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

Code Duplication Length = 21-27 lines in 18 locations

comics.py 18 locations


        }


class OneOneOneOneComic(GenericComicNotWorking, 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(GenericDeletedComic, 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],
        }


        }


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 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 Penmen(GenericComicNotWorking, GenericNavigableComic):
    """Class to retrieve Penmen comics."""
    name = 'penmen'

class GenericBoumerie(GenericNavigableComic):
    """Generic class to retrieve Boumeries comics in different languages."""
    # Also on http://boumeries.tumblr.com
    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 BoumerieEn(GenericBoumerie):
    """Class to retrieve Boumeries comics in English."""

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 PleasantThoughts(GenericNavigableComic):
    """Class to retrieve Pleasant Thoughts comics."""
    name = 'pleasant'

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
        }


class EveryDayBlues(GenericDeletedComic, GenericNavigableComic):
    """Class to retrieve EveryDayBlues Comics."""
    name = "blues"

class EveryDayBlues(GenericDeletedComic, 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, imgs
        return {
            'img': [i['src'] for i in imgs],
            'title': title,
            'author': author,
            'day': day.day,
            'month': day.month,
            'year': day.year
        }


class BiterComics(GenericNavigableComic):
    """Class to retrieve Biter Comics."""
    name = "biter"

class MouseBearComedy(GenericComicNotWorking):  # Website has changed
    """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,
        }


class BigFootJustice(GenericNavigableComic):
    """Class to retrieve Big Foot Justice comics."""
    # Also on http://tapastic.com/series/bigfoot-justice

    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 BiterComics(GenericNavigableComic):
    """Class to retrieve Biter Comics."""
    name = "biter"
    long_name = "Biter Comics"
    url = "http://www.bitercomics.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("h1", class_="entry-title").string
        author = soup.find("span", class_="author vcard").find("a").string
        date_str = soup.find("span", class_="entry-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'] for i in imgs)
        assert len(imgs) == 1, imgs
        alt = imgs[0]['alt']
        return {
            'img': [i['src'] for i in imgs],
            'title': title,
            'alt': alt,
            'author': author,
            '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

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 RockPaperScissors(GenericNavigableComic):
    """Class to retrieve Rock Paper Scissors comics."""
    name = 'rps'

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 LinsEditions(GenericDeletedComic):  # Permanently moved to warandpeas
    """Class to retrieve L.I.N.S. Editions comics."""
    # Also on https://linscomics.tumblr.com

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,
        }


class EarthExplodes(GenericNavigableComic):
    """Class to retrieve The Earth Explodes comics."""
    name = 'earthexplodes'

class Octopuns(GenericBlogspotComic):
    """Class to retrieve Octopuns comics."""
    # Also on http://octopuns.tumblr.com
    name = 'octopuns'
    long_name = 'Octopuns'
    url = 'http://www.octopuns.net'  # or http://octopuns.blogspot.fr/
    first_url = 'http://octopuns.blogspot.com/2010/12/17122010-always-read-label.html'

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


class GeekAndPoke(GenericNavigableComic):
    """Class to retrieve Geek And Poke comics."""
    name = 'geek'

class ManVersusManatee(GenericNavigableComic):
    """Class to retrieve Man Versus Manatee comics."""
    url = 'http://manvsmanatee.com'
    name = 'manvsmanatee'
    long_name = 'Man Versus Manatee'
    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
        imgs = soup.find('div', id='comic').find_all('img')
        date_str = soup.find('span', class_='post-date').string
        day = string_to_date(date_str, "%B %d, %Y")
        return {
            'img': [i['src'] for i in imgs],
            'title': title,
            'month': day.month,
            'year': day.year,
            'day': day.day,
        }


class TheMeerkatguy(GenericNavigableComic):
    """Class to retrieve The Meerkatguy comics."""
    long_name = 'The Meerkatguy'

class CompletelySeriousComics(GenericNavigableComic):
    """Class to retrieve Completely Serious comics."""
    name = 'completelyserious'
    long_name = 'Completely Serious Comics'
    url = 'http://completelyseriouscomics.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."""
        title = soup.find('h2', class_='post-title').string
        author = soup.find('span', class_='post-author').contents[1].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
        alt = imgs[0]['title']
        assert all(i['title'] == i['alt'] == alt for i in imgs)
        return {
            'month': day.month,
            'year': day.year,
            'day': day.day,
            'img': [i['src'] for i in imgs],
            'title': title,
            'alt': alt,
            'author': author,
        }


class PoorlyDrawnLines(GenericListableComic):
    """Class to retrieve Poorly Drawn Lines comics."""
    # Also on http://pdlcomics.tumblr.com

		@@ 720-743 (lines=24) @@
717		}
718
719
720		class OneOneOneOneComic(GenericComicNotWorking, GenericNavigableComic):
721		"""Class to retrieve 1111 Comics."""
722		# Also on http://comics1111.tumblr.com
723		# Also on https://tapastic.com/series/1111-Comics
724		name = '1111'
725		long_name = '1111 Comics'
726		url = 'http://www.1111comics.me'
727		_categories = ('ONEONEONEONE', )
728		get_first_comic_link = get_div_navfirst_a
729		get_navi_link = get_link_rel_next
730
731		@classmethod
732		def get_comic_info(cls, soup, link):
733		"""Get information about a particular comics."""
734		title = soup.find('h1', class_='comic-title').find('a').string
735		date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string
736		day = string_to_date(date_str, "%B %d, %Y")
737		imgs = soup.find_all('meta', property='og:image')
738		return {
739		'title': title,
740		'month': day.month,
741		'year': day.year,
742		'day': day.day,
743		'img': [i['content'] for i in imgs],
744		}
745
746
		@@ 948-970 (lines=23) @@
945		}
946
947
948		class TheGentlemanArmchair(GenericNavigableComic):
949		"""Class to retrieve The Gentleman Armchair comics."""
950		name = 'gentlemanarmchair'
951		long_name = 'The Gentleman Armchair'
952		url = 'http://thegentlemansarmchair.com'
953		get_first_comic_link = get_a_navi_navifirst
954		get_navi_link = get_link_rel_next
955
956		@classmethod
957		def get_comic_info(cls, soup, link):
958		"""Get information about a particular comics."""
959		title = soup.find('h2', class_='post-title').string
960		author = soup.find("span", class_="post-author").find("a").string
961		date_str = soup.find('span', class_='post-date').string
962		day = string_to_date(date_str, "%B %d, %Y")
963		imgs = soup.find('div', id='comic').find_all('img')
964		return {
965		'img': [i['src'] for i in imgs],
966		'title': title,
967		'author': author,
968		'month': day.month,
969		'year': day.year,
970		'day': day.day,
971		}
972
973
		@@ 747-768 (lines=22) @@
744		}
745
746
747		class AngryAtNothing(GenericDeletedComic, GenericNavigableComic):
748		"""Class to retrieve Angry at Nothing comics."""
749		# Also on http://tapastic.com/series/Comics-yeah-definitely-comics-
750		# Also on http://angryatnothing.tumblr.com
751		name = 'angry'
752		long_name = 'Angry At Nothing'
753		url = 'http://www.angryatnothing.net'
754		get_first_comic_link = get_div_navfirst_a
755		get_navi_link = get_a_rel_next
756
757		@classmethod
758		def get_comic_info(cls, soup, link):
759		"""Get information about a particular comics."""
760		title = soup.find('h1', class_='comic-title').find('a').string
761		date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string
762		day = string_to_date(date_str, "%B %d, %Y")
763		imgs = soup.find_all('meta', property='og:image')
764		return {
765		'title': title,
766		'month': day.month,
767		'year': day.year,
768		'day': day.day,
769		'img': [i['content'] for i in imgs],
770		}
771
		@@ 694-716 (lines=23) @@
691		}
692
693
694		class PenelopeBagieu(GenericNavigableComic):
695		"""Class to retrieve comics from Penelope Bagieu's blog."""
696		name = 'bagieu'
697		long_name = 'Ma vie est tout a fait fascinante (Bagieu)'
698		url = 'http://www.penelope-jolicoeur.com'
699		_categories = ('FRANCAIS', )
700		get_navi_link = get_link_rel_next
701		get_first_comic_link = simulate_first_link
702		first_url = 'http://www.penelope-jolicoeur.com/2007/02/ma-vie-mon-oeuv.html'
703
704		@classmethod
705		def get_comic_info(cls, soup, link):
706		"""Get information about a particular comics."""
707		date_str = soup.find('h2', class_='date-header').string
708		day = string_to_date(date_str, "%A %d %B %Y", "fr_FR.utf8")
709		imgs = soup.find('div', class_='entry-body').find_all('img')
710		title = soup.find('h3', class_='entry-header').string
711		return {
712		'title': title,
713		'img': [i['src'] for i in imgs],
714		'month': day.month,
715		'year': day.year,
716		'day': day.day,
717		}
718
719
		@@ 1908-1934 (lines=27) @@
1905		class PicturesInBoxes(GenericNavigableComic):
1906		"""Class to retrieve Pictures In Boxes comics."""
1907		# Also on https://picturesinboxescomic.tumblr.com
1908		name = 'picturesinboxes'
1909		long_name = 'Pictures in Boxes'
1910		url = 'http://www.picturesinboxes.com'
1911		get_navi_link = get_a_navi_navinext
1912		get_first_comic_link = simulate_first_link
1913		first_url = 'http://www.picturesinboxes.com/2013/10/26/tetris/'
1914
1915		@classmethod
1916		def get_comic_info(cls, soup, link):
1917		"""Get information about a particular comics."""
1918		title = soup.find('h2', class_='post-title').string
1919		author = soup.find("span", class_="post-author").find("a").string
1920		date_str = soup.find('span', class_='post-date').string
1921		day = string_to_date(date_str, '%B %d, %Y')
1922		imgs = soup.find('div', class_='comicpane').find_all('img')
1923		assert imgs
1924		assert all(i['title'] == i['alt'] == title for i in imgs)
1925		return {
1926		'day': day.day,
1927		'month': day.month,
1928		'year': day.year,
1929		'img': [i['src'] for i in imgs],
1930		'title': title,
1931		'author': author,
1932		}
1933
1934
1935		class Penmen(GenericComicNotWorking, GenericNavigableComic):
1936		"""Class to retrieve Penmen comics."""
1937		name = 'penmen'
		@@ 2895-2919 (lines=25) @@
2892		class GenericBoumerie(GenericNavigableComic):
2893		"""Generic class to retrieve Boumeries comics in different languages."""
2894		# Also on http://boumeries.tumblr.com
2895		get_first_comic_link = get_a_navi_navifirst
2896		get_navi_link = get_link_rel_next
2897		date_format = NotImplemented
2898		lang = NotImplemented
2899
2900		@classmethod
2901		def get_comic_info(cls, soup, link):
2902		"""Get information about a particular comics."""
2903		title = soup.find('h2', class_='post-title').string
2904		short_url = soup.find('link', rel='shortlink')['href']
2905		author = soup.find("span", class_="post-author").find("a").string
2906		date_str = soup.find('span', class_='post-date').string
2907		day = string_to_date(date_str, cls.date_format, cls.lang)
2908		imgs = soup.find('div', id='comic').find_all('img')
2909		assert all(i['alt'] == i['title'] for i in imgs)
2910		return {
2911		'short_url': short_url,
2912		'img': [i['src'] for i in imgs],
2913		'title': title,
2914		'author': author,
2915		'month': day.month,
2916		'year': day.year,
2917		'day': day.day,
2918		}
2919
2920
2921		class BoumerieEn(GenericBoumerie):
2922		"""Class to retrieve Boumeries comics in English."""
		@@ 2641-2666 (lines=26) @@
2638		class TheAwkwardYeti(GenericNavigableComic):
2639		"""Class to retrieve The Awkward Yeti comics."""
2640		# Also on http://www.gocomics.com/the-awkward-yeti
2641		# Also on http://larstheyeti.tumblr.com
2642		# Also on https://tapastic.com/series/TheAwkwardYeti
2643		name = 'yeti'
2644		long_name = 'The Awkward Yeti'
2645		url = 'http://theawkwardyeti.com'
2646		_categories = ('YETI', )
2647		get_first_comic_link = get_a_navi_navifirst
2648		get_navi_link = get_link_rel_next
2649
2650		@classmethod
2651		def get_comic_info(cls, soup, link):
2652		"""Get information about a particular comics."""
2653		title = soup.find('h2', class_='post-title').string
2654		date_str = soup.find("span", class_="post-date").string
2655		day = string_to_date(date_str, "%B %d, %Y")
2656		imgs = soup.find("div", id="comic").find_all("img")
2657		assert all(idx > 0 or i['alt'] == i['title'] for idx, i in enumerate(imgs))
2658		return {
2659		'img': [i['src'] for i in imgs],
2660		'title': title,
2661		'day': day.day,
2662		'month': day.month,
2663		'year': day.year
2664		}
2665
2666
2667		class PleasantThoughts(GenericNavigableComic):
2668		"""Class to retrieve Pleasant Thoughts comics."""
2669		name = 'pleasant'
		@@ 2554-2579 (lines=26) @@
2551		class GerbilWithAJetpack(GenericNavigableComic):
2552		"""Class to retrieve GerbilWithAJetpack comics."""
2553		name = 'gerbil'
2554		long_name = 'Gerbil With A Jetpack'
2555		url = 'http://gerbilwithajetpack.com'
2556		get_first_comic_link = get_a_navi_navifirst
2557		get_navi_link = get_a_rel_next
2558
2559		@classmethod
2560		def get_comic_info(cls, soup, link):
2561		"""Get information about a particular comics."""
2562		title = soup.find('h2', class_='post-title').string
2563		author = soup.find("span", class_="post-author").find("a").string
2564		date_str = soup.find("span", class_="post-date").string
2565		day = string_to_date(date_str, "%B %d, %Y")
2566		imgs = soup.find("div", id="comic").find_all("img")
2567		alt = imgs[0]['alt']
2568		assert all(i['alt'] == i['title'] == alt for i in imgs)
2569		return {
2570		'img': [i['src'] for i in imgs],
2571		'title': title,
2572		'alt': alt,
2573		'author': author,
2574		'day': day.day,
2575		'month': day.month,
2576		'year': day.year
2577		}
2578
2579
2580		class EveryDayBlues(GenericDeletedComic, GenericNavigableComic):
2581		"""Class to retrieve EveryDayBlues Comics."""
2582		name = "blues"
		@@ 2583-2607 (lines=25) @@
2580		class EveryDayBlues(GenericDeletedComic, GenericNavigableComic):
2581		"""Class to retrieve EveryDayBlues Comics."""
2582		name = "blues"
2583		long_name = "Every Day Blues"
2584		url = "http://everydayblues.net"
2585		get_first_comic_link = get_a_navi_navifirst
2586		get_navi_link = get_link_rel_next
2587
2588		@classmethod
2589		def get_comic_info(cls, soup, link):
2590		"""Get information about a particular comics."""
2591		title = soup.find("h2", class_="post-title").string
2592		author = soup.find("span", class_="post-author").find("a").string
2593		date_str = soup.find("span", class_="post-date").string
2594		day = string_to_date(date_str, "%d. %B %Y", "de_DE.utf8")
2595		imgs = soup.find("div", id="comic").find_all("img")
2596		assert all(i['alt'] == i['title'] == title for i in imgs)
2597		assert len(imgs) <= 1, imgs
2598		return {
2599		'img': [i['src'] for i in imgs],
2600		'title': title,
2601		'author': author,
2602		'day': day.day,
2603		'month': day.month,
2604		'year': day.year
2605		}
2606
2607
2608		class BiterComics(GenericNavigableComic):
2609		"""Class to retrieve Biter Comics."""
2610		name = "biter"
		@@ 1796-1820 (lines=25) @@
1793		class MouseBearComedy(GenericComicNotWorking): # Website has changed
1794		"""Class to retrieve Mouse Bear Comedy comics."""
1795		# Also on http://mousebearcomedy.tumblr.com
1796		name = 'mousebear'
1797		long_name = 'Mouse Bear Comedy'
1798		url = 'http://www.mousebearcomedy.com'
1799		get_first_comic_link = get_a_navi_navifirst
1800		get_navi_link = get_a_navi_comicnavnext_navinext
1801
1802		@classmethod
1803		def get_comic_info(cls, soup, link):
1804		"""Get information about a particular comics."""
1805		title = soup.find('h2', class_='post-title').string
1806		author = soup.find("span", class_="post-author").find("a").string
1807		date_str = soup.find("span", class_="post-date").string
1808		day = string_to_date(date_str, '%B %d, %Y')
1809		imgs = soup.find("div", id="comic").find_all("img")
1810		assert all(i['alt'] == i['title'] == title for i in imgs)
1811		return {
1812		'day': day.day,
1813		'month': day.month,
1814		'year': day.year,
1815		'img': [i['src'] for i in imgs],
1816		'title': title,
1817		'author': author,
1818		}
1819
1820
1821		class BigFootJustice(GenericNavigableComic):
1822		"""Class to retrieve Big Foot Justice comics."""
1823		# Also on http://tapastic.com/series/bigfoot-justice
		@@ 1206-1229 (lines=24) @@
1203		url = 'http://english.bouletcorp.com'
1204
1205
1206		class AmazingSuperPowers(GenericNavigableComic):
1207		"""Class to retrieve Amazing Super Powers comics."""
1208		name = 'asp'
1209		long_name = 'Amazing Super Powers'
1210		url = 'http://www.amazingsuperpowers.com'
1211		get_first_comic_link = get_a_navi_navifirst
1212		get_navi_link = get_a_navi_navinext
1213
1214		@classmethod
1215		def get_comic_info(cls, soup, link):
1216		"""Get information about a particular comics."""
1217		author = soup.find("span", class_="post-author").find("a").string
1218		date_str = soup.find('span', class_='post-date').string
1219		day = string_to_date(date_str, "%B %d, %Y")
1220		imgs = soup.find('div', id='comic').find_all('img')
1221		title = ' '.join(i['title'] for i in imgs)
1222		assert all(i['alt'] == i['title'] for i in imgs)
1223		return {
1224		'title': title,
1225		'author': author,
1226		'img': [img['src'] for img in imgs],
1227		'day': day.day,
1228		'month': day.month,
1229		'year': day.year
1230		}
1231
1232
		@@ 2611-2637 (lines=27) @@
2608		class BiterComics(GenericNavigableComic):
2609		"""Class to retrieve Biter Comics."""
2610		name = "biter"
2611		long_name = "Biter Comics"
2612		url = "http://www.bitercomics.com"
2613		get_first_comic_link = get_a_navi_navifirst
2614		get_navi_link = get_link_rel_next
2615
2616		@classmethod
2617		def get_comic_info(cls, soup, link):
2618		"""Get information about a particular comics."""
2619		title = soup.find("h1", class_="entry-title").string
2620		author = soup.find("span", class_="author vcard").find("a").string
2621		date_str = soup.find("span", class_="entry-date").string
2622		day = string_to_date(date_str, "%B %d, %Y")
2623		imgs = soup.find("div", id="comic").find_all("img")
2624		assert all(i['alt'] == i['title'] for i in imgs)
2625		assert len(imgs) == 1, imgs
2626		alt = imgs[0]['alt']
2627		return {
2628		'img': [i['src'] for i in imgs],
2629		'title': title,
2630		'alt': alt,
2631		'author': author,
2632		'day': day.day,
2633		'month': day.month,
2634		'year': day.year
2635		}
2636
2637
2638		class TheAwkwardYeti(GenericNavigableComic):
2639		"""Class to retrieve The Awkward Yeti comics."""
2640		# Also on http://www.gocomics.com/the-awkward-yeti
		@@ 2264-2289 (lines=26) @@
2261		class HappleTea(GenericNavigableComic):
2262		"""Class to retrieve Happle Tea Comics."""
2263		name = 'happletea'
2264		long_name = 'Happle Tea'
2265		url = 'http://www.happletea.com'
2266		get_first_comic_link = get_a_navi_navifirst
2267		get_navi_link = get_link_rel_next
2268
2269		@classmethod
2270		def get_comic_info(cls, soup, link):
2271		"""Get information about a particular comics."""
2272		imgs = soup.find('div', id='comic').find_all('img')
2273		post = soup.find('div', class_='post-content')
2274		title = post.find('h2', class_='post-title').string
2275		author = post.find('a', rel='author').string
2276		date_str = post.find('span', class_='post-date').string
2277		day = string_to_date(date_str, "%B %d, %Y")
2278		assert all(i['alt'] == i['title'] for i in imgs)
2279		return {
2280		'title': title,
2281		'img': [i['src'] for i in imgs],
2282		'alt': ''.join(i['alt'] for i in imgs),
2283		'month': day.month,
2284		'year': day.year,
2285		'day': day.day,
2286		'author': author,
2287		}
2288
2289
2290		class RockPaperScissors(GenericNavigableComic):
2291		"""Class to retrieve Rock Paper Scissors comics."""
2292		name = 'rps'
		@@ 2445-2469 (lines=25) @@
2442		class LonnieMillsap(GenericNavigableComic):
2443		"""Class to retrieve Lonnie Millsap's comics."""
2444		name = 'millsap'
2445		long_name = 'Lonnie Millsap'
2446		url = 'http://www.lonniemillsap.com'
2447		get_navi_link = get_link_rel_next
2448		get_first_comic_link = simulate_first_link
2449		first_url = 'http://www.lonniemillsap.com/?p=42'
2450
2451		@classmethod
2452		def get_comic_info(cls, soup, link):
2453		"""Get information about a particular comics."""
2454		title = soup.find('h2', class_='post-title').string
2455		post = soup.find('div', class_='post-content')
2456		author = post.find("span", class_="post-author").find("a").string
2457		date_str = post.find("span", class_="post-date").string
2458		day = string_to_date(date_str, "%B %d, %Y")
2459		imgs = post.find("div", class_="entry").find_all("img")
2460		return {
2461		'title': title,
2462		'author': author,
2463		'img': [i['src'] for i in imgs],
2464		'month': day.month,
2465		'year': day.year,
2466		'day': day.day,
2467		}
2468
2469
2470		class LinsEditions(GenericDeletedComic): # Permanently moved to warandpeas
2471		"""Class to retrieve L.I.N.S. Editions comics."""
2472		# Also on https://linscomics.tumblr.com
		@@ 3306-3329 (lines=24) @@
3303		class Ubertool(GenericNavigableComic):
3304		"""Class to retrieve Ubertool comics."""
3305		# Also on https://ubertool.tumblr.com
3306		# Also on https://tapastic.com/series/ubertool
3307		name = 'ubertool'
3308		long_name = 'Ubertool'
3309		url = 'http://ubertoolcomic.com'
3310		_categories = ('UBERTOOL', )
3311		get_first_comic_link = get_a_comicnavbase_comicnavfirst
3312		get_navi_link = get_a_comicnavbase_comicnavnext
3313
3314		@classmethod
3315		def get_comic_info(cls, soup, link):
3316		"""Get information about a particular comics."""
3317		title = soup.find('h2', class_='post-title').string
3318		date_str = soup.find('span', class_='post-date').string
3319		day = string_to_date(date_str, "%B %d, %Y")
3320		imgs = soup.find('div', id='comic').find_all('img')
3321		return {
3322		'img': [i['src'] for i in imgs],
3323		'title': title,
3324		'month': day.month,
3325		'year': day.year,
3326		'day': day.day,
3327		}
3328
3329
3330		class EarthExplodes(GenericNavigableComic):
3331		"""Class to retrieve The Earth Explodes comics."""
3332		name = 'earthexplodes'
		@@ 3607-3627 (lines=21) @@
3604		class Octopuns(GenericBlogspotComic):
3605		"""Class to retrieve Octopuns comics."""
3606		# Also on http://octopuns.tumblr.com
3607		name = 'octopuns'
3608		long_name = 'Octopuns'
3609		url = 'http://www.octopuns.net' # or http://octopuns.blogspot.fr/
3610		first_url = 'http://octopuns.blogspot.com/2010/12/17122010-always-read-label.html'
3611
3612		@classmethod
3613		def get_comic_info(cls, soup, link):
3614		"""Get information about a particular comics."""
3615		title = soup.find('h3', class_='post-title entry-title').string
3616		date_str = soup.find('h2', class_='date-header').string
3617		day = string_to_date(date_str, "%A, %B %d, %Y")
3618		imgs = soup.find_all('link', rel='image_src')
3619		return {
3620		'img': [i['href'] for i in imgs],
3621		'title': title,
3622		'day': day.day,
3623		'month': day.month,
3624		'year': day.year,
3625		}
3626
3627
3628		class GeekAndPoke(GenericNavigableComic):
3629		"""Class to retrieve Geek And Poke comics."""
3630		name = 'geek'
		@@ 3263-3283 (lines=21) @@
3260		class ManVersusManatee(GenericNavigableComic):
3261		"""Class to retrieve Man Versus Manatee comics."""
3262		url = 'http://manvsmanatee.com'
3263		name = 'manvsmanatee'
3264		long_name = 'Man Versus Manatee'
3265		get_first_comic_link = get_a_comicnavbase_comicnavfirst
3266		get_navi_link = get_a_comicnavbase_comicnavnext
3267
3268		@classmethod
3269		def get_comic_info(cls, soup, link):
3270		"""Get information about a particular comics."""
3271		title = soup.find('h2', class_='post-title').string
3272		imgs = soup.find('div', id='comic').find_all('img')
3273		date_str = soup.find('span', class_='post-date').string
3274		day = string_to_date(date_str, "%B %d, %Y")
3275		return {
3276		'img': [i['src'] for i in imgs],
3277		'title': title,
3278		'month': day.month,
3279		'year': day.year,
3280		'day': day.day,
3281		}
3282
3283
3284		class TheMeerkatguy(GenericNavigableComic):
3285		"""Class to retrieve The Meerkatguy comics."""
3286		long_name = 'The Meerkatguy'
		@@ 2053-2079 (lines=27) @@
2050		class CompletelySeriousComics(GenericNavigableComic):
2051		"""Class to retrieve Completely Serious comics."""
2052		name = 'completelyserious'
2053		long_name = 'Completely Serious Comics'
2054		url = 'http://completelyseriouscomics.com'
2055		get_first_comic_link = get_a_navi_navifirst
2056		get_navi_link = get_a_navi_navinext
2057
2058		@classmethod
2059		def get_comic_info(cls, soup, link):
2060		"""Get information about a particular comics."""
2061		title = soup.find('h2', class_='post-title').string
2062		author = soup.find('span', class_='post-author').contents[1].string
2063		date_str = soup.find('span', class_='post-date').string
2064		day = string_to_date(date_str, '%B %d, %Y')
2065		imgs = soup.find('div', class_='comicpane').find_all('img')
2066		assert imgs
2067		alt = imgs[0]['title']
2068		assert all(i['title'] == i['alt'] == alt for i in imgs)
2069		return {
2070		'month': day.month,
2071		'year': day.year,
2072		'day': day.day,
2073		'img': [i['src'] for i in imgs],
2074		'title': title,
2075		'alt': alt,
2076		'author': author,
2077		}
2078
2079
2080		class PoorlyDrawnLines(GenericListableComic):
2081		"""Class to retrieve Poorly Drawn Lines comics."""
2082		# Also on http://pdlcomics.tumblr.com

SylvainDe / ComicBookMaker

Code Duplication Length = 21-27 lines in 18 locations

comics.py 18 locations