Code Duplication    Length = 22-26 lines in 2 locations

comics.py 2 locations

@@ 958-983 (lines=26) @@
955
        }
956
957
958
class MyExtraLife(GenericNavigableComic):
959
    """Class to retrieve My Extra Life comics."""
960
    name = 'extralife'
961
    long_name = 'My Extra Life'
962
    url = 'http://www.myextralife.com'
963
    get_navi_link = get_link_rel_next
964
965
    @classmethod
966
    def get_first_comic_link(cls):
967
        """Get link to first comics."""
968
        return get_soup_at_url(cls.url).find('a', class_='comic_nav_link first_comic_link')
969
970
    @classmethod
971
    def get_comic_info(cls, soup, link):
972
        """Get information about a particular comics."""
973
        title = soup.find("h1", class_="comic_title").string
974
        date_str = soup.find("span", class_="comic_date").string
975
        day = string_to_date(date_str, "%B %d, %Y")
976
        imgs = soup.find_all("img", class_="comic")
977
        assert all(i['alt'] == i['title'] == title for i in imgs)
978
        return {
979
            'title': title,
980
            'img': [i['src'] for i in imgs if i["src"]],
981
            'day': day.day,
982
            'month': day.month,
983
            'year': day.year
984
        }
985
986
@@ 386-407 (lines=22) @@
383
        }
384
385
386
class GenericLeMondeBlog(GenericNavigableComic):
387
    """Generic class to retrieve comics from Le Monde blogs."""
388
    _categories = ('LEMONDE', 'FRANCAIS')
389
    get_navi_link = get_link_rel_next
390
    get_first_comic_link = simulate_first_link
391
    first_url = NotImplemented
392
393
    @classmethod
394
    def get_comic_info(cls, soup, link):
395
        """Get information about a particular comics."""
396
        url2 = soup.find('link', rel='shortlink')['href']
397
        title = soup.find('meta', property='og:title')['content']
398
        date_str = soup.find("span", class_="entry-date").string
399
        day = string_to_date(date_str, "%d %B %Y", "fr_FR.utf8")
400
        imgs = soup.find_all('meta', property='og:image')
401
        return {
402
            'title': title,
403
            'url2': url2,
404
            'img': [convert_iri_to_plain_ascii_uri(i['content']) for i in imgs],
405
            'month': day.month,
406
            'year': day.year,
407
            'day': day.day,
408
        }
409
410