id='comic').find_all('img')
3047
        alt = imgs[0]['title']
3048
        assert all(i['alt'] == i['title'] == alt for i in imgs)
3049
        date_str = soup.find('span', class_='post-date').string
3050
        day = string_to_date(date_str, "%B %d, %Y")
3051
        tags = ' '.join(t['content'] for t in soup.find_all('meta', property='article:tag'))
3052
        author = soup.find('span', class_='post-author').string
3053
        return {
3054
            'short_url': short_url,
3055
            'num': num,
3056
            'img': [i['src'] for i in imgs],
3057
            'month': day.month,
3058
            'year': day.year,
3059
            'day': day.day,
3060
            'title': title,
3061
            'tags': tags,
3062
            'alt': alt,
3063
            'author': author,
3064
        }
3065
3066
3067
class SystemComic(GenericNavigableComic):
3068
    """Class to retrieve System Comic."""
3069
    name = 'system'
3070
    long_name = 'System Comic'
3071
    url = 'http://www.systemcomic.com'
3072
    get_navi_link = get_a_rel_next
3073
3074
    @classmethod
3075
    def get_first_comic_link(cls):
3076
        """Get link to first comics."""
3077
        return get_soup_at_url(cls.url).find('li', class_='first').find('a')
3078
3079
    @classmethod
3080
    def get_comic_info(cls, soup, link):
3081
        """Get information about a particular comics."""
3082
        title = soup.find('meta', property='og:title')['content']
3083
        desc = soup.find('meta', property='og:description')['content']
3084
        date_str = soup.find('time')["datetime"]
3085
        day = string_to_date(date_str, "%Y-%m-%d")
3086
        imgs = soup.find('figure').find_all('img')
3087
        return {
3088
            'title': title,
3089
            'description': desc,
3090
            'day': day.day,
3091
            'month': day.month,
3092
            'year': day.year,
3093
            'img': [i['src'] for i in imgs],
3094
        }
3095
3096
3097 View Code Duplication
class LittleLifeLines(GenericNavigableComic):
3098
    """Class to retrieve Little Life Lines comics."""
3099
    # Also on https://little-life-lines.tumblr.com
3100
    name = 'life'
3101
    long_name = 'Little Life Lines'
3102
    url = 'http://www.littlelifelines.com'
3103
    get_url_from_link = join_cls_url_to_href
3104
    get_first_comic_link = simulate_first_link
3105
    first_url = 'http://www.littlelifelines.com/comics/well-done'
3106
3107
    @classmethod
3108
    def get_navi_link(cls, last_soup, next_):
3109
        """Get link to next or previous comic."""
3110
        # prev is next / next is prev
3111
        li = last_soup.find('li', class_='prev' if next_ else 'next')
3112
        return li.find('a') if li else None
3113
3114
    @classmethod
3115
    def get_comic_info(cls, soup, link):
3116
        """Get information about a particular comics."""
3117
        title = soup.find('meta', property='og:title')['content']
3118
        desc = soup.find('meta', property='og:description')['content']
3119
        date_str = soup.find('time', class_='published')['datetime']
3120
        day = string_to_date(date_str, "%Y-%m-%d")
3121
        author = soup.find('a', rel='author').string
3122
        div_content = soup.find('div', class_="body entry-content")
3123
        imgs = div_content.find_all('img')
3124
        imgs = [i for i in imgs if i.get('src') is not None]
3125
        alt = imgs[0]['alt']
3126
        return {
3127
            'title': title,
3128
            'alt': alt,
3129
            'description': desc,
3130
            'author': author,
3131
            'day': day.day,
3132
            'month': day.month,
3133
            'year': day.year,
3134
            'img': [i['src'] for i in imgs],
3135
        }
3136
3137
3138
class GenericWordPressInkblot(GenericNavigableComic):
3139
    """Generic class to retrieve comics using WordPress with Inkblot."""
3140
    get_navi_link = get_link_rel_next
3141
3142
    @classmethod
3143
    def get_first_comic_link(cls):
3144
        """Get link to first comics."""
3145
        return get_soup_at_url(cls.url).find('a', class_='webcomic-link webcomic1-link first-webcomic-link first-webcomic1-link')
3146
3147
    @classmethod
3148
    def get_comic_info(cls, soup, link):
3149
        """Get information about a particular comics."""
3150
        title = soup.find('meta', property='og:title')['content']
3151
        imgs = soup.find('div', class_='webcomic-image').find_all('img')
3152
        date_str = soup.find('meta', property='article:published_time')['content'][:10]
3153
        day = string_to_date(date_str, "%Y-%m-%d")
3154
        return {
3155
            'title': title,
3156
            'day': day.day,
3157
            'month': day.month,
3158
            'year': day.year,
3159
            'img': [i['src'] for i in imgs],
3160
        }
3161
3162
3163
class EverythingsStupid(GenericWordPressInkblot):
3164
    """Class to retrieve Everything's stupid Comics."""
3165
    # Also on http://tapastic.com/series/EverythingsStupid
3166
    # Also on http://www.webtoons.com/en/challenge/everythings-stupid/list?title_no=14591
3167
    # Also on http://everythingsstupidcomics.tumblr.com
3168
    name = 'stupid'
3169
    long_name = "Everything's Stupid"
3170
    url = 'http://everythingsstupid.net'
3171
3172
3173
class TheIsmComics(GenericDeletedComic, GenericWordPressInkblot):
3174
    """Class to retrieve The Ism Comics."""
3175
    # Also on https://tapastic.com/series/TheIsm (?)
3176
    name = 'theism'
3177
    long_name = "The Ism"
3178
    url = 'http://www.theism-comics.com'
3179
3180
3181
class WoodenPlankStudios(GenericWordPressInkblot):
3182
    """Class to retrieve Wooden Plank Studios comics."""
3183
    name = 'woodenplank'
3184
    long_name = 'Wooden Plank Studios'
3185
    url = 'http://woodenplankstudios.com'
3186
3187
3188
class ElectricBunnyComic(GenericNavigableComic):
3189
    """Class to retrieve Electric Bunny Comics."""
3190
    # Also on http://electricbunnycomics.tumblr.com
3191
    name = 'bunny'
3192
    long_name = 'Electric Bunny Comic'
3193
    url = 'http://www.electricbunnycomics.com/View/Comic/153/Welcome+to+Hell'
3194
    get_url_from_link = join_cls_url_to_href
3195
3196
    @classmethod
3197
    def get_first_comic_link(cls):
3198
        """Get link to first comics."""
3199
        return get_soup_at_url(cls.url).find('img', alt='First').parent
3200
3201
    @classmethod
3202
    def get_navi_link(cls, last_soup, next_):
3203
        """Get link to next or previous comic."""
3204
        img = last_soup.find('img', alt='Next' if next_ else 'Back')
3205
        return img.parent if img else None
3206
3207
    @classmethod
3208
    def get_comic_info(cls, soup, link):
3209
        """Get information about a particular comics."""
3210
        title = soup.find('meta', property='og:title')['content']
3211
        imgs = soup.find_all('meta', property='og:image')
3212
        return {
3213
            'title': title,
3214
            'img': [i['content'] for i in imgs],
3215
        }
3216
3217
3218
class SheldonComics(GenericNavigableComic):
3219
    """Class to retrieve Sheldon comics."""
3220
    # Also on http://www.gocomics.com/sheldon
3221
    name = 'sheldon'
3222
    long_name = 'Sheldon Comics'
3223
    url = 'http://www.sheldoncomics.com'
3224
3225
    @classmethod
3226
    def get_first_comic_link(cls):
3227
        """Get link to first comics."""
3228
        return get_soup_at_url(cls.url).find("a", id="nav-first")
3229
3230
    @classmethod
3231
    def get_navi_link(cls, last_soup, next_):
3232
        """Get link to next or previous comic."""
3233
        for link in last_soup.find_all("a", id="nav-next" if next_ else "nav-prev"):
3234
            if link['href'] != 'http://www.sheldoncomics.com':
3235
                return link
3236
        return None
3237
3238
    @classmethod
3239
    def get_comic_info(cls, soup, link):
3240
        """Get information about a particular comics."""
3241
        imgs = soup.find("div", id="comic-foot").find_all("img")
3242
        assert all(i['alt'] == i['title'] for i in imgs)
3243
        assert len(imgs) == 1, imgs
3244
        title = imgs[0]['title']
3245
        return {
3246
            'title': title,
3247
            'img': [i['src'] for i in imgs],
3248
        }
3249
3250
3251
class ManVersusManatee(GenericNavigableComic):
3252
    """Class to retrieve Man Versus Manatee comics."""
3253
    url = 'http://manvsmanatee.com'
3254
    name = 'manvsmanatee'
3255
    long_name = 'Man Versus Manatee'
3256
    get_first_comic_link = get_a_comicnavbase_comicnavfirst
3257
    get_navi_link = get_a_comicnavbase_comicnavnext
3258
3259
    @classmethod
3260
    def get_comic_info(cls, soup, link):
3261
        """Get information about a particular comics."""
3262
        title = soup.find('h2', class_='post-title').string
3263
        imgs = soup.find('div', id='comic').find_all('img')
3264
        date_str = soup.find('span', class_='post-date').string
3265
        day = string_to_date(date_str, "%B %d, %Y")
3266
        return {
3267
            'img': [i['src'] for i in imgs],
3268
            'title': title,
3269
            'month': day.month,
3270
            'year': day.year,
3271
            'day': day.day,
3272
        }
3273
3274
3275
class TheMeerkatguy(GenericNavigableComic):
3276
    """Class to retrieve The Meerkatguy comics."""
3277
    long_name = 'The Meerkatguy'
3278
    url = 'http://www.themeerkatguy.com'
3279
    name = 'meerkatguy'
3280
    get_first_comic_link = get_a_comicnavbase_comicnavfirst
3281
    get_navi_link = get_a_comicnavbase_comicnavnext
3282
3283
    @classmethod
3284
    def get_comic_info(cls, soup, link):
3285
        """Get information about a particular comics."""
3286
        title = soup.find('title').string
3287
        imgs = soup.find_all('meta', property='og:image')
3288
        return {
3289
            'img': [i['content'] for i in imgs],
3290
            'title': title,
3291
        }
3292
3293
3294 View Code Duplication
class Ubertool(GenericNavigableComic):
3295
    """Class to retrieve Ubertool comics."""
3296
    # Also on https://ubertool.tumblr.com
3297
    # Also on https://tapastic.com/series/ubertool
3298
    name = 'ubertool'
3299
    long_name = 'Ubertool'
3300
    url = 'http://ubertoolcomic.com'
3301
    _categories = ('UBERTOOL', )
3302
    get_first_comic_link = get_a_comicnavbase_comicnavfirst
3303
    get_navi_link = get_a_comicnavbase_comicnavnext
3304
3305
    @classmethod
3306
    def get_comic_info(cls, soup, link):
3307
        """Get information about a particular comics."""
3308
        title = soup.find('h2', class_='post-title').string
3309
        date_str = soup.find('span', class_='post-date').string
3310
        day = string_to_date(date_str, "%B %d, %Y")
3311
        imgs = soup.find('div', id='comic').find_all('img')
3312
        return {
3313
            'img': [i['src'] for i in imgs],
3314
            'title': title,
3315
            'month': day.month,
3316
            'year': day.year,
3317
            'day': day.day,
3318
        }
3319
3320
3321
class EarthExplodes(GenericNavigableComic):
3322
    """Class to retrieve The Earth Explodes comics."""
3323 View Code Duplication
    name = 'earthexplodes'
3324
    long_name = 'The Earth Explodes'
3325
    url = 'http://www.earthexplodes.com'
3326
    get_url_from_link = join_cls_url_to_href
3327
    get_first_comic_link = simulate_first_link
3328
    first_url = 'http://www.earthexplodes.com/comics/000/'
3329
3330
    @classmethod
3331
    def get_navi_link(cls, last_soup, next_):
3332
        """Get link to next or previous comic."""
3333
        return last_soup.find('a', id='next' if next_ else 'prev')
3334
3335
    @classmethod
3336
    def get_comic_info(cls, soup, link):
3337
        """Get information about a particular comics."""
3338
        title = soup.find('title').string
3339
        imgs = soup.find('div', id='image').find_all('img')
3340
        alt = imgs[0].get('title', '')
3341
        return {
3342
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
3343
            'title': title,
3344
            'alt': alt,
3345
        }
3346
3347
3348
class PomComics(GenericNavigableComic):
3349
    """Class to retrieve PomComics."""
3350
    name = 'pom'
3351
    long_name = 'Pom Comics / Piece of Me'
3352
    url = 'http://www.pomcomic.com'
3353
    get_url_from_link = join_cls_url_to_href
3354
3355
    @classmethod
3356
    def get_first_comic_link(cls):
3357
        """Get link to first comics."""
3358
        return get_soup_at_url(cls.url).find('a', class_='btn-first')
3359
3360
    @classmethod
3361
    def get_navi_link(cls, last_soup, next_):
3362
        """Get link to next or previous comic."""
3363
        return last_soup.find('a', class_='btn-next' if next_ else 'btn-prev')
3364
3365
    @classmethod
3366
    def get_comic_info(cls, soup, link):
3367
        """Get information about a particular comics."""
3368
        title = soup.find('h1').string
3369
        desc = soup.find('meta', property='og:description')['content']
3370
        tags = soup.find('meta', attrs={'name': 'keywords'})['content']
3371
        imgs = soup.find('div', class_='comic').find_all('img')
3372
        return {
3373
            'title': title,
3374
            'desc': desc,
3375
            'tags': tags,
3376
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
3377
        }
3378
3379
3380
class CubeDrone(GenericComicNotWorking, GenericNavigableComic):  # Website has changed
3381
    """Class to retrieve Cube Drone comics."""
3382
    name = 'cubedrone'
3383
    long_name = 'Cube Drone'
3384
    url = 'http://cube-drone.com/comics'
3385
    get_url_from_link = join_cls_url_to_href
3386
3387
    @classmethod
3388
    def get_first_comic_link(cls):
3389
        """Get link to first comics."""
3390
        return get_soup_at_url(cls.url).find('span', class_='glyphicon glyphicon-backward').parent
3391
3392
    @classmethod
3393
    def get_navi_link(cls, last_soup, next_):
3394
        """Get link to next or previous comic."""
3395
        class_ = 'glyphicon glyphicon-chevron-' + ('right' if next_ else 'left')
3396
        return last_soup.find('span', class_=class_).parent
3397
3398
    @classmethod
3399
    def get_comic_info(cls, soup, link):
3400
        """Get information about a particular comics."""
3401
        title = soup.find('meta', attrs={'name': 'twitter:title'})['content']
3402
        url2 = soup.find('meta', attrs={'name': 'twitter:url'})['content']
3403
        # date_str = soup.find('h2', class_='comic_title').find('small').string
3404
        # day = string_to_date(date_str, "%B %d, %Y, %I:%M %p")
3405
        imgs = soup.find_all('img', class_='comic img-responsive')
3406
        title2 = imgs[0]['title']
3407
        alt = imgs[0]['alt']
3408
        return {
3409
            'url2': url2,
3410
            'title': title,
3411
            'title2': title2,
3412
            'alt': alt,
3413
            'img': [i['src'] for i in imgs],
3414
        }
3415
3416
3417
class MakeItStoopid(GenericDeletedComic, GenericNavigableComic):
3418
    """Class to retrieve Make It Stoopid Comics."""
3419
    name = 'stoopid'
3420
    long_name = 'Make it stoopid'
3421
    url = 'http://makeitstoopid.com/comic.php'
3422
3423
    @classmethod
3424
    def get_nav(cls, soup):
3425
        """Get the navigation elements from soup object."""
3426
        cnav = soup.find_all(class_='cnav')
3427
        nav1, nav2 = cnav[:5], cnav[5:]
3428
        assert nav1 == nav2
3429
        # begin, prev, archive, next_, end = nav1
3430
        return [None if i.get('href') is None else i for i in nav1]
3431
3432
    @classmethod
3433
    def get_first_comic_link(cls):
3434
        """Get link to first comics."""
3435
        return cls.get_nav(get_soup_at_url(cls.url))[0]
3436
3437
    @classmethod
3438
    def get_navi_link(cls, last_soup, next_):
3439
        """Get link to next or previous comic."""
3440
        return cls.get_nav(last_soup)[3 if next_ else 1]
3441
3442
    @classmethod
3443
    def get_comic_info(cls, soup, link):
3444
        """Get information about a particular comics."""
3445
        title = link['title']
3446
        imgs = soup.find_all('img', id='comicimg')
3447
        return {
3448
            'title': title,
3449
            'img': [i['src'] for i in imgs],
3450
        }
3451
3452
3453
class OffTheLeashDog(GenericNavigableComic):
3454
    """Class to retrieve Off The Leash Dog comics."""
3455
    # Also on http://rupertfawcettsdoggyblog.tumblr.com
3456
    # Also on http://www.rupertfawcettcartoons.com
3457
    name = 'offtheleash'
3458
    long_name = 'Off The Leash Dog'
3459
    url = 'http://offtheleashdogcartoons.com'
3460
    _categories = ('FAWCETT', )
3461
    get_navi_link = get_a_rel_next
3462
    get_first_comic_link = simulate_first_link
3463
    first_url = 'http://offtheleashdogcartoons.com/uncategorized/can-i-help-you/'
3464
3465
    @classmethod
3466
    def get_comic_info(cls, soup, link):
3467
        """Get information about a particular comics."""
3468
        title = soup.find("h1", class_="entry-title").string
3469
        imgs = soup.find('div', class_='entry-content').find_all('img')
3470
        return {
3471
            'title': title,
3472
            'img': [i['src'] for i in imgs],
3473
        }
3474
3475
3476 View Code Duplication
class MarketoonistComics(GenericNavigableComic):
3477
    """Class to retrieve Marketoonist Comics."""
3478
    name = 'marketoonist'
3479
    long_name = 'Marketoonist'
3480
    url = 'https://marketoonist.com/cartoons'
3481
    get_first_comic_link = simulate_first_link
3482
    get_navi_link = get_link_rel_next
3483
    first_url = 'https://marketoonist.com/2002/10/the-8-types-of-brand-managers-2.html'
3484
3485
    @classmethod
3486
    def get_comic_info(cls, soup, link):
3487
        """Get information about a particular comics."""
3488
        imgs = soup.find_all('meta', property='og:image')
3489
        date_str = soup.find('meta', property='article:published_time')['content'][:10]
3490
        day = string_to_date(date_str, "%Y-%m-%d")
3491
        title = soup.find('meta', property='og:title')['content']
3492
        return {
3493
            'img': [i['content'] for i in imgs],
3494
            'day': day.day,
3495
            'month': day.month,
3496
            'year': day.year,
3497
            'title': title,
3498
        }
3499
3500
3501
class ConsoliaComics(GenericNavigableComic):
3502
    """Class to retrieve Consolia comics."""
3503
    name = 'consolia'
3504
    long_name = 'consolia'
3505
    url = 'https://consolia-comic.com'
3506
    get_url_from_link = join_cls_url_to_href
3507
3508
    @classmethod
3509
    def get_first_comic_link(cls):
3510
        """Get link to first comics."""
3511
        return get_soup_at_url(cls.url).find('a', class_='first')
3512
3513
    @classmethod
3514
    def get_navi_link(cls, last_soup, next_):
3515
        """Get link to next or previous comic."""
3516
        return last_soup.find('a', class_='next' if next_ else 'prev')
3517
3518
    @classmethod
3519
    def get_comic_info(cls, soup, link):
3520
        """Get information about a particular comics."""
3521 View Code Duplication
        title = soup.find('meta', property='og:title')['content']
3522
        date_str = soup.find('time')["datetime"]
3523
        day = string_to_date(date_str, "%Y-%m-%d")
3524
        imgs = soup.find_all('meta', property='og:image')
3525
        return {
3526
            'title': title,
3527
            'img': [i['content'] for i in imgs],
3528
            'day': day.day,
3529
            'month': day.month,
3530
            'year': day.year,
3531
        }
3532
3533
3534
class GenericBlogspotComic(GenericNavigableComic):
3535
    """Generic class to retrieve comics from Blogspot."""
3536
    get_first_comic_link = simulate_first_link
3537
    first_url = NotImplemented
3538
    _categories = ('BLOGSPOT', )
3539
3540
    @classmethod
3541
    def get_navi_link(cls, last_soup, next_):
3542
        """Get link to next or previous comic."""
3543
        return last_soup.find('a', id='Blog1_blog-pager-newer-link' if next_ else 'Blog1_blog-pager-older-link')
3544
3545
3546
class TuMourrasMoinsBete(GenericBlogspotComic):
3547
    """Class to retrieve Tu Mourras Moins Bete comics."""
3548
    name = 'mourrasmoinsbete'
3549
    long_name = 'Tu Mourras Moins Bete'
3550
    url = 'http://tumourrasmoinsbete.blogspot.fr'
3551
    _categories = ('FRANCAIS', )
3552
    first_url = 'http://tumourrasmoinsbete.blogspot.fr/2008/06/essai.html'
3553
3554
    @classmethod
3555
    def get_comic_info(cls, soup, link):
3556
        """Get information about a particular comics."""
3557
        title = soup.find('title').string
3558
        imgs = soup.find('div', itemprop='description articleBody').find_all('img')
3559
        author = soup.find('span', itemprop='author').string
3560
        return {
3561
            'img': [i['src'] for i in imgs],
3562
            'author': author,
3563
            'title': title,
3564
        }
3565
3566
3567 View Code Duplication
class Octopuns(GenericBlogspotComic):
3568
    """Class to retrieve Octopuns comics."""
3569
    # Also on http://octopuns.tumblr.com
3570
    name = 'octopuns'
3571
    long_name = 'Octopuns'
3572
    url = 'http://www.octopuns.net'  # or http://octopuns.blogspot.fr/
3573
    first_url = 'http://octopuns.blogspot.com/2010/12/17122010-always-read-label.html'
3574
3575
    @classmethod
3576
    def get_comic_info(cls, soup, link):
3577
        """Get information about a particular comics."""
3578
        title = soup.find('h3', class_='post-title entry-title').string
3579
        date_str = soup.find('h2', class_='date-header').string
3580
        day = string_to_date(date_str, "%A, %B %d, %Y")
3581
        imgs = soup.find_all('link', rel='image_src')
3582
        return {
3583
            'img': [i['href'] for i in imgs],
3584
            'title': title,
3585
            'day': day.day,
3586
            'month': day.month,
3587
            'year': day.year,
3588
        }
3589
3590
3591
class GeekAndPoke(GenericNavigableComic):
3592
    """Class to retrieve Geek And Poke comics."""
3593
    name = 'geek'
3594
    long_name = 'Geek And Poke'
3595
    url = 'http://geek-and-poke.com'
3596
    get_url_from_link = join_cls_url_to_href
3597
    get_first_comic_link = simulate_first_link
3598
    first_url = 'http://geek-and-poke.com/geekandpoke/2006/8/27/a-new-place-for-a-not-so-old-blog.html'
3599
3600
    @classmethod
3601
    def get_navi_link(cls, last_soup, next_):
3602
        """Get link to next or previous comic."""
3603
        return last_soup.find('a', class_='prev-item' if next_ else 'next-item')
3604
3605
    @classmethod
3606
    def get_comic_info(cls, soup, link):
3607 View Code Duplication
        """Get information about a particular comics."""
3608
        title = soup.find('meta', property='og:title')['content']
3609
        desc = soup.find('meta', property='og:description')
3610
        desc_str = "" if desc is None else desc['content']
3611
        date_str = soup.find('time', class_='published')['datetime']
3612
        day = string_to_date(date_str, "%Y-%m-%d")
3613
        author = soup.find('a', rel='author').string
3614
        div_content = (soup.find('div', class_="body entry-content") or
3615
                       soup.find('div', class_="special-content"))
3616
        imgs = div_content.find_all('img')
3617
        imgs = [i for i in imgs if i.get('src') is not None]
3618
        assert all('title' not in i or i['alt'] == i['title'] for i in imgs)
3619
        alt = imgs[0].get('alt', "") if imgs else []
3620
        return {
3621
            'title': title,
3622
            'alt': alt,
3623
            'description': desc_str,
3624
            'author': author,
3625
            'day': day.day,
3626
            'month': day.month,
3627
            'year': day.year,
3628
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
3629
        }
3630
3631
3632
class GloryOwlComix(GenericBlogspotComic):
3633
    """Class to retrieve Glory Owl comics."""
3634
    name = 'gloryowl'
3635
    long_name = 'Glory Owl'
3636
    url = 'http://gloryowlcomix.blogspot.fr'
3637
    _categories = ('NSFW', 'FRANCAIS')
3638
    first_url = 'http://gloryowlcomix.blogspot.fr/2013/02/1_7.html'
3639
3640
    @classmethod
3641
    def get_comic_info(cls, soup, link):
3642
        """Get information about a particular comics."""
3643
        title = soup.find('title').string
3644
        imgs = soup.find_all('link', rel='image_src')
3645
        author = soup.find('a', rel='author').string
3646
        return {
3647
            'img': [i['href'] for i in imgs],
3648
            'author': author,
3649
            'title': title,
3650
        }
3651
3652
3653
class GenericSquareSpace(GenericNavigableComic):
3654
    """Generic class to retrieve comics using SquareSpace."""
3655
    _categories = ('SQUARESPACE', )
3656
    get_url_from_link = join_cls_url_to_href
3657
    get_first_comic_link = simulate_first_link
3658
3659
    @classmethod
3660
    def get_navi_link(cls, last_soup, next_):
3661
        """Get link to next or previous comic."""
3662
        return last_soup.find('a', id='prevLink' if next_ else 'nextLink')
3663
3664
    @classmethod
3665
    def get_images(cls, soup):
3666
        """Get image URLs for a comic."""
3667
        raise NotImplementedError
3668
3669
    @classmethod
3670
    def get_comic_info(cls, soup, link):
3671
        """Get information about a particular comics."""
3672
        title = soup.find('meta', property='og:title')['content']
3673
        desc = soup.find('meta', property='og:description')['content']
3674
        date_str = soup.find('time', itemprop='datePublished')["datetime"]
3675
        day = string_to_date(date_str, "%Y-%m-%d")
3676
        author = soup.find('a', rel='author').string
3677
        imgs = soup.find_all('meta', property='og:image')
3678
        return {
3679
            'title': title,
3680
            'img': cls.get_images(soup),
3681
            'month': day.month,
3682
            'year': day.year,
3683
            'day': day.day,
3684
            'author': author,
3685
            'description': desc,
3686
        }
3687
3688
3689
class AtRandomComics(GenericSquareSpace):
3690
    """Class to retrieve At Random Comics."""
3691
    name = 'atrandom'
3692
    long_name = 'At Random Comics'
3693
    url = 'http://www.atrandomcomics.com'
3694
    first_url = 'http://www.atrandomcomics.com/at-random-comics-home/2015/5/5/can-of-worms'
3695
3696
    @classmethod
3697
    def get_images(cls, soup):
3698
        """Get image URLs for a comic."""
3699
        imgs = soup.find_all('meta', property='og:image')
3700
        return [i['content'] for i in imgs]
3701
3702
3703
class NothingSuspicious(GenericSquareSpace):
3704
    """Class to retrieve Nothing Suspicious comics."""
3705
    name = 'nothingsuspicious'
3706
    long_name = 'Nothing Suspicious'
3707
    url = 'https://nothingsuspicio.us'
3708
    first_url = 'https://nothingsuspicio.us/?offset=1483592400908'
3709
3710
    @classmethod
3711
    def get_images(cls, soup):
3712
        """Get image URLs for a comic."""
3713
        imgs = soup.find('div', class_='content-wrapper').find('img')
3714
        return [i['src'] for i in [imgs]]
3715
3716
3717
class DeathBulge(GenericComic):
3718
    """Class to retrieve the DeathBulge comics."""
3719
    name = 'deathbulge'
3720
    long_name = 'Death Bulge'
3721
    url = 'http://www.deathbulge.com'
3722
3723
    @classmethod
3724
    def get_next_comic(cls, last_comic):
3725
        """Generator to get the next comic. Implementation of GenericComic's abstract method."""
3726
        json_url = urljoin_wrapper(cls.url, 'api/comics/1')
3727
        json = load_json_at_url(json_url)
3728
        pagination = json['pagination_links']
3729
        first_num = last_comic['num'] if last_comic else pagination['first']
3730
        last_num = pagination['last']
3731
        for num in range(first_num + 1, last_num):
3732
            json_url = urljoin_wrapper(cls.url, 'api/comics/%d' % num)
3733
            json = load_json_at_url(json_url)
3734
            pagination = json['pagination_links']
3735
            comic_json = json['comic']
3736
            date_str = comic_json['timestamp'][:10]
3737
            day = string_to_date(date_str, "%Y-%m-%d")
3738
            comic_id = comic_json['id']  # not exactly 'num' o_O
3739
            yield {
3740
                'json_url': json_url,
3741
                'num': comic_id,
3742
                'url': urljoin_wrapper(cls.url, 'comics/%d' % num),
3743
                'alt': comic_json['alt_text'],
3744
                'title': comic_json['title'],
3745
                'img': [urljoin_wrapper(cls.url, comic_json['comic'])],
3746
                'month': day.month,
3747
                'year': day.year,
3748
                'day': day.day,
3749
            }
3750
3751
3752
class GenericTumblrV1(GenericComic):
3753
    """Generic class to retrieve comics from Tumblr using the V1 API."""
3754
    _categories = ('TUMBLR', )
3755
3756
    @classmethod
3757
    def get_next_comic(cls, last_comic):
3758
        """Generic implementation of get_next_comic for Tumblr comics."""
3759
        for p in cls.get_posts(last_comic):
3760
            comic = cls.get_comic_info(p)
3761
            if comic is not None:
3762
                yield comic
3763
3764
    @classmethod
3765
    def check_url(cls, url):
3766
        if not url.startswith(cls.url):
3767
            print("url '%s' does not start with '%s'" % (url, cls.url))
3768
        return url
3769
3770
    @classmethod
3771
    def get_url_from_post(cls, post):
3772
        return cls.check_url(post['url'])
3773
3774
    @classmethod
3775
    def get_api_url(cls):
3776
        return urljoin_wrapper(cls.url, '/api/read/')
3777
3778
    @classmethod
3779
    def get_api_url_for_id(cls, tumblr_id):
3780
        return cls.get_api_url() + '?id=%d' % (tumblr_id)
3781
3782
    @classmethod
3783
    def get_comic_info(cls, post):
3784
        """Get information about a particular comics."""
3785
        type_ = post['type']
3786
        if type_ != 'photo':
3787
            return None
3788
        tumblr_id = int(post['id'])
3789
        api_url = cls.get_api_url_for_id(tumblr_id)
3790
        day = datetime.datetime.fromtimestamp(int(post['unix-timestamp'])).date()
3791
        caption = post.find('photo-caption')
3792
        title = caption.string if caption else ""
3793
        tags = ' '.join(t.string for t in post.find_all('tag'))
3794
        # Photos may appear in 'photo' tags and/or straight in the post
3795
        photo_tags = post.find_all('photo')
3796
        if not photo_tags:
3797
            photo_tags = [post]
3798
        # Images are in multiple resolutions - taking the first one
3799
        imgs = [photo.find('photo-url') for photo in photo_tags]
3800
        return {
3801
            'url': cls.get_url_from_post(post),
3802
            'url2': post['url-with-slug'],
3803
            'day': day.day,
3804
            'month': day.month,
3805
            'year': day.year,
3806
            'title': title,
3807
            'tags': tags,
3808
            'img': [i.string for i in imgs],
3809
            'tumblr-id': tumblr_id,
3810
            'api_url': api_url,
3811
        }
3812
3813
    @classmethod
3814
    def get_posts(cls, last_comic, nb_post_per_call=10):
3815
        """Get posts using API. nb_post_per_call is max 50.
3816
3817
        Posts are retrieved from newer to older as per the tumblr v1 api
3818
        but are returned in chronological order."""
3819
        waiting_for_id = last_comic['tumblr-id'] if last_comic else None
3820
        posts_acc = []
3821
        if last_comic is not None:
3822
            # cls.check_url(last_comic['url'])
3823
            cls.check_url(last_comic['api_url'])
3824
            # Sometimes, tumblr posts are deleted. When previous post is deleted, we
3825
            # might end up spending a lot of time looking for something that
3826
            # doesn't exist. Failing early and clearly might be a better option.
3827
            last_api_url = cls.get_api_url_for_id(waiting_for_id)
3828
            try:
3829
                get_soup_at_url(last_api_url)
3830
            except urllib.error.HTTPError:
3831
                try:
3832
                    get_soup_at_url(cls.url)
3833
                except urllib.error.HTTPError:
3834
                    print("Did not find previous post nor main url %s" % cls.url)
3835
                else:
3836
                    print("Did not find previous post %s : it might have been deleted" % last_api_url)
3837
                return reversed(posts_acc)
3838
        api_url = cls.get_api_url()
3839
        posts = get_soup_at_url(api_url).find('posts')
3840
        start, total = int(posts['start']), int(posts['total'])
3841
        assert start == 0
3842
        for starting_num in range(0, total, nb_post_per_call):
3843
            api_url2 = api_url + '?start=%d&num=%d' % (starting_num, nb_post_per_call)
3844
            posts2 = get_soup_at_url(api_url2).find('posts')
3845
            start2, total2 = int(posts2['start']), int(posts2['total'])
3846
            assert starting_num == start2, "%d != %d" % (starting_num, start2)
3847
            # This may happen and should be handled in the future
3848
            assert total == total2, "%d != %d" % (total, total2)
3849
            for p in posts2.find_all('post'):
3850
                tumblr_id = int(p['id'])
3851
                if waiting_for_id and waiting_for_id == tumblr_id:
3852
                    return reversed(posts_acc)
3853
                posts_acc.append(p)
3854
        if waiting_for_id is None:
3855
            return reversed(posts_acc)
3856
        print("Did not find %s : there might be a problem" % waiting_for_id)
3857
        return []
3858
3859
3860
class SaturdayMorningBreakfastCerealTumblr(GenericTumblrV1):
3861
    """Class to retrieve Saturday Morning Breakfast Cereal comics."""
3862
    # Also on http://www.gocomics.com/saturday-morning-breakfast-cereal
3863
    # Also on http://www.smbc-comics.com
3864
    name = 'smbc-tumblr'
3865
    long_name = 'Saturday Morning Breakfast Cereal (from Tumblr)'
3866
    url = 'http://smbc-comics.tumblr.com'
3867
    _categories = ('SMBC', )
3868
3869
3870
class AHammADay(GenericTumblrV1):
3871
    """Class to retrieve class A Hamm A Day comics."""
3872
    name = 'hamm'
3873
    long_name = 'A Hamm A Day'
3874
    url = 'http://www.ahammaday.com'
3875
3876
3877
class IrwinCardozo(GenericTumblrV1):
3878
    """Class to retrieve Irwin Cardozo Comics."""
3879
    name = 'irwinc'
3880
    long_name = 'Irwin Cardozo'
3881
    url = 'http://irwincardozocomics.tumblr.com'
3882
3883
3884
class AccordingToDevin(GenericTumblrV1):
3885
    """Class to retrieve According To Devin comics."""
3886
    name = 'devin'
3887
    long_name = 'According To Devin'
3888
    url = 'http://accordingtodevin.tumblr.com'
3889
3890
3891
class ItsTheTieTumblr(GenericTumblrV1):
3892
    """Class to retrieve It's the tie comics."""
3893
    # Also on http://itsthetie.com
3894
    # Also on https://tapastic.com/series/itsthetie
3895
    name = 'tie-tumblr'
3896
    long_name = "It's the tie (from Tumblr)"
3897
    url = "http://itsthetie.tumblr.com"
3898
    _categories = ('TIE', )
3899
3900
3901
class OctopunsTumblr(GenericTumblrV1):
3902
    """Class to retrieve Octopuns comics."""
3903
    # Also on http://www.octopuns.net
3904
    name = 'octopuns-tumblr'
3905
    long_name = 'Octopuns (from Tumblr)'
3906
    url = 'http://octopuns.tumblr.com'
3907
3908
3909
class PicturesInBoxesTumblr(GenericTumblrV1):
3910
    """Class to retrieve Pictures In Boxes comics."""
3911
    # Also on http://www.picturesinboxes.com
3912
    name = 'picturesinboxes-tumblr'
3913
    long_name = 'Pictures in Boxes (from Tumblr)'
3914
    url = 'https://picturesinboxescomic.tumblr.com'
3915
3916
3917
class TubeyToonsTumblr(GenericTumblrV1):
3918
    """Class to retrieve TubeyToons comics."""
3919
    # Also on http://tapastic.com/series/Tubey-Toons
3920
    # Also on http://tubeytoons.com
3921
    name = 'tubeytoons-tumblr'
3922
    long_name = 'Tubey Toons (from Tumblr)'
3923
    url = 'https://tubeytoons.tumblr.com'
3924
    _categories = ('TUNEYTOONS', )
3925
3926
3927
class UnearthedComicsTumblr(GenericTumblrV1):
3928
    """Class to retrieve Unearthed comics."""
3929
    # Also on http://tapastic.com/series/UnearthedComics
3930
    # Also on http://unearthedcomics.com
3931
    name = 'unearthed-tumblr'
3932
    long_name = 'Unearthed Comics (from Tumblr)'
3933
    url = 'https://unearthedcomics.tumblr.com'
3934
    _categories = ('UNEARTHED', )
3935
3936
3937
class PieComic(GenericTumblrV1):
3938
    """Class to retrieve Pie Comic comics."""
3939
    name = 'pie'
3940
    long_name = 'Pie Comic'
3941
    url = "http://piecomic.tumblr.com"
3942
3943
3944
class MrEthanDiamond(GenericTumblrV1):
3945
    """Class to retrieve Mr Ethan Diamond comics."""
3946
    name = 'diamond'
3947
    long_name = 'Mr Ethan Diamond'
3948
    url = 'http://mrethandiamond.tumblr.com'
3949
3950
3951
class Flocci(GenericTumblrV1):
3952
    """Class to retrieve floccinaucinihilipilification comics."""
3953
    name = 'flocci'
3954
    long_name = 'floccinaucinihilipilification'
3955
    url = "http://floccinaucinihilipilificationa.tumblr.com"
3956
3957
3958
class UpAndOut(GenericTumblrV1):
3959
    """Class to retrieve Up & Out comics."""
3960
    # Also on http://tapastic.com/series/UP-and-OUT
3961
    name = 'upandout'
3962
    long_name = 'Up And Out (from Tumblr)'
3963
    url = 'http://upandoutcomic.tumblr.com'
3964
3965
3966
class Pundemonium(GenericTumblrV1):
3967
    """Class to retrieve Pundemonium comics."""
3968
    name = 'pundemonium'
3969
    long_name = 'Pundemonium'
3970
    url = 'http://monstika.tumblr.com'
3971
3972
3973
class PoorlyDrawnLinesTumblr(GenericTumblrV1):
3974
    """Class to retrieve Poorly Drawn Lines comics."""
3975
    # Also on http://poorlydrawnlines.com
3976
    name = 'poorlydrawn-tumblr'
3977
    long_name = 'Poorly Drawn Lines (from Tumblr)'
3978
    url = 'http://pdlcomics.tumblr.com'
3979
    _categories = ('POORLYDRAWN', )
3980
3981
3982
class PearShapedComics(GenericTumblrV1):
3983
    """Class to retrieve Pear Shaped Comics."""
3984
    name = 'pearshaped'
3985
    long_name = 'Pear-Shaped Comics'
3986
    url = 'http://pearshapedcomics.com'
3987
3988
3989
class PondScumComics(GenericTumblrV1):
3990
    """Class to retrieve Pond Scum Comics."""
3991
    name = 'pond'
3992
    long_name = 'Pond Scum'
3993
    url = 'http://pondscumcomic.tumblr.com'
3994
3995
3996
class MercworksTumblr(GenericTumblrV1):
3997
    """Class to retrieve Mercworks comics."""
3998
    # Also on http://mercworks.net
3999
    name = 'mercworks-tumblr'
4000
    long_name = 'Mercworks (from Tumblr)'
4001
    url = 'http://mercworks.tumblr.com'
4002
4003
4004
class OwlTurdTumblr(GenericTumblrV1):
4005
    """Class to retrieve Owl Turd comics."""
4006
    # Also on http://tapastic.com/series/Owl-Turd-Comix
4007
    name = 'owlturd-tumblr'
4008
    long_name = 'Owl Turd (from Tumblr)'
4009
    url = 'http://owlturd.com'
4010
    _categories = ('OWLTURD', )
4011
4012
4013
class VectorBelly(GenericTumblrV1):
4014
    """Class to retrieve Vector Belly comics."""
4015
    # Also on http://vectorbelly.com
4016
    name = 'vector'
4017
    long_name = 'Vector Belly'
4018
    url = 'http://vectorbelly.tumblr.com'
4019
4020
4021
class GoneIntoRapture(GenericTumblrV1):
4022
    """Class to retrieve Gone Into Rapture comics."""
4023
    # Also on http://goneintorapture.tumblr.com
4024
    # Also on http://tapastic.com/series/Goneintorapture
4025
    name = 'rapture'
4026
    long_name = 'Gone Into Rapture'
4027
    url = 'http://goneintorapture.com'
4028
4029
4030
class TheOatmealTumblr(GenericTumblrV1):
4031
    """Class to retrieve The Oatmeal comics."""
4032
    # Also on http://theoatmeal.com
4033
    name = 'oatmeal-tumblr'
4034
    long_name = 'The Oatmeal (from Tumblr)'
4035
    url = 'http://oatmeal.tumblr.com'
4036
4037
4038
class HeckIfIKnowComicsTumblr(GenericTumblrV1):
4039
    """Class to retrieve Heck If I Know Comics."""
4040
    # Also on http://tapastic.com/series/Regular
4041
    name = 'heck-tumblr'
4042
    long_name = 'Heck if I Know comics (from Tumblr)'
4043
    url = 'http://heckifiknowcomics.com'
4044
4045
4046
class MyJetPack(GenericTumblrV1):
4047
    """Class to retrieve My Jet Pack comics."""
4048
    name = 'jetpack'
4049
    long_name = 'My Jet Pack'
4050
    url = 'http://myjetpack.tumblr.com'
4051
4052
4053
class CheerUpEmoKidTumblr(GenericTumblrV1):
4054
    """Class to retrieve CheerUpEmoKid comics."""
4055
    # Also on http://www.cheerupemokid.com
4056
    # Also on http://tapastic.com/series/CUEK
4057
    name = 'cuek-tumblr'
4058
    long_name = 'Cheer Up Emo Kid (from Tumblr)'
4059
    url = 'https://enzocomics.tumblr.com'
4060
4061
4062
class ForLackOfABetterComic(GenericTumblrV1):
4063
    """Class to retrieve For Lack Of A Better Comics."""
4064
    # Also on http://forlackofabettercomic.com
4065
    name = 'lack'
4066
    long_name = 'For Lack Of A Better Comic'
4067
    url = 'http://forlackofabettercomic.tumblr.com'
4068
4069
4070
class ZenPencilsTumblr(GenericTumblrV1):
4071
    """Class to retrieve ZenPencils comics."""
4072
    # Also on http://zenpencils.com
4073
    # Also on http://www.gocomics.com/zen-pencils
4074
    name = 'zenpencils-tumblr'
4075
    long_name = 'Zen Pencils (from Tumblr)'
4076
    url = 'http://zenpencils.tumblr.com'
4077
    _categories = ('ZENPENCILS', )
4078
4079
4080
class ThreeWordPhraseTumblr(GenericTumblrV1):
4081
    """Class to retrieve Three Word Phrase comics."""
4082
    # Also on http://threewordphrase.com
4083
    name = 'threeword-tumblr'
4084
    long_name = 'Three Word Phrase (from Tumblr)'
4085
    url = 'http://threewordphrase.tumblr.com'
4086
4087
4088
class TimeTrabbleTumblr(GenericTumblrV1):
4089
    """Class to retrieve Time Trabble comics."""
4090
    # Also on http://timetrabble.com
4091
    name = 'timetrabble-tumblr'
4092
    long_name = 'Time Trabble (from Tumblr)'
4093
    url = 'http://timetrabble.tumblr.com'
4094
4095
4096
class SafelyEndangeredTumblr(GenericTumblrV1):
4097
    """Class to retrieve Safely Endangered comics."""
4098
    # Also on http://www.safelyendangered.com
4099
    name = 'endangered-tumblr'
4100
    long_name = 'Safely Endangered (from Tumblr)'
4101
    url = 'http://tumblr.safelyendangered.com'
4102
4103
4104
class MouseBearComedyTumblr(GenericTumblrV1):
4105
    """Class to retrieve Mouse Bear Comedy comics."""
4106
    # Also on http://www.mousebearcomedy.com
4107
    name = 'mousebear-tumblr'
4108
    long_name = 'Mouse Bear Comedy (from Tumblr)'
4109
    url = 'http://mousebearcomedy.tumblr.com'
4110
4111
4112
class BouletCorpTumblr(GenericTumblrV1):
4113
    """Class to retrieve BouletCorp comics."""
4114
    # Also on http://www.bouletcorp.com
4115
    name = 'boulet-tumblr'
4116
    long_name = 'Boulet Corp (from Tumblr)'
4117
    url = 'https://bouletcorp.tumblr.com'
4118
    _categories = ('BOULET', )
4119
4120
4121
class TheAwkwardYetiTumblr(GenericTumblrV1):
4122
    """Class to retrieve The Awkward Yeti comics."""
4123
    # Also on http://www.gocomics.com/the-awkward-yeti
4124
    # Also on http://theawkwardyeti.com
4125
    # Also on https://tapastic.com/series/TheAwkwardYeti
4126
    name = 'yeti-tumblr'
4127
    long_name = 'The Awkward Yeti (from Tumblr)'
4128
    url = 'http://larstheyeti.tumblr.com'
4129
    _categories = ('YETI', )
4130
4131
4132
class NellucNhoj(GenericTumblrV1):
4133
    """Class to retrieve NellucNhoj comics."""
4134
    name = 'nhoj'
4135
    long_name = 'Nelluc Nhoj'
4136
    url = 'http://nellucnhoj.com'
4137
4138
4139
class DownTheUpwardSpiralTumblr(GenericTumblrV1):
4140
    """Class to retrieve Down The Upward Spiral comics."""
4141
    # Also on http://www.downtheupwardspiral.com
4142
    # Also on https://tapastic.com/series/Down-the-Upward-Spiral
4143
    name = 'spiral-tumblr'
4144
    long_name = 'Down the Upward Spiral (from Tumblr)'
4145
    url = 'http://downtheupwardspiral.tumblr.com'
4146
4147
4148
class AsPerUsualTumblr(GenericTumblrV1):
4149
    """Class to retrieve As Per Usual comics."""
4150
    # Also on https://tapastic.com/series/AsPerUsual
4151
    name = 'usual-tumblr'
4152
    long_name = 'As Per Usual (from Tumblr)'
4153
    url = 'http://as-per-usual.tumblr.com'
4154
    categories = ('DAMILEE', )
4155
4156
4157
class HotComicsForCoolPeopleTumblr(GenericTumblrV1):
4158
    """Class to retrieve Hot Comics For Cool People."""
4159
    # Also on https://tapastic.com/series/Hot-Comics-For-Cool-People
4160
    # Also on http://hotcomics.biz (links to tumblr)
4161
    # Also on http://hcfcp.com (links to tumblr)
4162
    name = 'hotcomics-tumblr'
4163
    long_name = 'Hot Comics For Cool People (from Tumblr)'
4164
    url = 'http://hotcomicsforcoolpeople.tumblr.com'
4165
    categories = ('DAMILEE', )
4166
4167
4168
class OneOneOneOneComicTumblr(GenericTumblrV1):
4169
    """Class to retrieve 1111 Comics."""
4170
    # Also on http://www.1111comics.me
4171
    # Also on https://tapastic.com/series/1111-Comics
4172
    name = '1111-tumblr'
4173
    long_name = '1111 Comics (from Tumblr)'
4174
    url = 'http://comics1111.tumblr.com'
4175
    _categories = ('ONEONEONEONE', )
4176
4177
4178
class JhallComicsTumblr(GenericTumblrV1):
4179
    """Class to retrieve Jhall Comics."""
4180
    # Also on http://jhallcomics.com
4181
    name = 'jhall-tumblr'
4182
    long_name = 'Jhall Comics (from Tumblr)'
4183
    url = 'http://jhallcomics.tumblr.com'
4184
4185
4186
class BerkeleyMewsTumblr(GenericTumblrV1):
4187
    """Class to retrieve Berkeley Mews comics."""
4188
    # Also on http://www.gocomics.com/berkeley-mews
4189
    # Also on http://www.berkeleymews.com
4190
    name = 'berkeley-tumblr'
4191
    long_name = 'Berkeley Mews (from Tumblr)'
4192
    url = 'http://mews.tumblr.com'
4193
    _categories = ('BERKELEY', )
4194
4195
4196
class JoanCornellaTumblr(GenericTumblrV1):
4197
    """Class to retrieve Joan Cornella comics."""
4198
    # Also on http://joancornella.net
4199
    name = 'cornella-tumblr'
4200
    long_name = 'Joan Cornella (from Tumblr)'
4201
    url = 'http://cornellajoan.tumblr.com'
4202
4203
4204
class RespawnComicTumblr(GenericTumblrV1):
4205
    """Class to retrieve Respawn Comic."""
4206
    # Also on http://respawncomic.com
4207
    name = 'respawn-tumblr'
4208
    long_name = 'Respawn Comic (from Tumblr)'
4209
    url = 'https://respawncomic.tumblr.com'
4210
4211
4212
class ChrisHallbeckTumblr(GenericTumblrV1):
4213
    """Class to retrieve Chris Hallbeck comics."""
4214
    # Also on https://tapastic.com/ChrisHallbeck
4215
    # Also on http://maximumble.com
4216
    # Also on http://minimumble.com
4217
    # Also on http://thebookofbiff.com
4218
    name = 'hallbeck-tumblr'
4219
    long_name = 'Chris Hallback (from Tumblr)'
4220
    url = 'https://chrishallbeck.tumblr.com'
4221
    _categories = ('HALLBACK', )
4222
4223
4224
class ComicNuggets(GenericTumblrV1):
4225
    """Class to retrieve Comic Nuggets."""
4226
    name = 'nuggets'
4227
    long_name = 'Comic Nuggets'
4228
    url = 'http://comicnuggets.com'
4229
4230
4231
class PigeonGazetteTumblr(GenericTumblrV1):
4232
    """Class to retrieve The Pigeon Gazette comics."""
4233
    # Also on https://tapastic.com/series/The-Pigeon-Gazette
4234
    name = 'pigeon-tumblr'
4235
    long_name = 'The Pigeon Gazette (from Tumblr)'
4236
    url = 'http://thepigeongazette.tumblr.com'
4237
4238
4239
class CancerOwl(GenericTumblrV1):
4240
    """Class to retrieve Cancer Owl comics."""
4241
    # Also on http://cancerowl.com
4242
    name = 'cancerowl-tumblr'
4243
    long_name = 'Cancer Owl (from Tumblr)'
4244
    url = 'http://cancerowl.tumblr.com'
4245
4246
4247
class FowlLanguageTumblr(GenericTumblrV1):
4248
    """Class to retrieve Fowl Language comics."""
4249
    # Also on http://www.fowllanguagecomics.com
4250
    # Also on http://tapastic.com/series/Fowl-Language-Comics
4251
    # Also on http://www.gocomics.com/fowl-language
4252
    name = 'fowllanguage-tumblr'
4253
    long_name = 'Fowl Language Comics (from Tumblr)'
4254
    url = 'http://fowllanguagecomics.tumblr.com'
4255
    _categories = ('FOWLLANGUAGE', )
4256
4257
4258
class TheOdd1sOutTumblr(GenericTumblrV1):
4259
    """Class to retrieve The Odd 1s Out comics."""
4260
    # Also on http://theodd1sout.com
4261
    # Also on https://tapastic.com/series/Theodd1sout
4262
    name = 'theodd-tumblr'
4263
    long_name = 'The Odd 1s Out (from Tumblr)'
4264
    url = 'http://theodd1sout.tumblr.com'
4265
4266
4267
class TheUnderfoldTumblr(GenericTumblrV1):
4268
    """Class to retrieve The Underfold comics."""
4269
    # Also on http://theunderfold.com
4270
    name = 'underfold-tumblr'
4271
    long_name = 'The Underfold (from Tumblr)'
4272
    url = 'http://theunderfold.tumblr.com'
4273
4274
4275
class LolNeinTumblr(GenericTumblrV1):
4276
    """Class to retrieve Lol Nein comics."""
4277
    # Also on http://lolnein.com
4278
    name = 'lolnein-tumblr'
4279
    long_name = 'Lol Nein (from Tumblr)'
4280
    url = 'http://lolneincom.tumblr.com'
4281
4282
4283
class FatAwesomeComicsTumblr(GenericTumblrV1):
4284
    """Class to retrieve Fat Awesome Comics."""
4285
    # Also on http://fatawesome.com/comics
4286
    name = 'fatawesome-tumblr'
4287
    long_name = 'Fat Awesome (from Tumblr)'
4288
    url = 'http://fatawesomecomedy.tumblr.com'
4289
4290
4291
class TheWorldIsFlatTumblr(GenericTumblrV1):
4292
    """Class to retrieve The World Is Flat Comics."""
4293
    # Also on https://tapastic.com/series/The-World-is-Flat
4294
    name = 'flatworld-tumblr'
4295
    long_name = 'The World Is Flat (from Tumblr)'
4296
    url = 'http://theworldisflatcomics.com'
4297
4298
4299
class DorrisMc(GenericTumblrV1):
4300
    """Class to retrieve Dorris Mc Comics"""
4301
    # Also on http://www.gocomics.com/dorris-mccomics
4302
    name = 'dorrismc'
4303
    long_name = 'Dorris Mc'
4304
    url = 'http://dorrismccomics.com'
4305
4306
4307
class LeleozTumblr(GenericDeletedComic, GenericTumblrV1):
4308
    """Class to retrieve Leleoz comics."""
4309
    # Also on https://tapastic.com/series/Leleoz
4310
    name = 'leleoz-tumblr'
4311
    long_name = 'Leleoz (from Tumblr)'
4312
    url = 'http://leleozcomics.tumblr.com'
4313
4314
4315
class MoonBeardTumblr(GenericTumblrV1):
4316
    """Class to retrieve MoonBeard comics."""
4317
    # Also on http://moonbeard.com
4318
    # Also on http://www.webtoons.com/en/comedy/moon-beard/list?title_no=471
4319
    name = 'moonbeard-tumblr'
4320
    long_name = 'Moon Beard (from Tumblr)'
4321
    url = 'http://squireseses.tumblr.com'
4322
    _categories = ('MOONBEARD', )
4323
4324
4325
class AComik(GenericTumblrV1):
4326
    """Class to retrieve A Comik"""
4327
    name = 'comik'
4328
    long_name = 'A Comik'
4329
    url = 'http://acomik.com'
4330
4331
4332
class ClassicRandy(GenericTumblrV1):
4333
    """Class to retrieve Classic Randy comics."""
4334
    name = 'randy'
4335
    long_name = 'Classic Randy'
4336
    url = 'http://classicrandy.tumblr.com'
4337
4338
4339
class DagssonTumblr(GenericTumblrV1):
4340
    """Class to retrieve Dagsson comics."""
4341
    # Also on http://www.dagsson.com
4342
    name = 'dagsson-tumblr'
4343
    long_name = 'Dagsson Hugleikur (from Tumblr)'
4344
    url = 'https://hugleikurdagsson.tumblr.com'
4345
4346
4347
class LinsEditionsTumblr(GenericTumblrV1):
4348
    """Class to retrieve L.I.N.S. Editions comics."""
4349
    # Also on https://linsedition.com
4350
    # Now on http://warandpeas.tumblr.com
4351
    name = 'lins-tumblr'
4352
    long_name = 'L.I.N.S. Editions (from Tumblr)'
4353
    url = 'https://linscomics.tumblr.com'
4354
    _categories = ('LINS', )
4355
4356
4357
class WarAndPeasTumblr(GenericTumblrV1):
4358
    """Class to retrieve War And Peas comics."""
4359
    # Was on https://linscomics.tumblr.com
4360
    name = 'warandpeas-tumblr'
4361
    long_name = 'War And Peas (from Tumblr)'
4362
    url = 'http://warandpeas.tumblr.com'
4363
    _categories = ('WARANDPEAS', )
4364
4365
4366
class OrigamiHotDish(GenericTumblrV1):
4367
    """Class to retrieve Origami Hot Dish comics."""
4368
    name = 'origamihotdish'
4369
    long_name = 'Origami Hot Dish'
4370
    url = 'http://origamihotdish.com'
4371
4372
4373
class HitAndMissComicsTumblr(GenericTumblrV1):
4374
    """Class to retrieve Hit and Miss Comics."""
4375
    name = 'hitandmiss'
4376
    long_name = 'Hit and Miss Comics'
4377
    url = 'https://hitandmisscomics.tumblr.com'
4378
4379
4380
class HMBlanc(GenericTumblrV1):
4381
    """Class to retrieve HM Blanc comics."""
4382
    name = 'hmblanc'
4383
    long_name = 'HM Blanc'
4384
    url = 'http://hmblanc.tumblr.com'
4385
4386
4387
class TalesOfAbsurdityTumblr(GenericTumblrV1):
4388
    """Class to retrieve Tales Of Absurdity comics."""
4389
    # Also on http://talesofabsurdity.com
4390
    # Also on http://tapastic.com/series/Tales-Of-Absurdity
4391
    name = 'absurdity-tumblr'
4392
    long_name = 'Tales of Absurdity (from Tumblr)'
4393
    url = 'http://talesofabsurdity.tumblr.com'
4394
    _categories = ('ABSURDITY', )
4395
4396
4397
class RobbieAndBobby(GenericTumblrV1):
4398
    """Class to retrieve Robbie And Bobby comics."""
4399
    # Also on http://robbieandbobby.com
4400
    name = 'robbie-tumblr'
4401
    long_name = 'Robbie And Bobby (from Tumblr)'
4402
    url = 'http://robbieandbobby.tumblr.com'
4403
4404
4405
class ElectricBunnyComicTumblr(GenericTumblrV1):
4406
    """Class to retrieve Electric Bunny Comics."""
4407
    # Also on http://www.electricbunnycomics.com/View/Comic/153/Welcome+to+Hell
4408
    name = 'bunny-tumblr'
4409
    long_name = 'Electric Bunny Comic (from Tumblr)'
4410
    url = 'http://electricbunnycomics.tumblr.com'
4411
4412
4413
class Hoomph(GenericTumblrV1):
4414
    """Class to retrieve Hoomph comics."""
4415
    name = 'hoomph'
4416
    long_name = 'Hoomph'
4417
    url = 'http://hoom.ph'
4418
4419
4420
class BFGFSTumblr(GenericTumblrV1):
4421
    """Class to retrieve BFGFS comics."""
4422
    # Also on https://tapastic.com/series/BFGFS
4423
    # Also on http://bfgfs.com
4424
    name = 'bfgfs-tumblr'
4425
    long_name = 'BFGFS (from Tumblr)'
4426
    url = 'https://bfgfs.tumblr.com'
4427
4428
4429
class DoodleForFood(GenericTumblrV1):
4430
    """Class to retrieve Doodle For Food comics."""
4431
    # Also on https://tapastic.com/series/Doodle-for-Food
4432
    name = 'doodle'
4433
    long_name = 'Doodle For Food'
4434
    url = 'http://www.doodleforfood.com'
4435
4436
4437
class CassandraCalinTumblr(GenericTumblrV1):
4438
    """Class to retrieve C. Cassandra comics."""
4439
    # Also on http://cassandracalin.com
4440
    # Also on https://tapastic.com/series/C-Cassandra-comics
4441
    name = 'cassandra-tumblr'
4442
    long_name = 'Cassandra Calin (from Tumblr)'
4443
    url = 'http://c-cassandra.tumblr.com'
4444
4445
4446
class DougWasTaken(GenericTumblrV1):
4447
    """Class to retrieve Doug Was Taken comics."""
4448
    name = 'doug'
4449
    long_name = 'Doug Was Taken'
4450
    url = 'https://dougwastaken.tumblr.com'
4451
4452
4453
class MandatoryRollerCoaster(GenericTumblrV1):
4454
    """Class to retrieve Mandatory Roller Coaster comics."""
4455
    name = 'rollercoaster'
4456
    long_name = 'Mandatory Roller Coaster'
4457
    url = 'http://mandatoryrollercoaster.com'
4458
4459
4460
class CEstPasEnRegardantSesPompes(GenericTumblrV1):
4461
    """Class to retrieve C'Est Pas En Regardant Ses Pompes (...)  comics."""
4462
    name = 'cperspqccltt'
4463
    long_name = 'C Est Pas En Regardant Ses Pompes (...)'
4464
    url = 'http://marcoandco.tumblr.com'
4465
4466
4467
class TheGrohlTroll(GenericTumblrV1):
4468
    """Class to retrieve The Grohl Troll comics."""
4469
    name = 'grohltroll'
4470
    long_name = 'The Grohl Troll'
4471
    url = 'http://thegrohltroll.com'
4472
4473
4474
class WebcomicName(GenericTumblrV1):
4475
    """Class to retrieve Webcomic Name comics."""
4476
    name = 'webcomicname'
4477
    long_name = 'Webcomic Name'
4478
    url = 'http://webcomicname.com'
4479
4480
4481
class BooksOfAdam(GenericTumblrV1):
4482
    """Class to retrieve Books of Adam comics."""
4483
    # Also on http://www.booksofadam.com
4484
    name = 'booksofadam'
4485
    long_name = 'Books of Adam'
4486
    url = 'http://booksofadam.tumblr.com'
4487
4488
4489
class HarkAVagrant(GenericTumblrV1):
4490
    """Class to retrieve Hark A Vagrant comics."""
4491
    # Also on http://www.harkavagrant.com
4492
    name = 'hark-tumblr'
4493
    long_name = 'Hark A Vagrant (from Tumblr)'
4494
    url = 'http://beatonna.tumblr.com'
4495
4496
4497
class OurSuperAdventureTumblr(GenericTumblrV1):
4498
    """Class to retrieve Our Super Adventure comics."""
4499
    # Also on https://tapastic.com/series/Our-Super-Adventure
4500
    # Also on http://www.oursuperadventure.com
4501
    # http://sarahgraley.com
4502
    name = 'superadventure-tumblr'
4503
    long_name = 'Our Super Adventure (from Tumblr)'
4504
    url = 'http://sarahssketchbook.tumblr.com'
4505
4506
4507
class JakeLikesOnions(GenericTumblrV1):
4508
    """Class to retrieve Jake Likes Onions comics."""
4509
    name = 'jake'
4510
    long_name = 'Jake Likes Onions'
4511
    url = 'http://jakelikesonions.com'
4512
4513
4514
class InYourFaceCakeTumblr(GenericTumblrV1):
4515
    """Class to retrieve In Your Face Cake comics."""
4516
    # Also on https://tapas.io/series/In-Your-Face-Cake
4517
    name = 'inyourfacecake-tumblr'
4518
    long_name = 'In Your Face Cake (from Tumblr)'
4519
    url = 'https://in-your-face-cake.tumblr.com'
4520
    _categories = ('INYOURFACECAKE', )
4521
4522
4523
class Robospunk(GenericTumblrV1):
4524
    """Class to retrieve Robospunk comics."""
4525
    name = 'robospunk'
4526
    long_name = 'Robospunk'
4527
    url = 'http://robospunk.com'
4528
4529
4530
class BananaTwinky(GenericTumblrV1):
4531
    """Class to retrieve Banana Twinky comics."""
4532
    name = 'banana'
4533
    long_name = 'Banana Twinky'
4534
    url = 'https://bananatwinky.tumblr.com'
4535
4536
4537
class YesterdaysPopcornTumblr(GenericTumblrV1):
4538
    """Class to retrieve Yesterday's Popcorn comics."""
4539
    # Also on http://www.yesterdayspopcorn.com
4540
    # Also on https://tapastic.com/series/Yesterdays-Popcorn
4541
    name = 'popcorn-tumblr'
4542
    long_name = 'Yesterday\'s Popcorn (from Tumblr)'
4543
    url = 'http://yesterdayspopcorn.tumblr.com'
4544
4545
4546
class TwistedDoodles(GenericTumblrV1):
4547
    """Class to retrieve Twisted Doodles comics."""
4548
    name = 'twisted'
4549
    long_name = 'Twisted Doodles'
4550
    url = 'http://www.twisteddoodles.com'
4551
4552
4553
class UbertoolTumblr(GenericTumblrV1):
4554
    """Class to retrieve Ubertool comics."""
4555
    # Also on http://ubertoolcomic.com
4556
    # Also on https://tapastic.com/series/ubertool
4557
    name = 'ubertool-tumblr'
4558
    long_name = 'Ubertool (from Tumblr)'
4559
    url = 'https://ubertool.tumblr.com'
4560
    _categories = ('UBERTOOL', )
4561
4562
4563
class LittleLifeLinesTumblr(GenericDeletedComic, GenericTumblrV1):
4564
    """Class to retrieve Little Life Lines comics."""
4565
    # Also on http://www.littlelifelines.com
4566
    name = 'life-tumblr'
4567
    long_name = 'Little Life Lines (from Tumblr)'
4568
    url = 'https://little-life-lines.tumblr.com'
4569
4570
4571
class TheyCanTalk(GenericTumblrV1):
4572
    """Class to retrieve They Can Talk comics."""
4573
    name = 'theycantalk'
4574
    long_name = 'They Can Talk'
4575
    url = 'http://theycantalk.com'
4576
4577
4578
class Will5NeverCome(GenericTumblrV1):
4579
    """Class to retrieve Will 5:00 Never Come comics."""
4580
    name = 'will5'
4581
    long_name = 'Will 5:00 Never Come ?'
4582
    url = 'http://will5nevercome.com'
4583
4584
4585
class Sephko(GenericTumblrV1):
4586
    """Class to retrieve Sephko Comics."""
4587
    # Also on http://www.sephko.com
4588
    name = 'sephko'
4589
    long_name = 'Sephko'
4590
    url = 'https://sephko.tumblr.com'
4591
4592
4593
class BlazersAtDawn(GenericTumblrV1):
4594
    """Class to retrieve Blazers At Dawn Comics."""
4595
    name = 'blazers'
4596
    long_name = 'Blazers At Dawn'
4597
    url = 'http://blazersatdawn.tumblr.com'
4598
4599
4600
class ArtByMoga(GenericEmptyComic, GenericTumblrV1):  # Deactivated because it downloads too many things
4601
    """Class to retrieve Art By Moga Comics."""
4602
    name = 'moga'
4603
    long_name = 'Art By Moga'
4604
    url = 'http://artbymoga.tumblr.com'
4605
4606
4607
class VerbalVomitTumblr(GenericTumblrV1):
4608
    """Class to retrieve Verbal Vomit comics."""
4609
    # Also on http://www.verbal-vomit.com
4610
    name = 'vomit-tumblr'
4611
    long_name = 'Verbal Vomit (from Tumblr)'
4612
    url = 'http://verbalvomits.tumblr.com'
4613
4614
4615
class LibraryComic(GenericTumblrV1):
4616
    """Class to retrieve LibraryComic."""
4617
    # Also on http://librarycomic.com
4618
    name = 'library-tumblr'
4619
    long_name = 'LibraryComic (from Tumblr)'
4620
    url = 'https://librarycomic.tumblr.com'
4621
4622
4623
class TizzyStitchBirdTumblr(GenericTumblrV1):
4624
    """Class to retrieve Tizzy Stitch Bird comics."""
4625
    # Also on http://tizzystitchbird.com
4626
    # Also on https://tapastic.com/series/TizzyStitchbird
4627
    # Also on http://www.webtoons.com/en/challenge/tizzy-stitchbird/list?title_no=50082
4628
    name = 'tizzy-tumblr'
4629
    long_name = 'Tizzy Stitch Bird (from Tumblr)'
4630
    url = 'http://tizzystitchbird.tumblr.com'
4631
4632
4633
class VictimsOfCircumsolarTumblr(GenericTumblrV1):
4634
    """Class to retrieve VictimsOfCircumsolar comics."""
4635
    # Also on http://www.victimsofcircumsolar.com
4636
    name = 'circumsolar-tumblr'
4637
    long_name = 'Victims Of Circumsolar (from Tumblr)'
4638
    url = 'https://victimsofcomics.tumblr.com'
4639
4640
4641
class RockPaperCynicTumblr(GenericTumblrV1):
4642
    """Class to retrieve RockPaperCynic comics."""
4643
    # Also on http://www.rockpapercynic.com
4644
    # Also on https://tapastic.com/series/rockpapercynic
4645
    name = 'rpc-tumblr'
4646
    long_name = 'Rock Paper Cynic (from Tumblr)'
4647
    url = 'http://rockpapercynic.tumblr.com'
4648
4649
4650
class DeadlyPanelTumblr(GenericTumblrV1):
4651
    """Class to retrieve Deadly Panel comics."""
4652
    # Also on http://www.deadlypanel.com
4653
    # Also on https://tapastic.com/series/deadlypanel
4654
    name = 'deadly-tumblr'
4655
    long_name = 'Deadly Panel (from Tumblr)'
4656
    url = 'https://deadlypanel.tumblr.com'
4657
4658
4659
class CatanaComics(GenericComicNotWorking):  # Not a Tumblr anymore ?
4660
    """Class to retrieve Catana comics."""
4661
    name = 'catana'
4662
    long_name = 'Catana'
4663
    url = 'http://www.catanacomics.com'
4664
4665
4666
class AngryAtNothingTumblr(GenericTumblrV1):
4667
    """Class to retrieve Angry at Nothing comics."""
4668
    # Also on http://www.angryatnothing.net
4669
    # Also on http://tapastic.com/series/Comics-yeah-definitely-comics-
4670
    name = 'angry-tumblr'
4671
    long_name = 'Angry At Nothing (from Tumblr)'
4672
    url = 'http://angryatnothing.tumblr.com'
4673
4674
4675
class ShanghaiTango(GenericTumblrV1):
4676
    """Class to retrieve Shanghai Tango comic."""
4677
    name = 'tango'
4678
    long_name = 'Shanghai Tango'
4679
    url = 'http://tango2010weibo.tumblr.com'
4680
4681
4682
class OffTheLeashDogTumblr(GenericTumblrV1):
4683
    """Class to retrieve Off The Leash Dog comics."""
4684
    # Also on http://offtheleashdogcartoons.com
4685
    # Also on http://www.rupertfawcettcartoons.com
4686
    name = 'offtheleash-tumblr'
4687
    long_name = 'Off The Leash Dog (from Tumblr)'
4688
    url = 'http://rupertfawcettsdoggyblog.tumblr.com'
4689
    _categories = ('FAWCETT', )
4690
4691
4692
class ImogenQuestTumblr(GenericTumblrV1):
4693
    """Class to retrieve Imogen Quest comics."""
4694
    # Also on http://imogenquest.net
4695
    name = 'imogen-tumblr'
4696
    long_name = 'Imogen Quest (from Tumblr)'
4697
    url = 'http://imoquest.tumblr.com'
4698
4699
4700
class Shitfest(GenericTumblrV1):
4701
    """Class to retrieve Shitfest comics."""
4702
    name = 'shitfest'
4703
    long_name = 'Shitfest'
4704
    url = 'http://shitfestcomic.com'
4705
4706
4707
class IceCreamSandwichComics(GenericTumblrV1):
4708
    """Class to retrieve Ice Cream Sandwich Comics."""
4709
    name = 'icecream'
4710
    long_name = 'Ice Cream Sandwich Comics'
4711
    url = 'http://icecreamsandwichcomics.com'
4712
4713
4714
class Dustinteractive(GenericTumblrV1):
4715
    """Class to retrieve Dustinteractive comics."""
4716
    name = 'dustinteractive'
4717
    long_name = 'Dustinteractive'
4718
    url = 'http://dustinteractive.com'
4719
4720
4721
class StickyCinemaFloor(GenericTumblrV1):
4722
    """Class to retrieve Sticky Cinema Floor comics."""
4723
    name = 'stickycinema'
4724
    long_name = 'Sticky Cinema Floor'
4725
    url = 'https://stickycinemafloor.tumblr.com'
4726
4727
4728
class IncidentalComicsTumblr(GenericTumblrV1):
4729
    """Class to retrieve Incidental Comics."""
4730
    # Also on http://www.incidentalcomics.com
4731
    name = 'incidental-tumblr'
4732
    long_name = 'Incidental Comics (from Tumblr)'
4733
    url = 'http://incidentalcomics.tumblr.com'
4734
4735
4736
class APleasantWasteOfTimeTumblr(GenericTumblrV1):
4737
    """Class to retrieve A Pleasant Waste Of Time comics."""
4738
    # Also on https://tapas.io/series/A-Pleasant-
4739
    name = 'pleasant-waste-tumblr'
4740
    long_name = 'A Pleasant Waste Of Time (from Tumblr)'
4741
    url = 'https://artjcf.tumblr.com'
4742
    _categories = ('WASTE', )
4743
4744
4745
class HorovitzComicsTumblr(GenericTumblrV1):
4746
    """Class to retrieve Horovitz new comics."""
4747
    # Also on http://www.horovitzcomics.com
4748
    name = 'horovitz-tumblr'
4749
    long_name = 'Horovitz (from Tumblr)'
4750
    url = 'https://horovitzcomics.tumblr.com'
4751
    _categories = ('HOROVITZ', )
4752
4753
4754
class DeepDarkFearsTumblr(GenericTumblrV1):
4755
    """Class to retrieve DeepvDarkvFears comics."""
4756
    name = 'deep-dark-fears-tumblr'
4757
    long_name = 'Deep Dark Fears (from Tumblr)'
4758
    url = 'http://deep-dark-fears.tumblr.com'
4759
4760
4761
class DakotaMcDadzean(GenericTumblrV1):
4762
    """Class to retrieve Dakota McDadzean comics."""
4763
    name = 'dakota'
4764
    long_name = 'Dakota McDadzean'
4765
    url = 'http://dakotamcfadzean.tumblr.com'
4766
4767
4768
class ExtraFabulousComicsTumblr(GenericTumblrV1):
4769
    """Class to retrieve Extra Fabulous Comics."""
4770
    # Also on http://extrafabulouscomics.com
4771
    name = 'efc-tumblr'
4772
    long_name = 'Extra Fabulous Comics (from Tumblr)'
4773
    url = 'https://extrafabulouscomics.tumblr.com'
4774
    _categories = ('EFC', )
4775
4776
4777
class AlexLevesque(GenericTumblrV1):
4778
    """Class to retrieve AlexLevesque comics."""
4779
    name = 'alevesque'
4780
    long_name = 'Alex Levesque'
4781
    url = 'http://alexlevesque.com'
4782
    _categories = ('FRANCAIS', )
4783
4784
4785
class JamesOfNoTradesTumblr(GenericTumblrV1):
4786
    """Class to retrieve JamesOfNoTrades comics."""
4787
    # Also on http://jamesofnotrades.com
4788
    # Also on http://www.webtoons.com/en/challenge/james-of-no-trades/list?title_no=43422
4789
    # Also on https://tapas.io/series/James-of-No-Trades
4790
    name = 'jamesofnotrades-tumblr'
4791
    long_name = 'James Of No Trades (from Tumblr)'
4792
    url = 'http://jamesfregan.tumblr.com'
4793
    _categories = ('JAMESOFNOTRADES', )
4794
4795
4796
class InfiniteGuff(GenericTumblrV1):
4797
    """Class to retrieve Infinite Guff comics."""
4798
    name = 'infiniteguff'
4799
    long_name = 'Infinite Guff'
4800
    url = 'http://infiniteguff.com'
4801
4802
4803
class SkeletonClaw(GenericTumblrV1):
4804
    """Class to retrieve Skeleton Claw comics."""
4805
    name = 'skeletonclaw'
4806
    long_name = 'Skeleton Claw'
4807
    url = 'http://skeletonclaw.com'
4808
4809
4810
class MrsFrolleinTumblr(GenericTumblrV1):
4811
    """Class to retrieve Mrs Frollein comics."""
4812
    # Also on http://www.webtoons.com/en/challenge/mrsfrollein/list?title_no=51710
4813
    name = 'frollein'
4814
    long_name = 'Mrs Frollein (from Tumblr)'
4815
    url = 'https://mrsfrollein.tumblr.com'
4816
4817
4818
class GoodBearComicsTumblr(GenericTumblrV1):
4819
    """Class to retrieve GoodBearComics."""
4820
    # Also on https://goodbearcomics.com
4821
    name = 'goodbear-tumblr'
4822
    long_name = 'Good Bear Comics (from Tumblr)'
4823
    url = 'https://goodbearcomics.tumblr.com'
4824
4825
4826
class BrooklynCartoonsTumblr(GenericTumblrV1):
4827
    """Class to retrieve Brooklyn Cartoons."""
4828
    # Also on https://www.brooklyncartoons.com
4829
    # Also on https://www.instagram.com/brooklyncartoons
4830
    name = 'brooklyn-tumblr'
4831
    long_name = 'Brooklyn Cartoons (from Tumblr)'
4832
    url = 'http://brooklyncartoons.tumblr.com'
4833
4834
4835
class GemmaCorrellTumblr(GenericTumblrV1):
4836
    # Also on http://www.gemmacorrell.com/portfolio/comics/
4837
    name = 'gemma-tumblr'
4838
    long_name = 'Gemma Correll (from Tumblr)'
4839
    url = 'http://gemmacorrell.tumblr.com'
4840
4841
4842
class RobotatertotTumblr(GenericTumblrV1):
4843
    """Class to retrieve Robotatertot comics."""
4844
    # Also on https://www.instagram.com/robotatertotcomics
4845
    name = 'robotatertot-tumblr'
4846
    long_name = 'Robotatertot (from Tumblr)'
4847
    url = 'https://robotatertot.tumblr.com'
4848
4849
4850
class HuffyPenguin(GenericTumblrV1):
4851
    """Class to retrieve Huffy Penguin comics."""
4852
    name = 'huffypenguin'
4853
    long_name = 'Huffy Penguin'
4854
    url = 'http://huffy-penguin.tumblr.com'
4855
4856
4857
class CowardlyComicsTumblr(GenericTumblrV1):
4858
    """Class to retrieve Cowardly Comics."""
4859
    # Also on https://tapas.io/series/CowardlyComics
4860
    # Also on http://www.webtoons.com/en/challenge/cowardly-comics/list?title_no=65893
4861
    name = 'cowardly-tumblr'
4862
    long_name = 'Cowardly Comics (from Tumblr)'
4863
    url = 'http://cowardlycomics.tumblr.com'
4864
4865
4866
class Caw4hwTumblr(GenericTumblrV1):
4867
    """Class to retrieve Caw4hw comics."""
4868
    # Also on https://tapas.io/series/CAW4HW
4869
    name = 'caw4hw-tumblr'
4870
    long_name = 'Caw4hw (from Tumblr)'
4871
    url = 'https://caw4hw.tumblr.com'
4872
4873
4874
class WeFlapsTumblr(GenericTumblrV1):
4875
    """Class to retrieve WeFlaps comics."""
4876
    name = 'weflaps-tumblr'
4877
    long_name = 'We Flaps (from Tumblr)'
4878
    url = 'https://weflaps.tumblr.com'
4879
4880
4881
class TheseInsideJokesTumblr(GenericTumblrV1):
4882
    """Class to retrieve These Inside Jokes comics."""
4883
    # Also on http://www.theseinsidejokes.com
4884
    name = 'theseinsidejokes-tumblr'
4885
    long_name = 'These Inside Jokes (from Tumblr)'
4886
    url = 'http://theseinsidejokes.tumblr.com'
4887
4888
4889
class RustledJimmies(GenericTumblrV1):
4890
    """Class to retrieve Rustled Jimmies comics."""
4891
    name = 'restled'
4892
    long_name = 'Rustled Jimmies'
4893
    url = 'http://rustledjimmies.net'
4894
4895
4896
class SinewynTumblr(GenericTumblrV1):
4897
    """Class to retrieve Sinewyn comics."""
4898
    # Also on https://sinewyn.wordpress.com
4899
    name = 'sinewyn-tumblr'
4900
    long_name = 'Sinewyn (from Tumblr)'
4901
    url = 'https://sinewyn.tumblr.com'
4902
4903
4904
class ItFoolsAMonster(GenericTumblrV1):
4905
    """Class to retrieve It Fools A Monster comics."""
4906
    name = 'itfoolsamonster'
4907
    long_name = 'It Fools A Monster'
4908
    url = 'http://itfoolsamonster.com'
4909
4910
4911
class BoumeriesTumblr(GenericTumblrV1):
4912
    """Class to retrieve Boumeries comics."""
4913
    # Also on http://bd.boumerie.com
4914
    # Also on http://comics.boumerie.com
4915
    name = 'boumeries-tumblr'
4916
    long_name = 'Boumeries (from Tumblr)'
4917
    url = 'http://boumeries.tumblr.com/'
4918
    _categories = ('BOUMERIES', )
4919
4920
4921
class InfiniteImmortalBensTumblr(GenericTumblrV1):
4922
    """Class to retrieve Infinite Immortal Bens comics."""
4923
    # Also on http://www.webtoons.com/en/challenge/infinite-immortal-bens/list?title_no=32847
4924
    # Also on https://tapas.io/series/Infinite-Immortal-Bens
4925
    url = 'https://infiniteimmortalbens.tumblr.com'
4926
    name = 'infiniteimmortal-tumblr'
4927
    long_name = 'Infinite Immortal Bens (from Tumblr)'
4928
    _categories = ('INFINITEIMMORTAL', )
4929
4930
4931
class HorovitzComics(GenericDeletedComic, GenericListableComic):
4932
    """Generic class to handle the logic common to the different comics from Horovitz."""
4933
    # Also on https://horovitzcomics.tumblr.com
4934
    url = 'http://www.horovitzcomics.com'
4935
    _categories = ('HOROVITZ', )
4936
    img_re = re.compile('.*comics/([0-9]*)/([0-9]*)/([0-9]*)/.*$')
4937
    link_re = NotImplemented
4938
    get_url_from_archive_element = join_cls_url_to_href
4939
4940 View Code Duplication
    @classmethod
0 ignored issues
show
This code seems to be duplicated in your project.
Loading history...
4941
    def get_comic_info(cls, soup, link):
4942
        """Get information about a particular comics."""
4943
        href = link['href']
4944
        num = int(cls.link_re.match(href).groups()[0])
4945
        title = link.string
4946
        imgs = soup.find_all('img', id='comic')
4947
        assert len(imgs) == 1, imgs
4948
        year, month, day = [int(s)
4949
                            for s in cls.img_re.match(imgs[0]['src']).groups()]
4950
        return {
4951
            'title': title,
4952
            'day': day,
4953
            'month': month,
4954
            'year': year,
4955
            'img': [i['src'] for i in imgs],
4956
            'num': num,
4957
        }
4958
4959
    @classmethod
4960
    def get_archive_elements(cls):
4961
        archive_url = 'http://www.horovitzcomics.com/comics/archive/'
4962
        return reversed(get_soup_at_url(archive_url).find_all('a', href=cls.link_re))
4963
4964
4965
class HorovitzNew(HorovitzComics):
4966
    """Class to retrieve Horovitz new comics."""
4967
    name = 'horovitznew'
4968
    long_name = 'Horovitz New'
4969
    link_re = re.compile('^/comics/new/([0-9]+)$')
4970
4971
4972
class HorovitzClassic(HorovitzComics):
4973
    """Class to retrieve Horovitz classic comics."""
4974
    name = 'horovitzclassic'
4975
    long_name = 'Horovitz Classic'
4976
    link_re = re.compile('^/comics/classic/([0-9]+)$')
4977
4978
4979
class GenericGoComic(GenericNavigableComic):
4980
    """Generic class to handle the logic common to comics from gocomics.com."""
4981
    _categories = ('GOCOMIC', )
4982
4983
    @classmethod
4984
    def get_first_comic_link(cls):
4985
        """Get link to first comics."""
4986
        return get_soup_at_url(cls.url).find('a', class_='fa gc-comic-nav__button fa fa-backward sm ')
4987
4988
    @classmethod
4989
    def get_navi_link(cls, last_soup, next_):
4990
        """Get link to next or previous comic."""
4991
        PREV = 'fa gc-comic-nav__button fa-caret-left sm js-previous-comic '
4992
        NEXT = 'fa gc-comic-nav__button fa-caret-right sm js-next-comic d-sm-none '
4993
        return last_soup.find('a', class_=NEXT if next_ else PREV)
4994
4995
    @classmethod
4996
    def get_url_from_link(cls, link):
4997
        gocomics = 'http://www.gocomics.com'
4998
        return urljoin_wrapper(gocomics, link['href'])
4999
5000
    @classmethod
5001
    def get_comic_info(cls, soup, link):
5002
        """Get information about a particular comics."""
5003
        date_str = soup.find('meta', property='article:published_time')['content']
5004
        day = string_to_date(date_str, "%Y-%m-%d")
5005
        imgs = soup.find('picture', class_='img-fluid item-comic-image').find_all('img')
5006
        author = soup.find('meta', property='article:author')['content']
5007
        tags = soup.find('meta', property='article:tag')['content']
5008
        return {
5009
            'day': day.day,
5010
            'month': day.month,
5011
            'year': day.year,
5012
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
5013
            'author': author,
5014
            'tags': tags,
5015
        }
5016
5017
5018
class PearlsBeforeSwine(GenericGoComic):
5019
    """Class to retrieve Pearls Before Swine comics."""
5020
    name = 'pearls'
5021
    long_name = 'Pearls Before Swine'
5022
    url = 'http://www.gocomics.com/pearlsbeforeswine'
5023
5024
5025
class Peanuts(GenericGoComic):
5026
    """Class to retrieve Peanuts comics."""
5027
    name = 'peanuts'
5028
    long_name = 'Peanuts'
5029
    url = 'http://www.gocomics.com/peanuts'
5030
5031
5032
class MattWuerker(GenericGoComic):
5033
    """Class to retrieve Matt Wuerker comics."""
5034
    name = 'wuerker'
5035
    long_name = 'Matt Wuerker'
5036
    url = 'http://www.gocomics.com/mattwuerker'
5037
5038
5039
class TomToles(GenericGoComic):
5040
    """Class to retrieve Tom Toles comics."""
5041
    name = 'toles'
5042
    long_name = 'Tom Toles'
5043
    url = 'http://www.gocomics.com/tomtoles'
5044
5045
5046
class BreakOfDay(GenericGoComic):
5047
    """Class to retrieve Break Of Day comics."""
5048
    name = 'breakofday'
5049
    long_name = 'Break Of Day'
5050
    url = 'http://www.gocomics.com/break-of-day'
5051
5052
5053
class Brevity(GenericGoComic):
5054
    """Class to retrieve Brevity comics."""
5055
    name = 'brevity'
5056
    long_name = 'Brevity'
5057
    url = 'http://www.gocomics.com/brevity'
5058
5059
5060
class MichaelRamirez(GenericGoComic):
5061
    """Class to retrieve Michael Ramirez comics."""
5062
    name = 'ramirez'
5063
    long_name = 'Michael Ramirez'
5064
    url = 'http://www.gocomics.com/michaelramirez'
5065
5066
5067
class MikeLuckovich(GenericGoComic):
5068
    """Class to retrieve Mike Luckovich comics."""
5069
    name = 'luckovich'
5070
    long_name = 'Mike Luckovich'
5071
    url = 'http://www.gocomics.com/mikeluckovich'
5072
5073
5074
class JimBenton(GenericGoComic):
5075
    """Class to retrieve Jim Benton comics."""
5076
    # Also on http://jimbenton.tumblr.com
5077
    name = 'benton'
5078
    long_name = 'Jim Benton'
5079
    url = 'http://www.gocomics.com/jim-benton-cartoons'
5080
5081
5082
class TheArgyleSweater(GenericGoComic):
5083
    """Class to retrieve the Argyle Sweater comics."""
5084
    name = 'argyle'
5085
    long_name = 'Argyle Sweater'
5086
    url = 'http://www.gocomics.com/theargylesweater'
5087
5088
5089
class SunnyStreet(GenericGoComic):
5090
    """Class to retrieve Sunny Street comics."""
5091
    # Also on http://www.sunnystreetcomics.com
5092
    name = 'sunny'
5093
    long_name = 'Sunny Street'
5094
    url = 'http://www.gocomics.com/sunny-street'
5095
5096
5097
class OffTheMark(GenericGoComic):
5098
    """Class to retrieve Off The Mark comics."""
5099
    # Also on https://www.offthemark.com
5100
    name = 'offthemark'
5101
    long_name = 'Off The Mark'
5102
    url = 'http://www.gocomics.com/offthemark'
5103
5104
5105
class WuMo(GenericGoComic):
5106
    """Class to retrieve WuMo comics."""
5107
    # Also on http://wumo.com
5108
    name = 'wumo'
5109
    long_name = 'WuMo'
5110
    url = 'http://www.gocomics.com/wumo'
5111
5112
5113
class LunarBaboon(GenericGoComic):
5114
    """Class to retrieve Lunar Baboon comics."""
5115
    # Also on http://www.lunarbaboon.com
5116
    # Also on https://tapastic.com/series/Lunarbaboon
5117
    name = 'lunarbaboon'
5118
    long_name = 'Lunar Baboon'
5119
    url = 'http://www.gocomics.com/lunarbaboon'
5120
5121
5122
class SandersenGocomic(GenericGoComic):
5123
    """Class to retrieve Sarah Andersen comics."""
5124
    # Also on http://sarahcandersen.com
5125
    # Also on http://tapastic.com/series/Doodle-Time
5126
    name = 'sandersen-goc'
5127
    long_name = 'Sarah Andersen (from GoComics)'
5128
    url = 'http://www.gocomics.com/sarahs-scribbles'
5129
5130
5131
class SaturdayMorningBreakfastCerealGoComic(GenericGoComic):
5132
    """Class to retrieve Saturday Morning Breakfast Cereal comics."""
5133
    # Also on http://smbc-comics.tumblr.com
5134
    # Also on http://www.smbc-comics.com
5135
    name = 'smbc-goc'
5136
    long_name = 'Saturday Morning Breakfast Cereal (from GoComics)'
5137
    url = 'http://www.gocomics.com/saturday-morning-breakfast-cereal'
5138
    _categories = ('SMBC', )
5139
5140
5141
class CalvinAndHobbesGoComic(GenericGoComic):
5142
    """Class to retrieve Calvin and Hobbes comics."""
5143
    # From gocomics, not http://marcel-oehler.marcellosendos.ch/comics/ch/
5144
    name = 'calvin-goc'
5145
    long_name = 'Calvin and Hobbes (from GoComics)'
5146
    url = 'http://www.gocomics.com/calvinandhobbes'
5147
5148
5149
class RallGoComic(GenericGoComic):
5150
    """Class to retrieve Ted Rall comics."""
5151
    # Also on http://rall.com/comic
5152
    name = 'rall-goc'
5153
    long_name = "Ted Rall (from GoComics)"
5154
    url = "http://www.gocomics.com/ted-rall"
5155
    _categories = ('RALL', )
5156
5157
5158
class TheAwkwardYetiGoComic(GenericGoComic):
5159
    """Class to retrieve The Awkward Yeti comics."""
5160
    # Also on http://larstheyeti.tumblr.com
5161
    # Also on http://theawkwardyeti.com
5162
    # Also on https://tapastic.com/series/TheAwkwardYeti
5163
    name = 'yeti-goc'
5164
    long_name = 'The Awkward Yeti (from GoComics)'
5165
    url = 'http://www.gocomics.com/the-awkward-yeti'
5166
    _categories = ('YETI', )
5167
5168
5169
class BerkeleyMewsGoComics(GenericGoComic):
5170
    """Class to retrieve Berkeley Mews comics."""
5171
    # Also on http://mews.tumblr.com
5172
    # Also on http://www.berkeleymews.com
5173
    name = 'berkeley-goc'
5174
    long_name = 'Berkeley Mews (from GoComics)'
5175
    url = 'http://www.gocomics.com/berkeley-mews'
5176
    _categories = ('BERKELEY', )
5177
5178
5179
class SheldonGoComics(GenericGoComic):
5180
    """Class to retrieve Sheldon comics."""
5181
    # Also on http://www.sheldoncomics.com
5182
    name = 'sheldon-goc'
5183
    long_name = 'Sheldon Comics (from GoComics)'
5184
    url = 'http://www.gocomics.com/sheldon'
5185
5186
5187
class FowlLanguageGoComics(GenericGoComic):
5188
    """Class to retrieve Fowl Language comics."""
5189
    # Also on http://www.fowllanguagecomics.com
5190
    # Also on http://tapastic.com/series/Fowl-Language-Comics
5191
    # Also on http://fowllanguagecomics.tumblr.com
5192
    name = 'fowllanguage-goc'
5193
    long_name = 'Fowl Language Comics (from GoComics)'
5194
    url = 'http://www.gocomics.com/fowl-language'
5195
    _categories = ('FOWLLANGUAGE', )
5196
5197
5198
class NickAnderson(GenericGoComic):
5199
    """Class to retrieve Nick Anderson comics."""
5200
    name = 'nickanderson'
5201
    long_name = 'Nick Anderson'
5202
    url = 'http://www.gocomics.com/nickanderson'
5203
5204
5205
class GarfieldGoComics(GenericGoComic):
5206
    """Class to retrieve Garfield comics."""
5207
    # Also on http://garfield.com
5208
    name = 'garfield-goc'
5209
    long_name = 'Garfield (from GoComics)'
5210
    url = 'http://www.gocomics.com/garfield'
5211
    _categories = ('GARFIELD', )
5212
5213
5214
class DorrisMcGoComics(GenericGoComic):
5215
    """Class to retrieve Dorris Mc Comics"""
5216
    # Also on http://dorrismccomics.com
5217
    name = 'dorrismc-goc'
5218
    long_name = 'Dorris Mc (from GoComics)'
5219
    url = 'http://www.gocomics.com/dorris-mccomics'
5220
5221
5222
class FoxTrot(GenericGoComic):
5223
    """Class to retrieve FoxTrot comics."""
5224
    name = 'foxtrot'
5225
    long_name = 'FoxTrot'
5226
    url = 'http://www.gocomics.com/foxtrot'
5227
5228
5229
class FoxTrotClassics(GenericGoComic):
5230
    """Class to retrieve FoxTrot Classics comics."""
5231
    name = 'foxtrot-classics'
5232
    long_name = 'FoxTrot Classics'
5233
    url = 'http://www.gocomics.com/foxtrotclassics'
5234
5235
5236
class MisterAndMeGoComics(GenericDeletedComic, GenericGoComic):
5237
    """Class to retrieve Mister & Me Comics."""
5238
    # Also on http://www.mister-and-me.com
5239
    # Also on https://tapastic.com/series/Mister-and-Me
5240
    name = 'mister-goc'
5241
    long_name = 'Mister & Me (from GoComics)'
5242
    url = 'http://www.gocomics.com/mister-and-me'
5243
5244
5245
class NonSequitur(GenericGoComic):
5246
    """Class to retrieve Non Sequitur (Wiley Miller) comics."""
5247
    name = 'nonsequitur'
5248
    long_name = 'Non Sequitur'
5249
    url = 'http://www.gocomics.com/nonsequitur'
5250
5251
5252
class JoeyAlisonSayers(GenericGoComic):
5253
    """Class to retrieve Joey Alison Sayers comics."""
5254
    name = 'joeyalison'
5255
    long_name = 'Joey Alison Sayers (from GoComics)'
5256
    url = 'http://www.gocomics.com/joey-alison-sayers-comics'
5257
5258
5259
class SavageChickenGoComics(GenericGoComic):
5260
    """Class to retrieve Savage Chicken comics."""
5261
    # Also on http://www.savagechickens.com
5262
    name = 'savage-goc'
5263
    long_name = 'Savage Chicken (from GoComics)'
5264
    url = 'http://www.gocomics.com/savage-chickens'
5265
5266
5267
class GenericTapasticComic(GenericListableComic):
5268
    """Generic class to handle the logic common to comics from tapastic.com."""
5269
    _categories = ('TAPASTIC', )
5270
5271
    @classmethod
5272
    def get_comic_info(cls, soup, archive_elt):
5273
        """Get information about a particular comics."""
5274
        timestamp = int(archive_elt['publishDate']) / 1000.0
5275
        day = datetime.datetime.fromtimestamp(timestamp).date()
5276
        imgs = soup.find_all('img', class_='art-image')
5277
        if not imgs:
5278
            # print("Comic %s is being uploaded, retry later" % cls.get_url_from_archive_element(archive_elt))
5279
            return None
5280
        assert len(imgs) > 0, imgs
5281
        return {
5282
            'day': day.day,
5283
            'year': day.year,
5284
            'month': day.month,
5285
            'img': [i['src'] for i in imgs],
5286
            'title': archive_elt['title'],
5287
        }
5288
5289
    @classmethod
5290
    def get_url_from_archive_element(cls, archive_elt):
5291
        return 'http://tapastic.com/episode/' + str(archive_elt['id'])
5292
5293
    @classmethod
5294
    def get_archive_elements(cls):
5295
        pref, suff = 'episodeList : ', ','
5296
        # Information is stored in the javascript part
5297
        # I don't know the clean way to get it so this is the ugly way.
5298
        string = [s[len(pref):-len(suff)] for s in (s.decode('utf-8').strip() for s in urlopen_wrapper(cls.url).readlines()) if s.startswith(pref) and s.endswith(suff)][0]
5299
        return json.loads(string)
5300
5301
5302
class VegetablesForDessert(GenericTapasticComic):
5303
    """Class to retrieve Vegetables For Dessert comics."""
5304
    # Also on http://vegetablesfordessert.tumblr.com
5305
    name = 'vegetables'
5306
    long_name = 'Vegetables For Dessert'
5307
    url = 'http://tapastic.com/series/vegetablesfordessert'
5308
5309
5310
class FowlLanguageTapa(GenericTapasticComic):
5311
    """Class to retrieve Fowl Language comics."""
5312
    # Also on http://www.fowllanguagecomics.com
5313
    # Also on http://fowllanguagecomics.tumblr.com
5314
    # Also on http://www.gocomics.com/fowl-language
5315
    name = 'fowllanguage-tapa'
5316
    long_name = 'Fowl Language Comics (from Tapastic)'
5317
    url = 'http://tapastic.com/series/Fowl-Language-Comics'
5318
    _categories = ('FOWLLANGUAGE', )
5319
5320
5321
class OscillatingProfundities(GenericTapasticComic):
5322
    """Class to retrieve Oscillating Profundities comics."""
5323
    name = 'oscillating'
5324
    long_name = 'Oscillating Profundities'
5325
    url = 'http://tapastic.com/series/oscillatingprofundities'
5326
5327
5328
class ZnoflatsComics(GenericTapasticComic):
5329
    """Class to retrieve Znoflats comics."""
5330
    name = 'znoflats'
5331
    long_name = 'Znoflats Comics'
5332
    url = 'http://tapastic.com/series/Znoflats-Comics'
5333
5334
5335
class SandersenTapastic(GenericTapasticComic):
5336
    """Class to retrieve Sarah Andersen comics."""
5337
    # Also on http://sarahcandersen.com
5338
    # Also on http://www.gocomics.com/sarahs-scribbles
5339
    name = 'sandersen-tapa'
5340
    long_name = 'Sarah Andersen (from Tapastic)'
5341
    url = 'http://tapastic.com/series/Doodle-Time'
5342
5343
5344
class TubeyToonsTapastic(GenericTapasticComic):
5345
    """Class to retrieve TubeyToons comics."""
5346
    # Also on http://tubeytoons.com
5347
    # Also on https://tubeytoons.tumblr.com
5348
    name = 'tubeytoons-tapa'
5349
    long_name = 'Tubey Toons (from Tapastic)'
5350
    url = 'http://tapastic.com/series/Tubey-Toons'
5351
    _categories = ('TUNEYTOONS', )
5352
5353
5354
class AnythingComicTapastic(GenericTapasticComic):
5355
    """Class to retrieve Anything Comics."""
5356
    # Also on http://www.anythingcomic.com
5357
    name = 'anythingcomic-tapa'
5358
    long_name = 'Anything Comic (from Tapastic)'
5359
    url = 'http://tapastic.com/series/anything'
5360
5361
5362
class UnearthedComicsTapastic(GenericTapasticComic):
5363
    """Class to retrieve Unearthed comics."""
5364
    # Also on http://unearthedcomics.com
5365
    # Also on https://unearthedcomics.tumblr.com
5366
    name = 'unearthed-tapa'
5367
    long_name = 'Unearthed Comics (from Tapastic)'
5368
    url = 'http://tapastic.com/series/UnearthedComics'
5369
    _categories = ('UNEARTHED', )
5370
5371
5372
class EverythingsStupidTapastic(GenericTapasticComic):
5373
    """Class to retrieve Everything's stupid Comics."""
5374
    # Also on http://www.webtoons.com/en/challenge/everythings-stupid/list?title_no=14591
5375
    # Also on http://everythingsstupid.net
5376
    name = 'stupid-tapa'
5377
    long_name = "Everything's Stupid (from Tapastic)"
5378
    url = 'http://tapastic.com/series/EverythingsStupid'
5379
5380
5381
class JustSayEhTapastic(GenericTapasticComic):
5382
    """Class to retrieve Just Say Eh comics."""
5383
    # Also on http://www.justsayeh.com
5384
    name = 'justsayeh-tapa'
5385
    long_name = 'Just Say Eh (from Tapastic)'
5386
    url = 'http://tapastic.com/series/Just-Say-Eh'
5387
5388
5389
class ThorsThundershackTapastic(GenericTapasticComic):
5390
    """Class to retrieve Thor's Thundershack comics."""
5391
    # Also on http://www.thorsthundershack.com
5392
    name = 'thor-tapa'
5393
    long_name = 'Thor\'s Thundershack (from Tapastic)'
5394
    url = 'http://tapastic.com/series/Thors-Thundershac'
5395
    _categories = ('THOR', )
5396
5397
5398
class OwlTurdTapastic(GenericTapasticComic):
5399
    """Class to retrieve Owl Turd comics."""
5400
    # Also on http://owlturd.com
5401
    name = 'owlturd-tapa'
5402
    long_name = 'Owl Turd (from Tapastic)'
5403
    url = 'http://tapastic.com/series/Owl-Turd-Comix'
5404
    _categories = ('OWLTURD', )
5405
5406
5407
class GoneIntoRaptureTapastic(GenericTapasticComic):
5408
    """Class to retrieve Gone Into Rapture comics."""
5409
    # Also on http://goneintorapture.tumblr.com
5410
    # Also on http://goneintorapture.com
5411
    name = 'rapture-tapa'
5412
    long_name = 'Gone Into Rapture (from Tapastic)'
5413
    url = 'http://tapastic.com/series/Goneintorapture'
5414
5415
5416
class HeckIfIKnowComicsTapa(GenericTapasticComic):
5417
    """Class to retrieve Heck If I Know Comics."""
5418
    # Also on http://heckifiknowcomics.com
5419
    name = 'heck-tapa'
5420
    long_name = 'Heck if I Know comics (from Tapastic)'
5421
    url = 'http://tapastic.com/series/Regular'
5422
5423
5424
class CheerUpEmoKidTapa(GenericTapasticComic):
5425
    """Class to retrieve CheerUpEmoKid comics."""
5426
    # Also on http://www.cheerupemokid.com
5427
    # Also on https://enzocomics.tumblr.com
5428
    name = 'cuek-tapa'
5429
    long_name = 'Cheer Up Emo Kid (from Tapastic)'
5430
    url = 'http://tapastic.com/series/CUEK'
5431
5432
5433
class BigFootJusticeTapa(GenericTapasticComic):
5434
    """Class to retrieve Big Foot Justice comics."""
5435
    # Also on http://bigfootjustice.com
5436
    name = 'bigfoot-tapa'
5437
    long_name = 'Big Foot Justice (from Tapastic)'
5438
    url = 'http://tapastic.com/series/bigfoot-justice'
5439
5440
5441
class UpAndOutTapa(GenericTapasticComic):
5442
    """Class to retrieve Up & Out comics."""
5443
    # Also on http://upandoutcomic.tumblr.com
5444
    name = 'upandout-tapa'
5445
    long_name = 'Up And Out (from Tapastic)'
5446
    url = 'http://tapastic.com/series/UP-and-OUT'
5447
5448
5449
class ToonHoleTapa(GenericTapasticComic):
5450
    """Class to retrieve Toon Holes comics."""
5451
    # Also on http://www.toonhole.com
5452
    name = 'toonhole-tapa'
5453
    long_name = 'Toon Hole (from Tapastic)'
5454
    url = 'http://tapastic.com/series/TOONHOLE'
5455
5456
5457
class AngryAtNothingTapa(GenericTapasticComic):
5458
    """Class to retrieve Angry at Nothing comics."""
5459
    # Also on http://www.angryatnothing.net
5460
    # Also on http://angryatnothing.tumblr.com
5461
    name = 'angry-tapa'
5462
    long_name = 'Angry At Nothing (from Tapastic)'
5463
    url = 'http://tapastic.com/series/Comics-yeah-definitely-comics-'
5464
5465
5466
class LeleozTapa(GenericTapasticComic):
5467
    """Class to retrieve Leleoz comics."""
5468
    # Also on http://leleozcomics.tumblr.com
5469
    name = 'leleoz-tapa'
5470
    long_name = 'Leleoz (from Tapastic)'
5471
    url = 'https://tapastic.com/series/Leleoz'
5472
5473
5474
class TheAwkwardYetiTapa(GenericTapasticComic):
5475
    """Class to retrieve The Awkward Yeti comics."""
5476
    # Also on http://www.gocomics.com/the-awkward-yeti
5477
    # Also on http://theawkwardyeti.com
5478
    # Also on http://larstheyeti.tumblr.com
5479
    name = 'yeti-tapa'
5480
    long_name = 'The Awkward Yeti (from Tapastic)'
5481
    url = 'https://tapastic.com/series/TheAwkwardYeti'
5482
    _categories = ('YETI', )
5483
5484
5485
class AsPerUsualTapa(GenericTapasticComic):
5486
    """Class to retrieve As Per Usual comics."""
5487
    # Also on http://as-per-usual.tumblr.com
5488
    name = 'usual-tapa'
5489
    long_name = 'As Per Usual (from Tapastic)'
5490
    url = 'https://tapastic.com/series/AsPerUsual'
5491
    categories = ('DAMILEE', )
5492
5493
5494
class HotComicsForCoolPeopleTapa(GenericTapasticComic):
5495
    """Class to retrieve Hot Comics For Cool People."""
5496
    # Also on http://hotcomicsforcoolpeople.tumblr.com
5497
    # Also on http://hotcomics.biz (links to tumblr)
5498
    # Also on http://hcfcp.com (links to tumblr)
5499
    name = 'hotcomics-tapa'
5500
    long_name = 'Hot Comics For Cool People (from Tapastic)'
5501
    url = 'https://tapastic.com/series/Hot-Comics-For-Cool-People'
5502
    categories = ('DAMILEE', )
5503
5504
5505
class OneOneOneOneComicTapa(GenericTapasticComic):
5506
    """Class to retrieve 1111 Comics."""
5507
    # Also on http://www.1111comics.me
5508
    # Also on http://comics1111.tumblr.com
5509
    name = '1111-tapa'
5510
    long_name = '1111 Comics (from Tapastic)'
5511
    url = 'https://tapastic.com/series/1111-Comics'
5512
    _categories = ('ONEONEONEONE', )
5513
5514
5515
class TumbleDryTapa(GenericTapasticComic):
5516
    """Class to retrieve Tumble Dry comics."""
5517
    # Also on http://tumbledrycomics.com
5518
    name = 'tumbledry-tapa'
5519
    long_name = 'Tumblr Dry (from Tapastic)'
5520
    url = 'https://tapastic.com/series/TumbleDryComics'
5521
5522
5523
class DeadlyPanelTapa(GenericTapasticComic):
5524
    """Class to retrieve Deadly Panel comics."""
5525
    # Also on http://www.deadlypanel.com
5526
    # Also on https://deadlypanel.tumblr.com
5527
    name = 'deadly-tapa'
5528
    long_name = 'Deadly Panel (from Tapastic)'
5529
    url = 'https://tapastic.com/series/deadlypanel'
5530
5531
5532
class ChrisHallbeckMaxiTapa(GenericTapasticComic):
5533
    """Class to retrieve Chris Hallbeck comics."""
5534
    # Also on https://chrishallbeck.tumblr.com
5535
    # Also on http://maximumble.com
5536
    name = 'hallbeckmaxi-tapa'
5537
    long_name = 'Chris Hallback - Maximumble (from Tapastic)'
5538
    url = 'https://tapastic.com/series/Maximumble'
5539
    _categories = ('HALLBACK', )
5540
5541
5542
class ChrisHallbeckMiniTapa(GenericDeletedComic, GenericTapasticComic):
5543
    """Class to retrieve Chris Hallbeck comics."""
5544
    # Also on https://chrishallbeck.tumblr.com
5545
    # Also on http://minimumble.com
5546
    name = 'hallbeckmini-tapa'
5547
    long_name = 'Chris Hallback - Minimumble (from Tapastic)'
5548
    url = 'https://tapastic.com/series/Minimumble'
5549
    _categories = ('HALLBACK', )
5550
5551
5552
class ChrisHallbeckBiffTapa(GenericDeletedComic, GenericTapasticComic):
5553
    """Class to retrieve Chris Hallbeck comics."""
5554
    # Also on https://chrishallbeck.tumblr.com
5555
    # Also on http://thebookofbiff.com
5556
    name = 'hallbeckbiff-tapa'
5557
    long_name = 'Chris Hallback - The Book of Biff (from Tapastic)'
5558
    url = 'https://tapastic.com/series/Biff'
5559
    _categories = ('HALLBACK', )
5560
5561
5562
class RandoWisTapa(GenericTapasticComic):
5563
    """Class to retrieve RandoWis comics."""
5564
    # Also on https://randowis.com
5565
    name = 'randowis-tapa'
5566
    long_name = 'RandoWis (from Tapastic)'
5567
    url = 'https://tapastic.com/series/RandoWis'
5568
5569
5570
class PigeonGazetteTapa(GenericTapasticComic):
5571
    """Class to retrieve The Pigeon Gazette comics."""
5572
    # Also on http://thepigeongazette.tumblr.com
5573
    name = 'pigeon-tapa'
5574
    long_name = 'The Pigeon Gazette (from Tapastic)'
5575
    url = 'https://tapastic.com/series/The-Pigeon-Gazette'
5576
5577
5578
class TheOdd1sOutTapa(GenericTapasticComic):
5579
    """Class to retrieve The Odd 1s Out comics."""
5580
    # Also on http://theodd1sout.com
5581
    # Also on http://theodd1sout.tumblr.com
5582
    name = 'theodd-tapa'
5583
    long_name = 'The Odd 1s Out (from Tapastic)'
5584
    url = 'https://tapastic.com/series/Theodd1sout'
5585
5586
5587
class TheWorldIsFlatTapa(GenericTapasticComic):
5588
    """Class to retrieve The World Is Flat Comics."""
5589
    # Also on http://theworldisflatcomics.tumblr.com
5590
    name = 'flatworld-tapa'
5591
    long_name = 'The World Is Flat (from Tapastic)'
5592
    url = 'https://tapastic.com/series/The-World-is-Flat'
5593
5594
5595
class MisterAndMeTapa(GenericTapasticComic):
5596
    """Class to retrieve Mister & Me Comics."""
5597
    # Also on http://www.mister-and-me.com
5598
    # Also on http://www.gocomics.com/mister-and-me
5599
    name = 'mister-tapa'
5600
    long_name = 'Mister & Me (from Tapastic)'
5601
    url = 'https://tapastic.com/series/Mister-and-Me'
5602
5603
5604
class TalesOfAbsurdityTapa(GenericDeletedComic, GenericTapasticComic):
5605
    """Class to retrieve Tales Of Absurdity comics."""
5606
    # Also on http://talesofabsurdity.com
5607
    # Also on http://talesofabsurdity.tumblr.com
5608
    name = 'absurdity-tapa'
5609
    long_name = 'Tales of Absurdity (from Tapastic)'
5610
    url = 'http://tapastic.com/series/Tales-Of-Absurdity'
5611
    _categories = ('ABSURDITY', )
5612
5613
5614
class BFGFSTapa(GenericTapasticComic):
5615
    """Class to retrieve BFGFS comics."""
5616
    # Also on http://bfgfs.com
5617
    # Also on https://bfgfs.tumblr.com
5618
    name = 'bfgfs-tapa'
5619
    long_name = 'BFGFS (from Tapastic)'
5620
    url = 'https://tapastic.com/series/BFGFS'
5621
5622
5623
class DoodleForFoodTapa(GenericTapasticComic):
5624
    """Class to retrieve Doodle For Food comics."""
5625
    # Also on http://www.doodleforfood.com
5626
    name = 'doodle-tapa'
5627
    long_name = 'Doodle For Food (from Tapastic)'
5628
    url = 'https://tapastic.com/series/Doodle-for-Food'
5629
5630
5631
class MrLovensteinTapa(GenericTapasticComic):
5632
    """Class to retrieve Mr Lovenstein comics."""
5633
    # Also on  https://tapastic.com/series/MrLovenstein
5634
    name = 'mrlovenstein-tapa'
5635
    long_name = 'Mr. Lovenstein (from Tapastic)'
5636
    url = 'https://tapastic.com/series/MrLovenstein'
5637
5638
5639
class CassandraCalinTapa(GenericTapasticComic):
5640
    """Class to retrieve C. Cassandra comics."""
5641
    # Also on http://cassandracalin.com
5642
    # Also on http://c-cassandra.tumblr.com
5643
    name = 'cassandra-tapa'
5644
    long_name = 'Cassandra Calin (from Tapastic)'
5645
    url = 'https://tapastic.com/series/C-Cassandra-comics'
5646
5647
5648
class WafflesAndPancakes(GenericTapasticComic):
5649
    """Class to retrieve Waffles And Pancakes comics."""
5650
    # Also on http://wandpcomic.com
5651
    name = 'waffles'
5652
    long_name = 'Waffles And Pancakes'
5653
    url = 'https://tapastic.com/series/Waffles-and-Pancakes'
5654
5655
5656
class YesterdaysPopcornTapastic(GenericTapasticComic):
5657
    """Class to retrieve Yesterday's Popcorn comics."""
5658
    # Also on http://www.yesterdayspopcorn.com
5659
    # Also on http://yesterdayspopcorn.tumblr.com
5660
    name = 'popcorn-tapa'
5661
    long_name = 'Yesterday\'s Popcorn (from Tapastic)'
5662
    url = 'https://tapastic.com/series/Yesterdays-Popcorn'
5663
5664
5665
class OurSuperAdventureTapastic(GenericDeletedComic, GenericTapasticComic):
5666
    """Class to retrieve Our Super Adventure comics."""
5667
    # Also on http://www.oursuperadventure.com
5668
    # http://sarahssketchbook.tumblr.com
5669
    # http://sarahgraley.com
5670
    name = 'superadventure-tapastic'
5671
    long_name = 'Our Super Adventure (from Tapastic)'
5672
    url = 'https://tapastic.com/series/Our-Super-Adventure'
5673
5674
5675
class NamelessPCs(GenericTapasticComic):
5676
    """Class to retrieve Nameless PCs comics."""
5677
    # Also on http://namelesspcs.com
5678
    name = 'namelesspcs-tapa'
5679
    long_name = 'NamelessPCs (from Tapastic)'
5680
    url = 'https://tapastic.com/series/NamelessPC'
5681
5682
5683
class DownTheUpwardSpiralTapa(GenericTapasticComic):
5684
    """Class to retrieve Down The Upward Spiral comics."""
5685
    # Also on http://www.downtheupwardspiral.com
5686
    # Also on http://downtheupwardspiral.tumblr.com
5687
    name = 'spiral-tapa'
5688
    long_name = 'Down the Upward Spiral (from Tapastic)'
5689
    url = 'https://tapastic.com/series/Down-the-Upward-Spiral'
5690
5691
5692
class UbertoolTapa(GenericTapasticComic):
5693
    """Class to retrieve Ubertool comics."""
5694
    # Also on http://ubertoolcomic.com
5695
    # Also on https://ubertool.tumblr.com
5696
    name = 'ubertool-tapa'
5697
    long_name = 'Ubertool (from Tapastic)'
5698
    url = 'https://tapastic.com/series/ubertool'
5699
    _categories = ('UBERTOOL', )
5700
5701
5702
class BarteNerdsTapa(GenericDeletedComic, GenericTapasticComic):
5703
    """Class to retrieve BarteNerds comics."""
5704
    # Also on http://www.bartenerds.com
5705
    name = 'bartenerds-tapa'
5706
    long_name = 'BarteNerds (from Tapastic)'
5707
    url = 'https://tapastic.com/series/BarteNERDS'
5708
5709
5710
class SmallBlueYonderTapa(GenericTapasticComic):
5711
    """Class to retrieve Small Blue Yonder comics."""
5712
    # Also on http://www.smallblueyonder.com
5713
    name = 'smallblue-tapa'
5714
    long_name = 'Small Blue Yonder (from Tapastic)'
5715
    url = 'https://tapastic.com/series/Small-Blue-Yonder'
5716
5717
5718
class TizzyStitchBirdTapa(GenericTapasticComic):
5719
    """Class to retrieve Tizzy Stitch Bird comics."""
5720
    # Also on http://tizzystitchbird.com
5721
    # Also on http://tizzystitchbird.tumblr.com
5722
    # Also on http://www.webtoons.com/en/challenge/tizzy-stitchbird/list?title_no=50082
5723
    name = 'tizzy-tapa'
5724
    long_name = 'Tizzy Stitch Bird (from Tapastic)'
5725
    url = 'https://tapastic.com/series/TizzyStitchbird'
5726
5727
5728
class RockPaperCynicTapa(GenericTapasticComic):
5729
    """Class to retrieve RockPaperCynic comics."""
5730
    # Also on http://www.rockpapercynic.com
5731
    # Also on http://rockpapercynic.tumblr.com
5732
    name = 'rpc-tapa'
5733
    long_name = 'Rock Paper Cynic (from Tapastic)'
5734
    url = 'https://tapastic.com/series/rockpapercynic'
5735
5736
5737
class IsItCanonTapa(GenericTapasticComic):
5738
    """Class to retrieve Is It Canon comics."""
5739
    # Also on http://www.isitcanon.com
5740
    name = 'canon-tapa'
5741
    long_name = 'Is It Canon (from Tapastic)'
5742
    url = 'http://tapastic.com/series/isitcanon'
5743
5744
5745
class ItsTheTieTapa(GenericTapasticComic):
5746
    """Class to retrieve It's the tie comics."""
5747
    # Also on http://itsthetie.com
5748
    # Also on http://itsthetie.tumblr.com
5749
    name = 'tie-tapa'
5750
    long_name = "It's the tie (from Tapastic)"
5751
    url = "https://tapastic.com/series/itsthetie"
5752
    _categories = ('TIE', )
5753
5754
5755
class JamesOfNoTradesTapa(GenericTapasticComic):
5756
    """Class to retrieve JamesOfNoTrades comics."""
5757
    # Also on http://jamesofnotrades.com
5758
    # Also on http://www.webtoons.com/en/challenge/james-of-no-trades/list?title_no=43422
5759
    # Also on http://jamesfregan.tumblr.com
5760
    name = 'jamesofnotrades-tapa'
5761
    long_name = 'James Of No Trades (from Tapastic)'
5762
    url = 'https://tapas.io/series/James-of-No-Trades'
5763
    _categories = ('JAMESOFNOTRADES', )
5764
5765
5766
class MomentumTapa(GenericTapasticComic):
5767
    """Class to retrieve Momentum comics."""
5768
    # Also on http://www.momentumcomic.com
5769
    name = 'momentum-tapa'
5770
    long_name = 'Momentum (from Tapastic)'
5771
    url = 'https://tapastic.com/series/momentum'
5772
5773
5774
class InYourFaceCakeTapa(GenericTapasticComic):
5775
    """Class to retrieve In Your Face Cake comics."""
5776
    # Also on https://in-your-face-cake.tumblr.com
5777
    name = 'inyourfacecake-tapa'
5778
    long_name = 'In Your Face Cake (from Tapastic)'
5779
    url = 'https://tapas.io/series/In-Your-Face-Cake'
5780
    _categories = ('INYOURFACECAKE', )
5781
5782
5783
class CowardlyComicsTapa(GenericTapasticComic):
5784
    """Class to retrieve Cowardly Comics."""
5785
    # Also on http://cowardlycomics.tumblr.com
5786
    # Also on http://www.webtoons.com/en/challenge/cowardly-comics/list?title_no=65893
5787
    name = 'cowardly-tapa'
5788
    long_name = 'Cowardly Comics (from Tapastic)'
5789
    url = 'https://tapas.io/series/CowardlyComics'
5790
5791
5792
class Caw4hwTapa(GenericTapasticComic):
5793
    """Class to retrieve Caw4hw comics."""
5794
    # Also on https://caw4hw.tumblr.com
5795
    name = 'caw4hw-tapa'
5796
    long_name = 'Caw4hw (from Tapastic)'
5797
    url = 'https://tapas.io/series/CAW4HW'
5798
5799
5800
class DontBeDadTapa(GenericTapasticComic):
5801
    """Class to retrieve Don't Be Dad comics."""
5802
    # Also on https://dontbedad.com/
5803
    # Also on http://www.webtoons.com/en/challenge/dontbedad/list?title_no=123074
5804
    name = 'dontbedad-tapa'
5805
    long_name = "Don't Be Dad (from Tapastic)"
5806
    url = 'https://tapas.io/series/DontBeDad-Comics'
5807
5808
5809
class APleasantWasteOfTimeTapa(GenericTapasticComic):
5810
    """Class to retrieve A Pleasant Waste Of Time comics."""
5811
    # Also on https://artjcf.tumblr.com
5812
    name = 'pleasant-waste-tapa'
5813
    long_name = 'A Pleasant Waste Of Time (from Tapastic)'
5814
    url = 'https://tapas.io/series/A-Pleasant-'
5815
    _categories = ('WASTE', )
5816
5817
5818
class InfiniteImmortalBensTapa(GenericTapasticComic):
5819
    """Class to retrieve Infinite Immortal Bens comics."""
5820
    # Also on http://www.webtoons.com/en/challenge/infinite-immortal-bens/list?title_no=32847
5821
    # Also on https://infiniteimmortalbens.tumblr.com
5822
    url = 'https://tapas.io/series/Infinite-Immortal-Bens'
5823
    name = 'infiniteimmortal-tapa'
5824
    long_name = 'Infinite Immortal Bens (from Tapastic)'
5825
    _categories = ('INFINITEIMMORTAL', )
5826
5827
5828
class AbsurdoLapin(GenericNavigableComic):
5829
    """Class to retrieve Absurdo Lapin comics."""
5830
    name = 'absurdo'
5831
    long_name = 'Absurdo'
5832
    url = 'https://absurdo.lapin.org'
5833
    get_url_from_link = join_cls_url_to_href
5834
5835
    @classmethod
5836
    def get_nav(cls, soup):
5837
        """Get the navigation elements from soup object."""
5838
        cont = soup.find('div', id='content')
5839
        _, b2 = cont.find_all('div', class_='buttons')
5840
        # prev, first, last, next
5841
        return [li.find('a') for li in b2.find_all('li')]
5842
5843
    @classmethod
5844
    def get_first_comic_link(cls):
5845
        """Get link to first comics."""
5846
        return cls.get_nav(get_soup_at_url(cls.url))[1]
5847
5848
    @classmethod
5849
    def get_navi_link(cls, last_soup, next_):
5850
        """Get link to next or previous comic."""
5851
        return cls.get_nav(last_soup)[3 if next_ else 0]
5852
5853
    @classmethod
5854
    def get_comic_info(cls, soup, link):
5855
        """Get information about a particular comics."""
5856
        author = soup.find('meta', attrs={'name': 'author'})['content']
5857
        tags = soup.find('meta', attrs={'name': 'keywords'})['content']
5858
        title = soup.find('title').string
5859
        imgs = soup.find('div', id='content').find_all('img')
5860
        return {
5861
            'title': title,
5862
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
5863
            'tags': tags,
5864
            'author': author,
5865
        }
5866
5867
5868
def get_subclasses(klass):
5869
    """Gets the list of direct/indirect subclasses of a class"""
5870
    subclasses = klass.__subclasses__()
5871
    for derived in list(subclasses):
5872
        subclasses.extend(get_subclasses(derived))
5873
    return subclasses
5874
5875
5876
def remove_st_nd_rd_th_from_date(string):
5877
    """Function to transform 1st/2nd/3rd/4th in a parsable date format."""
5878
    # Hackish way to convert string with numeral "1st"/"2nd"/etc to date
5879
    return (string.replace('st', '')
5880
            .replace('nd', '')
5881
            .replace('rd', '')
5882
            .replace('th', '')
5883
            .replace('Augu', 'August'))
5884
5885
5886
def string_to_date(string, date_format, local=DEFAULT_LOCAL):
5887
    """Function to convert string to date object.
5888
    Wrapper around datetime.datetime.strptime."""
5889
    # format described in https://docs.python.org/2/library/datetime.html#strftime-and-strptime-behavior
5890
    prev_locale = locale.setlocale(locale.LC_ALL)
5891
    if local != prev_locale:
5892
        locale.setlocale(locale.LC_ALL, local)
5893
    ret = datetime.datetime.strptime(string, date_format).date()
5894
    if local != prev_locale:
5895
        locale.setlocale(locale.LC_ALL, prev_locale)
5896
    return ret
5897
5898
5899
COMICS = set(get_subclasses(GenericComic))
5900
VALID_COMICS = [c for c in COMICS if c.name is not None]
5901
COMIC_NAMES = {c.name: c for c in VALID_COMICS}
5902
assert len(VALID_COMICS) == len(COMIC_NAMES)
5903
CLASS_NAMES = {c.__name__ for c in VALID_COMICS}
5904
assert len(VALID_COMICS) == len(CLASS_NAMES)
5905