Completed
Push — master ( d1cd46...f97202 )
by De
54s
created

comics.py (3 issues)

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