Completed
Push — master ( 6131c3...1b01a6 )
by De
35s
created

comics.py (47 issues)

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