Code Duplication    Length = 22-26 lines in 5 locations

comics.py 5 locations

@@ 911-936 (lines=26) @@
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
@@ 2274-2298 (lines=25) @@
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
@@ 341-363 (lines=23) @@
338
        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
@@ 367-388 (lines=22) @@
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
@@ 1801-1826 (lines=26) @@
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
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