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

Code Duplication Length = 23-27 lines in 11 locations

comics.py 11 locations


        }


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(GenericNavigableComic):
    """Class to retrieve Angry at Nothing comics."""
    # Also on http://tapastic.com/series/Comics-yeah-definitely-comics-
    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],
        }


class NeDroid(GenericNavigableComic):

        }


class PicturesInBoxes(GenericNavigableComic):
    """Class to retrieve Pictures In Boxes comics."""
    # Also on http://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 ImogenQuest(GenericEmptyComic, GenericNavigableComic):
    """Class to retrieve Imogen Quest comics."""
    # Also on http://imoquest.tumblr.com
    name = 'imogen'
    long_name = 'Imogen Quest'
    url = 'http://imogenquest.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('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 all(i['alt'] == i['title'] for i in imgs)
        title2 = imgs[0]['title']
        return {
            'day': day.day,
            'month': day.month,
            'year': day.year,
            'img': [i['src'] for i in imgs],
            'title': title,
            'title2': title2,
            'author': author,
        }



        }


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(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 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(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],
        }



		@@ 896-918 (lines=23) @@
893		}
894
895
896		class TheGentlemanArmchair(GenericNavigableComic):
897		"""Class to retrieve The Gentleman Armchair comics."""
898		name = 'gentlemanarmchair'
899		long_name = 'The Gentleman Armchair'
900		url = 'http://thegentlemansarmchair.com'
901		get_first_comic_link = get_a_navi_navifirst
902		get_navi_link = get_link_rel_next
903
904		@classmethod
905		def get_comic_info(cls, soup, link):
906		"""Get information about a particular comics."""
907		title = soup.find('h2', class_='post-title').string
908		author = soup.find("span", class_="post-author").find("a").string
909		date_str = soup.find('span', class_='post-date').string
910		day = string_to_date(date_str, "%B %d, %Y")
911		imgs = soup.find('div', id='comic').find_all('img')
912		return {
913		'img': [i['src'] for i in imgs],
914		'title': title,
915		'author': author,
916		'month': day.month,
917		'year': day.year,
918		'day': day.day,
919		}
920
921
		@@ 696-718 (lines=23) @@
693		}
694
695
696		class AngryAtNothing(GenericNavigableComic):
697		"""Class to retrieve Angry at Nothing comics."""
698		# Also on http://tapastic.com/series/Comics-yeah-definitely-comics-
699		name = 'angry'
700		long_name = 'Angry At Nothing'
701		url = 'http://www.angryatnothing.net'
702		get_first_comic_link = get_div_navfirst_a
703		get_navi_link = get_a_rel_next
704
705		@classmethod
706		def get_comic_info(cls, soup, link):
707		"""Get information about a particular comics."""
708		title = soup.find('h1', class_='comic-title').find('a').string
709		date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string
710		day = string_to_date(date_str, "%B %d, %Y")
711		imgs = soup.find_all('meta', property='og:image')
712		return {
713		'title': title,
714		'month': day.month,
715		'year': day.year,
716		'day': day.day,
717		'img': [i['content'] for i in imgs],
718		}
719
720
721		class NeDroid(GenericNavigableComic):
		@@ 1862-1888 (lines=27) @@
1859		}
1860
1861
1862		class PicturesInBoxes(GenericNavigableComic):
1863		"""Class to retrieve Pictures In Boxes comics."""
1864		# Also on http://picturesinboxescomic.tumblr.com
1865		name = 'picturesinboxes'
1866		long_name = 'Pictures in Boxes'
1867		url = 'http://www.picturesinboxes.com'
1868		get_navi_link = get_a_navi_navinext
1869		get_first_comic_link = simulate_first_link
1870		first_url = 'http://www.picturesinboxes.com/2013/10/26/tetris/'
1871
1872		@classmethod
1873		def get_comic_info(cls, soup, link):
1874		"""Get information about a particular comics."""
1875		title = soup.find('h2', class_='post-title').string
1876		author = soup.find("span", class_="post-author").find("a").string
1877		date_str = soup.find('span', class_='post-date').string
1878		day = string_to_date(date_str, '%B %d, %Y')
1879		imgs = soup.find('div', class_='comicpane').find_all('img')
1880		assert imgs
1881		assert all(i['title'] == i['alt'] == title for i in imgs)
1882		return {
1883		'day': day.day,
1884		'month': day.month,
1885		'year': day.year,
1886		'img': [i['src'] for i in imgs],
1887		'title': title,
1888		'author': author,
1889		}
1890
1891
		@@ 922-948 (lines=27) @@
919		}
920
921
922		class ImogenQuest(GenericEmptyComic, GenericNavigableComic):
923		"""Class to retrieve Imogen Quest comics."""
924		# Also on http://imoquest.tumblr.com
925		name = 'imogen'
926		long_name = 'Imogen Quest'
927		url = 'http://imogenquest.net'
928		get_first_comic_link = get_div_navfirst_a
929		get_navi_link = get_a_rel_next
930
931		@classmethod
932		def get_comic_info(cls, soup, link):
933		"""Get information about a particular comics."""
934		title = soup.find('h2', class_='post-title').string
935		author = soup.find("span", class_="post-author").find("a").string
936		date_str = soup.find('span', class_='post-date').string
937		day = string_to_date(date_str, '%B %d, %Y')
938		imgs = soup.find('div', class_='comicpane').find_all('img')
939		assert all(i['alt'] == i['title'] for i in imgs)
940		title2 = imgs[0]['title']
941		return {
942		'day': day.day,
943		'month': day.month,
944		'year': day.year,
945		'img': [i['src'] for i in imgs],
946		'title': title,
947		'title2': title2,
948		'author': author,
949		}
950
951
		@@ 2511-2536 (lines=26) @@
2508		}
2509
2510
2511		class TheAwkwardYeti(GenericNavigableComic):
2512		"""Class to retrieve The Awkward Yeti comics."""
2513		# Also on http://www.gocomics.com/the-awkward-yeti
2514		# Also on http://larstheyeti.tumblr.com
2515		# Also on https://tapastic.com/series/TheAwkwardYeti
2516		name = 'yeti'
2517		long_name = 'The Awkward Yeti'
2518		url = 'http://theawkwardyeti.com'
2519		_categories = ('YETI', )
2520		get_first_comic_link = get_a_navi_navifirst
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		date_str = soup.find("span", class_="post-date").string
2528		day = string_to_date(date_str, "%B %d, %Y")
2529		imgs = soup.find("div", id="comic").find_all("img")
2530		assert all(idx > 0 or i['alt'] == i['title'] for idx, i in enumerate(imgs))
2531		return {
2532		'img': [i['src'] for i in imgs],
2533		'title': title,
2534		'day': day.day,
2535		'month': day.month,
2536		'year': day.year
2537		}
2538
2539
		@@ 2424-2449 (lines=26) @@
2421		}
2422
2423
2424		class GerbilWithAJetpack(GenericNavigableComic):
2425		"""Class to retrieve GerbilWithAJetpack comics."""
2426		name = 'gerbil'
2427		long_name = 'Gerbil With A Jetpack'
2428		url = 'http://gerbilwithajetpack.com'
2429		get_first_comic_link = get_a_navi_navifirst
2430		get_navi_link = get_a_rel_next
2431
2432		@classmethod
2433		def get_comic_info(cls, soup, link):
2434		"""Get information about a particular comics."""
2435		title = soup.find('h2', class_='post-title').string
2436		author = soup.find("span", class_="post-author").find("a").string
2437		date_str = soup.find("span", class_="post-date").string
2438		day = string_to_date(date_str, "%B %d, %Y")
2439		imgs = soup.find("div", id="comic").find_all("img")
2440		alt = imgs[0]['alt']
2441		assert all(i['alt'] == i['title'] == alt for i in imgs)
2442		return {
2443		'img': [i['src'] for i in imgs],
2444		'title': title,
2445		'alt': alt,
2446		'author': author,
2447		'day': day.day,
2448		'month': day.month,
2449		'year': day.year
2450		}
2451
2452
		@@ 2765-2789 (lines=25) @@
2762		first_url = 'http://www.commitstrip.com/en/2012/02/22/interview/'
2763
2764
2765		class GenericBoumerie(GenericNavigableComic):
2766		"""Generic class to retrieve Boumeries comics in different languages."""
2767		get_first_comic_link = get_a_navi_navifirst
2768		get_navi_link = get_link_rel_next
2769		date_format = NotImplemented
2770		lang = NotImplemented
2771
2772		@classmethod
2773		def get_comic_info(cls, soup, link):
2774		"""Get information about a particular comics."""
2775		title = soup.find('h2', class_='post-title').string
2776		short_url = soup.find('link', rel='shortlink')['href']
2777		author = soup.find("span", class_="post-author").find("a").string
2778		date_str = soup.find('span', class_='post-date').string
2779		day = string_to_date(date_str, cls.date_format, cls.lang)
2780		imgs = soup.find('div', id='comic').find_all('img')
2781		assert all(i['alt'] == i['title'] for i in imgs)
2782		return {
2783		'short_url': short_url,
2784		'img': [i['src'] for i in imgs],
2785		'title': title,
2786		'author': author,
2787		'month': day.month,
2788		'year': day.year,
2789		'day': day.day,
2790		}
2791
2792
		@@ 2453-2477 (lines=25) @@
2450		}
2451
2452
2453		class EveryDayBlues(GenericNavigableComic):
2454		"""Class to retrieve EveryDayBlues Comics."""
2455		name = "blues"
2456		long_name = "Every Day Blues"
2457		url = "http://everydayblues.net"
2458		get_first_comic_link = get_a_navi_navifirst
2459		get_navi_link = get_link_rel_next
2460
2461		@classmethod
2462		def get_comic_info(cls, soup, link):
2463		"""Get information about a particular comics."""
2464		title = soup.find("h2", class_="post-title").string
2465		author = soup.find("span", class_="post-author").find("a").string
2466		date_str = soup.find("span", class_="post-date").string
2467		day = string_to_date(date_str, "%d. %B %Y", "de_DE.utf8")
2468		imgs = soup.find("div", id="comic").find_all("img")
2469		assert all(i['alt'] == i['title'] == title for i in imgs)
2470		assert len(imgs) <= 1
2471		return {
2472		'img': [i['src'] for i in imgs],
2473		'title': title,
2474		'author': author,
2475		'day': day.day,
2476		'month': day.month,
2477		'year': day.year
2478		}
2479
2480
		@@ 1750-1774 (lines=25) @@
1747		}
1748
1749
1750		class MouseBearComedy(GenericNavigableComic):
1751		"""Class to retrieve Mouse Bear Comedy comics."""
1752		# Also on http://mousebearcomedy.tumblr.com
1753		name = 'mousebear'
1754		long_name = 'Mouse Bear Comedy'
1755		url = 'http://www.mousebearcomedy.com'
1756		get_first_comic_link = get_a_navi_navifirst
1757		get_navi_link = get_a_navi_comicnavnext_navinext
1758
1759		@classmethod
1760		def get_comic_info(cls, soup, link):
1761		"""Get information about a particular comics."""
1762		title = soup.find('h2', class_='post-title').string
1763		author = soup.find("span", class_="post-author").find("a").string
1764		date_str = soup.find("span", class_="post-date").string
1765		day = string_to_date(date_str, '%B %d, %Y')
1766		imgs = soup.find("div", id="comic").find_all("img")
1767		assert all(i['alt'] == i['title'] == title for i in imgs)
1768		return {
1769		'day': day.day,
1770		'month': day.month,
1771		'year': day.year,
1772		'img': [i['src'] for i in imgs],
1773		'title': title,
1774		'author': author,
1775		}
1776
1777
		@@ 1158-1181 (lines=24) @@
1155		url = 'http://english.bouletcorp.com'
1156
1157
1158		class AmazingSuperPowers(GenericNavigableComic):
1159		"""Class to retrieve Amazing Super Powers comics."""
1160		name = 'asp'
1161		long_name = 'Amazing Super Powers'
1162		url = 'http://www.amazingsuperpowers.com'
1163		get_first_comic_link = get_a_navi_navifirst
1164		get_navi_link = get_a_navi_navinext
1165
1166		@classmethod
1167		def get_comic_info(cls, soup, link):
1168		"""Get information about a particular comics."""
1169		author = soup.find("span", class_="post-author").find("a").string
1170		date_str = soup.find('span', class_='post-date').string
1171		day = string_to_date(date_str, "%B %d, %Y")
1172		imgs = soup.find('div', id='comic').find_all('img')
1173		title = ' '.join(i['title'] for i in imgs)
1174		assert all(i['alt'] == i['title'] for i in imgs)
1175		return {
1176		'title': title,
1177		'author': author,
1178		'img': [img['src'] for img in imgs],
1179		'day': day.day,
1180		'month': day.month,
1181		'year': day.year
1182		}
1183
1184
		@@ 669-692 (lines=24) @@
666		}
667
668
669		class OneOneOneOneComic(GenericNavigableComic):
670		"""Class to retrieve 1111 Comics."""
671		# Also on http://comics1111.tumblr.com
672		# Also on https://tapastic.com/series/1111-Comics
673		name = '1111'
674		long_name = '1111 Comics'
675		url = 'http://www.1111comics.me'
676		_categories = ('ONEONEONEONE', )
677		get_first_comic_link = get_div_navfirst_a
678		get_navi_link = get_link_rel_next
679
680		@classmethod
681		def get_comic_info(cls, soup, link):
682		"""Get information about a particular comics."""
683		title = soup.find('h1', class_='comic-title').find('a').string
684		date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string
685		day = string_to_date(date_str, "%B %d, %Y")
686		imgs = soup.find_all('meta', property='og:image')
687		return {
688		'title': title,
689		'month': day.month,
690		'year': day.year,
691		'day': day.day,
692		'img': [i['content'] for i in imgs],
693		}
694
695

SylvainDe / ComicBookMaker

Code Duplication Length = 23-27 lines in 11 locations

comics.py 11 locations