Code Duplication - SylvainDe/ComicBookMaker - Measure and Improve Code Quality continuously with Scrutinizer

Code Duplication Length = 21-27 lines in 15 locations

comics.py 15 locations


        }


class PicturesInBoxes(GenericNavigableComic):
    """Class to retrieve Pictures In Boxes comics."""
    # Also on https://picturesinboxescomic.tumblr.com
    name = 'picturesinboxes'
    long_name = 'Pictures in Boxes'
    url = 'http://www.picturesinboxes.com'
    get_navi_link = get_a_navi_navinext
    get_first_comic_link = simulate_first_link
    first_url = 'http://www.picturesinboxes.com/2013/10/26/tetris/'

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('h2', class_='post-title').string
        author = soup.find("span", class_="post-author").find("a").string
        date_str = soup.find('span', class_='post-date').string
        day = string_to_date(date_str, '%B %d, %Y')
        imgs = soup.find('div', class_='comicpane').find_all('img')
        assert imgs
        assert all(i['title'] == i['alt'] == title for i in imgs)
        return {
            'day': day.day,
            'month': day.month,
            'year': day.year,
            'img': [i['src'] for i in imgs],
            'title': title,
            'author': author,
        }



        }


class MouseBearComedy(GenericNavigableComic):
    """Class to retrieve Mouse Bear Comedy comics."""
    # Also on http://mousebearcomedy.tumblr.com
    name = 'mousebear'
    long_name = 'Mouse Bear Comedy'
    url = 'http://www.mousebearcomedy.com'
    get_first_comic_link = get_a_navi_navifirst
    get_navi_link = get_a_navi_comicnavnext_navinext

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('h2', class_='post-title').string
        author = soup.find("span", class_="post-author").find("a").string
        date_str = soup.find("span", class_="post-date").string
        day = string_to_date(date_str, '%B %d, %Y')
        imgs = soup.find("div", id="comic").find_all("img")
        assert all(i['alt'] == i['title'] == title for i in imgs)
        return {
            'day': day.day,
            'month': day.month,
            'year': day.year,
            'img': [i['src'] for i in imgs],
            'title': title,
            'author': author,
        }



    url = 'http://english.bouletcorp.com'


class AmazingSuperPowers(GenericNavigableComic):
    """Class to retrieve Amazing Super Powers comics."""
    name = 'asp'
    long_name = 'Amazing Super Powers'
    url = 'http://www.amazingsuperpowers.com'
    get_first_comic_link = get_a_navi_navifirst
    get_navi_link = get_a_navi_navinext

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        author = soup.find("span", class_="post-author").find("a").string
        date_str = soup.find('span', class_='post-date').string
        day = string_to_date(date_str, "%B %d, %Y")
        imgs = soup.find('div', id='comic').find_all('img')
        title = ' '.join(i['title'] for i in imgs)
        assert all(i['alt'] == i['title'] for i in imgs)
        return {
            'title': title,
            'author': author,
            'img': [img['src'] for img in imgs],
            'day': day.day,
            'month': day.month,
            'year': day.year
        }



        }


class OneOneOneOneComic(GenericEmptyComic, GenericNavigableComic):
    """Class to retrieve 1111 Comics."""
    # Also on http://comics1111.tumblr.com
    # Also on https://tapastic.com/series/1111-Comics
    name = '1111'
    long_name = '1111 Comics'
    url = 'http://www.1111comics.me'
    _categories = ('ONEONEONEONE', )
    get_first_comic_link = get_div_navfirst_a
    get_navi_link = get_link_rel_next

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('h1', class_='comic-title').find('a').string
        date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string
        day = string_to_date(date_str, "%B %d, %Y")
        imgs = soup.find_all('meta', property='og:image')
        return {
            'title': title,
            'month': day.month,
            'year': day.year,
            'day': day.day,
            'img': [i['content'] for i in imgs],
        }



        }


class TheGentlemanArmchair(GenericNavigableComic):
    """Class to retrieve The Gentleman Armchair comics."""
    name = 'gentlemanarmchair'
    long_name = 'The Gentleman Armchair'
    url = 'http://thegentlemansarmchair.com'
    get_first_comic_link = get_a_navi_navifirst
    get_navi_link = get_link_rel_next

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('h2', class_='post-title').string
        author = soup.find("span", class_="post-author").find("a").string
        date_str = soup.find('span', class_='post-date').string
        day = string_to_date(date_str, "%B %d, %Y")
        imgs = soup.find('div', id='comic').find_all('img')
        return {
            'img': [i['src'] for i in imgs],
            'title': title,
            'author': author,
            'month': day.month,
            'year': day.year,
            'day': day.day,
        }



        }


class AngryAtNothing(GenericEmptyComic, GenericNavigableComic):
    """Class to retrieve Angry at Nothing comics."""
    # Also on http://tapastic.com/series/Comics-yeah-definitely-comics-
    # Also on http://angryatnothing.tumblr.com
    name = 'angry'
    long_name = 'Angry At Nothing'
    url = 'http://www.angryatnothing.net'
    get_first_comic_link = get_div_navfirst_a
    get_navi_link = get_a_rel_next

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('h1', class_='comic-title').find('a').string
        date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string
        day = string_to_date(date_str, "%B %d, %Y")
        imgs = soup.find_all('meta', property='og:image')
        return {
            'title': title,
            'month': day.month,
            'year': day.year,
            'day': day.day,
            'img': [i['content'] for i in imgs],
        }


        return reversed(get_soup_at_url(archive_url).find('tbody').find_all('tr'))


class HappleTea(GenericNavigableComic):
    """Class to retrieve Happle Tea Comics."""
    name = 'happletea'
    long_name = 'Happle Tea'
    url = 'http://www.happletea.com'
    get_first_comic_link = get_a_navi_navifirst
    get_navi_link = get_link_rel_next

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        imgs = soup.find('div', id='comic').find_all('img')
        post = soup.find('div', class_='post-content')
        title = post.find('h2', class_='post-title').string
        author = post.find('a', rel='author').string
        date_str = post.find('span', class_='post-date').string
        day = string_to_date(date_str, "%B %d, %Y")
        assert all(i['alt'] == i['title'] for i in imgs)
        return {
            'title': title,
            'img': [i['src'] for i in imgs],
            'alt': ''.join(i['alt'] for i in imgs),
            'month': day.month,
            'year': day.year,
            'day': day.day,
            'author': author,
        }



        }


class PenelopeBagieu(GenericNavigableComic):
    """Class to retrieve comics from Penelope Bagieu's blog."""
    name = 'bagieu'
    long_name = 'Ma vie est tout a fait fascinante (Bagieu)'
    url = 'http://www.penelope-jolicoeur.com'
    _categories = ('FRANCAIS', )
    get_navi_link = get_link_rel_next
    get_first_comic_link = simulate_first_link
    first_url = 'http://www.penelope-jolicoeur.com/2007/02/ma-vie-mon-oeuv.html'

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        date_str = soup.find('h2', class_='date-header').string
        day = string_to_date(date_str, "%A %d %B %Y", "fr_FR.utf8")
        imgs = soup.find('div', class_='entry-body').find_all('img')
        title = soup.find('h3', class_='entry-header').string
        return {
            'title': title,
            'img': [i['src'] for i in imgs],
            'month': day.month,
            'year': day.year,
            'day': day.day,
        }



        }


class WarehouseComic(GenericNavigableComic):
    """Class to retrieve Warehouse Comic comics."""
    name = 'warehouse'
    long_name = 'Warehouse Comic'
    url = 'http://warehousecomic.com'
    get_first_comic_link = get_a_navi_navifirst
    get_navi_link = get_link_rel_next

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('h2', class_='post-title').string
        date_str = soup.find('span', class_='post-date').string
        day = string_to_date(date_str, "%B %d, %Y")
        imgs = soup.find('div', id='comic').find_all('img')
        return {
            'img': [i['src'] for i in imgs],
            'title': title,
            'day': day.day,
            'month': day.month,
            'year': day.year,
        }



        }


class TheAwkwardYeti(GenericNavigableComic):
    """Class to retrieve The Awkward Yeti comics."""
    # Also on http://www.gocomics.com/the-awkward-yeti
    # Also on http://larstheyeti.tumblr.com
    # Also on https://tapastic.com/series/TheAwkwardYeti
    name = 'yeti'
    long_name = 'The Awkward Yeti'
    url = 'http://theawkwardyeti.com'
    _categories = ('YETI', )
    get_first_comic_link = get_a_navi_navifirst
    get_navi_link = get_link_rel_next

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('h2', class_='post-title').string
        date_str = soup.find("span", class_="post-date").string
        day = string_to_date(date_str, "%B %d, %Y")
        imgs = soup.find("div", id="comic").find_all("img")
        assert all(idx > 0 or i['alt'] == i['title'] for idx, i in enumerate(imgs))
        return {
            'img': [i['src'] for i in imgs],
            'title': title,
            'day': day.day,
            'month': day.month,
            'year': day.year
        }



        }


class GerbilWithAJetpack(GenericNavigableComic):
    """Class to retrieve GerbilWithAJetpack comics."""
    name = 'gerbil'
    long_name = 'Gerbil With A Jetpack'
    url = 'http://gerbilwithajetpack.com'
    get_first_comic_link = get_a_navi_navifirst
    get_navi_link = get_a_rel_next

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('h2', class_='post-title').string
        author = soup.find("span", class_="post-author").find("a").string
        date_str = soup.find("span", class_="post-date").string
        day = string_to_date(date_str, "%B %d, %Y")
        imgs = soup.find("div", id="comic").find_all("img")
        alt = imgs[0]['alt']
        assert all(i['alt'] == i['title'] == alt for i in imgs)
        return {
            'img': [i['src'] for i in imgs],
            'title': title,
            'alt': alt,
            'author': author,
            'day': day.day,
            'month': day.month,
            'year': day.year
        }



    first_url = 'http://www.commitstrip.com/en/2012/02/22/interview/'


class GenericBoumerie(GenericNavigableComic):
    """Generic class to retrieve Boumeries comics in different languages."""
    get_first_comic_link = get_a_navi_navifirst
    get_navi_link = get_link_rel_next
    date_format = NotImplemented
    lang = NotImplemented

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('h2', class_='post-title').string
        short_url = soup.find('link', rel='shortlink')['href']
        author = soup.find("span", class_="post-author").find("a").string
        date_str = soup.find('span', class_='post-date').string
        day = string_to_date(date_str, cls.date_format, cls.lang)
        imgs = soup.find('div', id='comic').find_all('img')
        assert all(i['alt'] == i['title'] for i in imgs)
        return {
            'short_url': short_url,
            'img': [i['src'] for i in imgs],
            'title': title,
            'author': author,
            'month': day.month,
            'year': day.year,
            'day': day.day,
        }



        }


class EveryDayBlues(GenericEmptyComic, GenericNavigableComic):
    """Class to retrieve EveryDayBlues Comics."""
    name = "blues"
    long_name = "Every Day Blues"
    url = "http://everydayblues.net"
    get_first_comic_link = get_a_navi_navifirst
    get_navi_link = get_link_rel_next

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find("h2", class_="post-title").string
        author = soup.find("span", class_="post-author").find("a").string
        date_str = soup.find("span", class_="post-date").string
        day = string_to_date(date_str, "%d. %B %Y", "de_DE.utf8")
        imgs = soup.find("div", id="comic").find_all("img")
        assert all(i['alt'] == i['title'] == title for i in imgs)
        assert len(imgs) <= 1
        return {
            'img': [i['src'] for i in imgs],
            'title': title,
            'author': author,
            'day': day.day,
            'month': day.month,
            'year': day.year
        }



        }


class LonnieMillsap(GenericNavigableComic):
    """Class to retrieve Lonnie Millsap's comics."""
    name = 'millsap'
    long_name = 'Lonnie Millsap'
    url = 'http://www.lonniemillsap.com'
    get_navi_link = get_link_rel_next
    get_first_comic_link = simulate_first_link
    first_url = 'http://www.lonniemillsap.com/?p=42'

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('h2', class_='post-title').string
        post = soup.find('div', class_='post-content')
        author = post.find("span", class_="post-author").find("a").string
        date_str = post.find("span", class_="post-date").string
        day = string_to_date(date_str, "%B %d, %Y")
        imgs = post.find("div", class_="entry").find_all("img")
        return {
            'title': title,
            'author': author,
            'img': [i['src'] for i in imgs],
            'month': day.month,
            'year': day.year,
            'day': day.day,
        }



        }


class Ubertool(GenericNavigableComic):
    """Class to retrieve Ubertool comics."""
    # Also on https://ubertool.tumblr.com
    # Also on https://tapastic.com/series/ubertool
    name = 'ubertool'
    long_name = 'Ubertool'
    url = 'http://ubertoolcomic.com'
    _categories = ('UBERTOOL', )
    get_first_comic_link = get_a_comicnavbase_comicnavfirst
    get_navi_link = get_a_comicnavbase_comicnavnext

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('h2', class_='post-title').string
        date_str = soup.find('span', class_='post-date').string
        day = string_to_date(date_str, "%B %d, %Y")
        imgs = soup.find('div', id='comic').find_all('img')
        return {
            'img': [i['src'] for i in imgs],
            'title': title,
            'month': day.month,
            'year': day.year,
            'day': day.day,
        }



		@@ 1861-1887 (lines=27) @@
1858		}
1859
1860
1861		class PicturesInBoxes(GenericNavigableComic):
1862		"""Class to retrieve Pictures In Boxes comics."""
1863		# Also on https://picturesinboxescomic.tumblr.com
1864		name = 'picturesinboxes'
1865		long_name = 'Pictures in Boxes'
1866		url = 'http://www.picturesinboxes.com'
1867		get_navi_link = get_a_navi_navinext
1868		get_first_comic_link = simulate_first_link
1869		first_url = 'http://www.picturesinboxes.com/2013/10/26/tetris/'
1870
1871		@classmethod
1872		def get_comic_info(cls, soup, link):
1873		"""Get information about a particular comics."""
1874		title = soup.find('h2', class_='post-title').string
1875		author = soup.find("span", class_="post-author").find("a").string
1876		date_str = soup.find('span', class_='post-date').string
1877		day = string_to_date(date_str, '%B %d, %Y')
1878		imgs = soup.find('div', class_='comicpane').find_all('img')
1879		assert imgs
1880		assert all(i['title'] == i['alt'] == title for i in imgs)
1881		return {
1882		'day': day.day,
1883		'month': day.month,
1884		'year': day.year,
1885		'img': [i['src'] for i in imgs],
1886		'title': title,
1887		'author': author,
1888		}
1889
1890
		@@ 1749-1773 (lines=25) @@
1746		}
1747
1748
1749		class MouseBearComedy(GenericNavigableComic):
1750		"""Class to retrieve Mouse Bear Comedy comics."""
1751		# Also on http://mousebearcomedy.tumblr.com
1752		name = 'mousebear'
1753		long_name = 'Mouse Bear Comedy'
1754		url = 'http://www.mousebearcomedy.com'
1755		get_first_comic_link = get_a_navi_navifirst
1756		get_navi_link = get_a_navi_comicnavnext_navinext
1757
1758		@classmethod
1759		def get_comic_info(cls, soup, link):
1760		"""Get information about a particular comics."""
1761		title = soup.find('h2', class_='post-title').string
1762		author = soup.find("span", class_="post-author").find("a").string
1763		date_str = soup.find("span", class_="post-date").string
1764		day = string_to_date(date_str, '%B %d, %Y')
1765		imgs = soup.find("div", id="comic").find_all("img")
1766		assert all(i['alt'] == i['title'] == title for i in imgs)
1767		return {
1768		'day': day.day,
1769		'month': day.month,
1770		'year': day.year,
1771		'img': [i['src'] for i in imgs],
1772		'title': title,
1773		'author': author,
1774		}
1775
1776
		@@ 1157-1180 (lines=24) @@
1154		url = 'http://english.bouletcorp.com'
1155
1156
1157		class AmazingSuperPowers(GenericNavigableComic):
1158		"""Class to retrieve Amazing Super Powers comics."""
1159		name = 'asp'
1160		long_name = 'Amazing Super Powers'
1161		url = 'http://www.amazingsuperpowers.com'
1162		get_first_comic_link = get_a_navi_navifirst
1163		get_navi_link = get_a_navi_navinext
1164
1165		@classmethod
1166		def get_comic_info(cls, soup, link):
1167		"""Get information about a particular comics."""
1168		author = soup.find("span", class_="post-author").find("a").string
1169		date_str = soup.find('span', class_='post-date').string
1170		day = string_to_date(date_str, "%B %d, %Y")
1171		imgs = soup.find('div', id='comic').find_all('img')
1172		title = ' '.join(i['title'] for i in imgs)
1173		assert all(i['alt'] == i['title'] for i in imgs)
1174		return {
1175		'title': title,
1176		'author': author,
1177		'img': [img['src'] for img in imgs],
1178		'day': day.day,
1179		'month': day.month,
1180		'year': day.year
1181		}
1182
1183
		@@ 674-697 (lines=24) @@
671		}
672
673
674		class OneOneOneOneComic(GenericEmptyComic, GenericNavigableComic):
675		"""Class to retrieve 1111 Comics."""
676		# Also on http://comics1111.tumblr.com
677		# Also on https://tapastic.com/series/1111-Comics
678		name = '1111'
679		long_name = '1111 Comics'
680		url = 'http://www.1111comics.me'
681		_categories = ('ONEONEONEONE', )
682		get_first_comic_link = get_div_navfirst_a
683		get_navi_link = get_link_rel_next
684
685		@classmethod
686		def get_comic_info(cls, soup, link):
687		"""Get information about a particular comics."""
688		title = soup.find('h1', class_='comic-title').find('a').string
689		date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string
690		day = string_to_date(date_str, "%B %d, %Y")
691		imgs = soup.find_all('meta', property='og:image')
692		return {
693		'title': title,
694		'month': day.month,
695		'year': day.year,
696		'day': day.day,
697		'img': [i['content'] for i in imgs],
698		}
699
700
		@@ 902-924 (lines=23) @@
899		}
900
901
902		class TheGentlemanArmchair(GenericNavigableComic):
903		"""Class to retrieve The Gentleman Armchair comics."""
904		name = 'gentlemanarmchair'
905		long_name = 'The Gentleman Armchair'
906		url = 'http://thegentlemansarmchair.com'
907		get_first_comic_link = get_a_navi_navifirst
908		get_navi_link = get_link_rel_next
909
910		@classmethod
911		def get_comic_info(cls, soup, link):
912		"""Get information about a particular comics."""
913		title = soup.find('h2', class_='post-title').string
914		author = soup.find("span", class_="post-author").find("a").string
915		date_str = soup.find('span', class_='post-date').string
916		day = string_to_date(date_str, "%B %d, %Y")
917		imgs = soup.find('div', id='comic').find_all('img')
918		return {
919		'img': [i['src'] for i in imgs],
920		'title': title,
921		'author': author,
922		'month': day.month,
923		'year': day.year,
924		'day': day.day,
925		}
926
927
		@@ 701-722 (lines=22) @@
698		}
699
700
701		class AngryAtNothing(GenericEmptyComic, GenericNavigableComic):
702		"""Class to retrieve Angry at Nothing comics."""
703		# Also on http://tapastic.com/series/Comics-yeah-definitely-comics-
704		# Also on http://angryatnothing.tumblr.com
705		name = 'angry'
706		long_name = 'Angry At Nothing'
707		url = 'http://www.angryatnothing.net'
708		get_first_comic_link = get_div_navfirst_a
709		get_navi_link = get_a_rel_next
710
711		@classmethod
712		def get_comic_info(cls, soup, link):
713		"""Get information about a particular comics."""
714		title = soup.find('h1', class_='comic-title').find('a').string
715		date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string
716		day = string_to_date(date_str, "%B %d, %Y")
717		imgs = soup.find_all('meta', property='og:image')
718		return {
719		'title': title,
720		'month': day.month,
721		'year': day.year,
722		'day': day.day,
723		'img': [i['content'] for i in imgs],
724		}
725
		@@ 2218-2243 (lines=26) @@
2215		return reversed(get_soup_at_url(archive_url).find('tbody').find_all('tr'))
2216
2217
2218		class HappleTea(GenericNavigableComic):
2219		"""Class to retrieve Happle Tea Comics."""
2220		name = 'happletea'
2221		long_name = 'Happle Tea'
2222		url = 'http://www.happletea.com'
2223		get_first_comic_link = get_a_navi_navifirst
2224		get_navi_link = get_link_rel_next
2225
2226		@classmethod
2227		def get_comic_info(cls, soup, link):
2228		"""Get information about a particular comics."""
2229		imgs = soup.find('div', id='comic').find_all('img')
2230		post = soup.find('div', class_='post-content')
2231		title = post.find('h2', class_='post-title').string
2232		author = post.find('a', rel='author').string
2233		date_str = post.find('span', class_='post-date').string
2234		day = string_to_date(date_str, "%B %d, %Y")
2235		assert all(i['alt'] == i['title'] for i in imgs)
2236		return {
2237		'title': title,
2238		'img': [i['src'] for i in imgs],
2239		'alt': ''.join(i['alt'] for i in imgs),
2240		'month': day.month,
2241		'year': day.year,
2242		'day': day.day,
2243		'author': author,
2244		}
2245
2246
		@@ 648-670 (lines=23) @@
645		}
646
647
648		class PenelopeBagieu(GenericNavigableComic):
649		"""Class to retrieve comics from Penelope Bagieu's blog."""
650		name = 'bagieu'
651		long_name = 'Ma vie est tout a fait fascinante (Bagieu)'
652		url = 'http://www.penelope-jolicoeur.com'
653		_categories = ('FRANCAIS', )
654		get_navi_link = get_link_rel_next
655		get_first_comic_link = simulate_first_link
656		first_url = 'http://www.penelope-jolicoeur.com/2007/02/ma-vie-mon-oeuv.html'
657
658		@classmethod
659		def get_comic_info(cls, soup, link):
660		"""Get information about a particular comics."""
661		date_str = soup.find('h2', class_='date-header').string
662		day = string_to_date(date_str, "%A %d %B %Y", "fr_FR.utf8")
663		imgs = soup.find('div', class_='entry-body').find_all('img')
664		title = soup.find('h3', class_='entry-header').string
665		return {
666		'title': title,
667		'img': [i['src'] for i in imgs],
668		'month': day.month,
669		'year': day.year,
670		'day': day.day,
671		}
672
673
		@@ 1702-1722 (lines=21) @@
1699		}
1700
1701
1702		class WarehouseComic(GenericNavigableComic):
1703		"""Class to retrieve Warehouse Comic comics."""
1704		name = 'warehouse'
1705		long_name = 'Warehouse Comic'
1706		url = 'http://warehousecomic.com'
1707		get_first_comic_link = get_a_navi_navifirst
1708		get_navi_link = get_link_rel_next
1709
1710		@classmethod
1711		def get_comic_info(cls, soup, link):
1712		"""Get information about a particular comics."""
1713		title = soup.find('h2', class_='post-title').string
1714		date_str = soup.find('span', class_='post-date').string
1715		day = string_to_date(date_str, "%B %d, %Y")
1716		imgs = soup.find('div', id='comic').find_all('img')
1717		return {
1718		'img': [i['src'] for i in imgs],
1719		'title': title,
1720		'day': day.day,
1721		'month': day.month,
1722		'year': day.year,
1723		}
1724
1725
		@@ 2562-2587 (lines=26) @@
2559		}
2560
2561
2562		class TheAwkwardYeti(GenericNavigableComic):
2563		"""Class to retrieve The Awkward Yeti comics."""
2564		# Also on http://www.gocomics.com/the-awkward-yeti
2565		# Also on http://larstheyeti.tumblr.com
2566		# Also on https://tapastic.com/series/TheAwkwardYeti
2567		name = 'yeti'
2568		long_name = 'The Awkward Yeti'
2569		url = 'http://theawkwardyeti.com'
2570		_categories = ('YETI', )
2571		get_first_comic_link = get_a_navi_navifirst
2572		get_navi_link = get_link_rel_next
2573
2574		@classmethod
2575		def get_comic_info(cls, soup, link):
2576		"""Get information about a particular comics."""
2577		title = soup.find('h2', class_='post-title').string
2578		date_str = soup.find("span", class_="post-date").string
2579		day = string_to_date(date_str, "%B %d, %Y")
2580		imgs = soup.find("div", id="comic").find_all("img")
2581		assert all(idx > 0 or i['alt'] == i['title'] for idx, i in enumerate(imgs))
2582		return {
2583		'img': [i['src'] for i in imgs],
2584		'title': title,
2585		'day': day.day,
2586		'month': day.month,
2587		'year': day.year
2588		}
2589
2590
		@@ 2475-2500 (lines=26) @@
2472		}
2473
2474
2475		class GerbilWithAJetpack(GenericNavigableComic):
2476		"""Class to retrieve GerbilWithAJetpack comics."""
2477		name = 'gerbil'
2478		long_name = 'Gerbil With A Jetpack'
2479		url = 'http://gerbilwithajetpack.com'
2480		get_first_comic_link = get_a_navi_navifirst
2481		get_navi_link = get_a_rel_next
2482
2483		@classmethod
2484		def get_comic_info(cls, soup, link):
2485		"""Get information about a particular comics."""
2486		title = soup.find('h2', class_='post-title').string
2487		author = soup.find("span", class_="post-author").find("a").string
2488		date_str = soup.find("span", class_="post-date").string
2489		day = string_to_date(date_str, "%B %d, %Y")
2490		imgs = soup.find("div", id="comic").find_all("img")
2491		alt = imgs[0]['alt']
2492		assert all(i['alt'] == i['title'] == alt for i in imgs)
2493		return {
2494		'img': [i['src'] for i in imgs],
2495		'title': title,
2496		'alt': alt,
2497		'author': author,
2498		'day': day.day,
2499		'month': day.month,
2500		'year': day.year
2501		}
2502
2503
		@@ 2816-2840 (lines=25) @@
2813		first_url = 'http://www.commitstrip.com/en/2012/02/22/interview/'
2814
2815
2816		class GenericBoumerie(GenericNavigableComic):
2817		"""Generic class to retrieve Boumeries comics in different languages."""
2818		get_first_comic_link = get_a_navi_navifirst
2819		get_navi_link = get_link_rel_next
2820		date_format = NotImplemented
2821		lang = NotImplemented
2822
2823		@classmethod
2824		def get_comic_info(cls, soup, link):
2825		"""Get information about a particular comics."""
2826		title = soup.find('h2', class_='post-title').string
2827		short_url = soup.find('link', rel='shortlink')['href']
2828		author = soup.find("span", class_="post-author").find("a").string
2829		date_str = soup.find('span', class_='post-date').string
2830		day = string_to_date(date_str, cls.date_format, cls.lang)
2831		imgs = soup.find('div', id='comic').find_all('img')
2832		assert all(i['alt'] == i['title'] for i in imgs)
2833		return {
2834		'short_url': short_url,
2835		'img': [i['src'] for i in imgs],
2836		'title': title,
2837		'author': author,
2838		'month': day.month,
2839		'year': day.year,
2840		'day': day.day,
2841		}
2842
2843
		@@ 2504-2528 (lines=25) @@
2501		}
2502
2503
2504		class EveryDayBlues(GenericEmptyComic, GenericNavigableComic):
2505		"""Class to retrieve EveryDayBlues Comics."""
2506		name = "blues"
2507		long_name = "Every Day Blues"
2508		url = "http://everydayblues.net"
2509		get_first_comic_link = get_a_navi_navifirst
2510		get_navi_link = get_link_rel_next
2511
2512		@classmethod
2513		def get_comic_info(cls, soup, link):
2514		"""Get information about a particular comics."""
2515		title = soup.find("h2", class_="post-title").string
2516		author = soup.find("span", class_="post-author").find("a").string
2517		date_str = soup.find("span", class_="post-date").string
2518		day = string_to_date(date_str, "%d. %B %Y", "de_DE.utf8")
2519		imgs = soup.find("div", id="comic").find_all("img")
2520		assert all(i['alt'] == i['title'] == title for i in imgs)
2521		assert len(imgs) <= 1
2522		return {
2523		'img': [i['src'] for i in imgs],
2524		'title': title,
2525		'author': author,
2526		'day': day.day,
2527		'month': day.month,
2528		'year': day.year
2529		}
2530
2531
		@@ 2374-2398 (lines=25) @@
2371		}
2372
2373
2374		class LonnieMillsap(GenericNavigableComic):
2375		"""Class to retrieve Lonnie Millsap's comics."""
2376		name = 'millsap'
2377		long_name = 'Lonnie Millsap'
2378		url = 'http://www.lonniemillsap.com'
2379		get_navi_link = get_link_rel_next
2380		get_first_comic_link = simulate_first_link
2381		first_url = 'http://www.lonniemillsap.com/?p=42'
2382
2383		@classmethod
2384		def get_comic_info(cls, soup, link):
2385		"""Get information about a particular comics."""
2386		title = soup.find('h2', class_='post-title').string
2387		post = soup.find('div', class_='post-content')
2388		author = post.find("span", class_="post-author").find("a").string
2389		date_str = post.find("span", class_="post-date").string
2390		day = string_to_date(date_str, "%B %d, %Y")
2391		imgs = post.find("div", class_="entry").find_all("img")
2392		return {
2393		'title': title,
2394		'author': author,
2395		'img': [i['src'] for i in imgs],
2396		'month': day.month,
2397		'year': day.year,
2398		'day': day.day,
2399		}
2400
2401
		@@ 3215-3238 (lines=24) @@
3212		}
3213
3214
3215		class Ubertool(GenericNavigableComic):
3216		"""Class to retrieve Ubertool comics."""
3217		# Also on https://ubertool.tumblr.com
3218		# Also on https://tapastic.com/series/ubertool
3219		name = 'ubertool'
3220		long_name = 'Ubertool'
3221		url = 'http://ubertoolcomic.com'
3222		_categories = ('UBERTOOL', )
3223		get_first_comic_link = get_a_comicnavbase_comicnavfirst
3224		get_navi_link = get_a_comicnavbase_comicnavnext
3225
3226		@classmethod
3227		def get_comic_info(cls, soup, link):
3228		"""Get information about a particular comics."""
3229		title = soup.find('h2', class_='post-title').string
3230		date_str = soup.find('span', class_='post-date').string
3231		day = string_to_date(date_str, "%B %d, %Y")
3232		imgs = soup.find('div', id='comic').find_all('img')
3233		return {
3234		'img': [i['src'] for i in imgs],
3235		'title': title,
3236		'month': day.month,
3237		'year': day.year,
3238		'day': day.day,
3239		}
3240
3241

SylvainDe / ComicBookMaker

Code Duplication Length = 21-27 lines in 15 locations

comics.py 15 locations