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'

        desc = soup.find('meta', property='og:description')['content']
        title = soup.find('meta', property='og:title')['content']
        imgs = soup.find('div', class_='entry-content').find_all('img')
        title2 = ' '.join(i.get('title', '') for i in imgs)
        return {
            'title': title,
            'title2': title2,
            'description': desc,
            'img': [urljoin_wrapper(cls.url, convert_iri_to_plain_ascii_uri(i['src'])) for i in imgs],
        }


class CommitStripFr(GenericCommitStrip):
    """Class to retrieve Commit Strips in French."""
    name = 'commit_fr'
    long_name = 'Commit Strip (Fr)'
    url = 'http://www.commitstrip.com/fr'
    _categories = ('FRANCAIS', )
    first_url = 'http://www.commitstrip.com/fr/2012/02/22/interview/'


class CommitStripEn(GenericCommitStrip):
    """Class to retrieve Commit Strips in English."""
    name = 'commit_en'
    long_name = 'Commit Strip (En)'
    url = 'http://www.commitstrip.com/en'
    first_url = 'http://www.commitstrip.com/en/2012/02/22/interview/'


class GenericBoumerie(GenericNavigableComic):
    """Generic class to retrieve Boumeries comics in different languages."""

    """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

        """Get link to next or previous comic."""
        for link in last_soup.find_all('a', rel='next' if next_ else 'prev'):
            if link['href'] != '/comic':
                return link
        return None

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('meta', attrs={'name': 'description'})["content"]
        description = soup.find('div', itemprop='articleBody').text
        author = soup.find('span', itemprop='author copyrightHolder').string
        imgs = soup.find_all('img', itemprop='image')
        assert all(i['title'] == i['alt'] for i in imgs)
        alt = imgs[0]['alt'] if imgs else ""
        date_str = soup.find('time', itemprop='datePublished')["datetime"]
        day = string_to_date(date_str, "%Y-%m-%d %H:%M:%S")
        return {
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
            'month': day.month,
            'year': day.year,
            'day': day.day,
            'author': author,
            'title': title,
            'alt': alt,
            'description': description,
        }


class GerbilWithAJetpack(GenericNavigableComic):
    """Class to retrieve GerbilWithAJetpack comics."""
    name = 'gerbil'

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."""

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 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"
    long_name = "Biter Comics"

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'

    def get_url_from_archive_element(cls, tr):
        """Get url corresponding to an archive element."""
        _, td_comic, td_date, _ = tr.find_all('td')
        link = td_comic.find('a')
        return urljoin_wrapper(cls.url, link['href'])

    @classmethod
    def get_comic_info(cls, soup, tr):
        """Get information about a particular comics."""
        td_num, td_comic, td_date, _ = tr.find_all('td')
        num = int(td_num.string)
        link = td_comic.find('a')
        title = link.string
        imgs = soup.find_all('img', id='comic_image')
        date_str = td_date.string
        day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y, %I:%M %p")
        assert len(imgs) == 1, imgs
        assert all(i.get('alt') == i.get('title') for i in imgs)
        return {
            'num': num,
            'title': title,
            'alt': imgs[0].get('alt', ''),
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
            'month': day.month,
            'year': day.year,
            'day': day.day,
        }


class LonnieMillsap(GenericNavigableComic):
    """Class to retrieve Lonnie Millsap's comics."""

        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'
    url = 'http://www.themeerkatguy.com'
    name = 'meerkatguy'
    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('title').string
        imgs = soup.find_all('meta', property='og:image')
        return {
            'img': [i['content'] for i in imgs],
            'title': title,
        }


class Ubertool(GenericNavigableComic):

    _categories = ('BLOGSPOT', )

    @classmethod
    def get_navi_link(cls, last_soup, next_):
        """Get link to next or previous comic."""
        return last_soup.find('a', id='Blog1_blog-pager-newer-link' if next_ else 'Blog1_blog-pager-older-link')


class TuMourrasMoinsBete(GenericBlogspotComic):
    """Class to retrieve Tu Mourras Moins Bete comics."""
    name = 'mourrasmoinsbete'
    long_name = 'Tu Mourras Moins Bete'
    url = 'http://tumourrasmoinsbete.blogspot.fr'
    _categories = ('FRANCAIS', )
    first_url = 'http://tumourrasmoinsbete.blogspot.fr/2008/06/essai.html'

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('title').string
        imgs = soup.find('div', itemprop='description articleBody').find_all('img')
        author = soup.find('span', itemprop='author').string
        return {
            'img': [i['src'] for i in imgs],
            'author': author,
            'title': title,
        }

    long_name = 'Sheldon Comics'
    url = 'http://www.sheldoncomics.com'

    @classmethod
    def get_first_comic_link(cls):
        """Get link to first comics."""
        return get_soup_at_url(cls.url).find("a", id="nav-first")

    @classmethod
    def get_navi_link(cls, last_soup, next_):
        """Get link to next or previous comic."""
        for link in last_soup.find_all("a", id="nav-next" if next_ else "nav-prev"):
            if link['href'] != 'http://www.sheldoncomics.com':
                return link
        return None

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        imgs = soup.find("div", id="comic-foot").find_all("img")
        assert all(i['alt'] == i['title'] for i in imgs)
        assert len(imgs) == 1, imgs
        title = imgs[0]['title']
        return {
            'title': title,
            'img': [i['src'] for i in imgs],
        }

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		desc = soup.find('meta', property='og:description')['content']
2893		title = soup.find('meta', property='og:title')['content']
2894		imgs = soup.find('div', class_='entry-content').find_all('img')
2895		title2 = ' '.join(i.get('title', '') for i in imgs)
2896		return {
2897		'title': title,
2898		'title2': title2,
2899		'description': desc,
2900		'img': [urljoin_wrapper(cls.url, convert_iri_to_plain_ascii_uri(i['src'])) for i in imgs],
2901		}
2902
2903
2904		class CommitStripFr(GenericCommitStrip):
2905		"""Class to retrieve Commit Strips in French."""
2906		name = 'commit_fr'
2907		long_name = 'Commit Strip (Fr)'
2908		url = 'http://www.commitstrip.com/fr'
2909		_categories = ('FRANCAIS', )
2910		first_url = 'http://www.commitstrip.com/fr/2012/02/22/interview/'
2911
2912
2913		class CommitStripEn(GenericCommitStrip):
2914		"""Class to retrieve Commit Strips in English."""
2915		name = 'commit_en'
2916		long_name = 'Commit Strip (En)'
2917		url = 'http://www.commitstrip.com/en'
2918		first_url = 'http://www.commitstrip.com/en/2012/02/22/interview/'
2919
2920
2921		class GenericBoumerie(GenericNavigableComic):
2922		"""Generic class to retrieve Boumeries comics in different languages."""
		@@ 2641-2666 (lines=26) @@
2638		"""Class to retrieve Biter Comics."""
2639		name = "biter"
2640		long_name = "Biter Comics"
2641		url = "http://www.bitercomics.com"
2642		get_first_comic_link = get_a_navi_navifirst
2643		get_navi_link = get_link_rel_next
2644
2645		@classmethod
2646		def get_comic_info(cls, soup, link):
2647		"""Get information about a particular comics."""
2648		title = soup.find("h1", class_="entry-title").string
2649		author = soup.find("span", class_="author vcard").find("a").string
2650		date_str = soup.find("span", class_="entry-date").string
2651		day = string_to_date(date_str, "%B %d, %Y")
2652		imgs = soup.find("div", id="comic").find_all("img")
2653		assert all(i['alt'] == i['title'] for i in imgs)
2654		assert len(imgs) == 1, imgs
2655		alt = imgs[0]['alt']
2656		return {
2657		'img': [i['src'] for i in imgs],
2658		'title': title,
2659		'alt': alt,
2660		'author': author,
2661		'day': day.day,
2662		'month': day.month,
2663		'year': day.year
2664		}
2665
2666
2667		class TheAwkwardYeti(GenericNavigableComic):
2668		"""Class to retrieve The Awkward Yeti comics."""
2669		# Also on http://www.gocomics.com/the-awkward-yeti
		@@ 2554-2579 (lines=26) @@
2551		"""Get link to next or previous comic."""
2552		for link in last_soup.find_all('a', rel='next' if next_ else 'prev'):
2553		if link['href'] != '/comic':
2554		return link
2555		return None
2556
2557		@classmethod
2558		def get_comic_info(cls, soup, link):
2559		"""Get information about a particular comics."""
2560		title = soup.find('meta', attrs={'name': 'description'})["content"]
2561		description = soup.find('div', itemprop='articleBody').text
2562		author = soup.find('span', itemprop='author copyrightHolder').string
2563		imgs = soup.find_all('img', itemprop='image')
2564		assert all(i['title'] == i['alt'] for i in imgs)
2565		alt = imgs[0]['alt'] if imgs else ""
2566		date_str = soup.find('time', itemprop='datePublished')["datetime"]
2567		day = string_to_date(date_str, "%Y-%m-%d %H:%M:%S")
2568		return {
2569		'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
2570		'month': day.month,
2571		'year': day.year,
2572		'day': day.day,
2573		'author': author,
2574		'title': title,
2575		'alt': alt,
2576		'description': description,
2577		}
2578
2579
2580		class GerbilWithAJetpack(GenericNavigableComic):
2581		"""Class to retrieve GerbilWithAJetpack comics."""
2582		name = 'gerbil'
		@@ 2583-2607 (lines=25) @@
2580		class GerbilWithAJetpack(GenericNavigableComic):
2581		"""Class to retrieve GerbilWithAJetpack comics."""
2582		name = 'gerbil'
2583		long_name = 'Gerbil With A Jetpack'
2584		url = 'http://gerbilwithajetpack.com'
2585		get_first_comic_link = get_a_navi_navifirst
2586		get_navi_link = get_a_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, "%B %d, %Y")
2595		imgs = soup.find("div", id="comic").find_all("img")
2596		alt = imgs[0]['alt']
2597		assert all(i['alt'] == i['title'] == alt for i in imgs)
2598		return {
2599		'img': [i['src'] for i in imgs],
2600		'title': title,
2601		'alt': alt,
2602		'author': author,
2603		'day': day.day,
2604		'month': day.month,
2605		'year': day.year
2606		}
2607
2608
2609		class EveryDayBlues(GenericDeletedComic, GenericNavigableComic):
2610		"""Class to retrieve EveryDayBlues Comics."""
		@@ 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
2609		class EveryDayBlues(GenericDeletedComic, GenericNavigableComic):
2610		"""Class to retrieve EveryDayBlues Comics."""
2611		name = "blues"
2612		long_name = "Every Day Blues"
2613		url = "http://everydayblues.net"
2614		get_first_comic_link = get_a_navi_navifirst
2615		get_navi_link = get_link_rel_next
2616
2617		@classmethod
2618		def get_comic_info(cls, soup, link):
2619		"""Get information about a particular comics."""
2620		title = soup.find("h2", class_="post-title").string
2621		author = soup.find("span", class_="post-author").find("a").string
2622		date_str = soup.find("span", class_="post-date").string
2623		day = string_to_date(date_str, "%d. %B %Y", "de_DE.utf8")
2624		imgs = soup.find("div", id="comic").find_all("img")
2625		assert all(i['alt'] == i['title'] == title for i in imgs)
2626		assert len(imgs) <= 1, imgs
2627		return {
2628		'img': [i['src'] for i in imgs],
2629		'title': title,
2630		'author': author,
2631		'day': day.day,
2632		'month': day.month,
2633		'year': day.year
2634		}
2635
2636
2637		class BiterComics(GenericNavigableComic):
2638		"""Class to retrieve Biter Comics."""
2639		name = "biter"
2640		long_name = "Biter Comics"
		@@ 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		def get_url_from_archive_element(cls, tr):
2443		"""Get url corresponding to an archive element."""
2444		_, td_comic, td_date, _ = tr.find_all('td')
2445		link = td_comic.find('a')
2446		return urljoin_wrapper(cls.url, link['href'])
2447
2448		@classmethod
2449		def get_comic_info(cls, soup, tr):
2450		"""Get information about a particular comics."""
2451		td_num, td_comic, td_date, _ = tr.find_all('td')
2452		num = int(td_num.string)
2453		link = td_comic.find('a')
2454		title = link.string
2455		imgs = soup.find_all('img', id='comic_image')
2456		date_str = td_date.string
2457		day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y, %I:%M %p")
2458		assert len(imgs) == 1, imgs
2459		assert all(i.get('alt') == i.get('title') for i in imgs)
2460		return {
2461		'num': num,
2462		'title': title,
2463		'alt': imgs[0].get('alt', ''),
2464		'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
2465		'month': day.month,
2466		'year': day.year,
2467		'day': day.day,
2468		}
2469
2470
2471		class LonnieMillsap(GenericNavigableComic):
2472		"""Class to retrieve Lonnie Millsap's comics."""
		@@ 3306-3329 (lines=24) @@
3303		day = string_to_date(date_str, "%B %d, %Y")
3304		return {
3305		'img': [i['src'] for i in imgs],
3306		'title': title,
3307		'month': day.month,
3308		'year': day.year,
3309		'day': day.day,
3310		}
3311
3312
3313		class TheMeerkatguy(GenericNavigableComic):
3314		"""Class to retrieve The Meerkatguy comics."""
3315		long_name = 'The Meerkatguy'
3316		url = 'http://www.themeerkatguy.com'
3317		name = 'meerkatguy'
3318		get_first_comic_link = get_a_comicnavbase_comicnavfirst
3319		get_navi_link = get_a_comicnavbase_comicnavnext
3320
3321		@classmethod
3322		def get_comic_info(cls, soup, link):
3323		"""Get information about a particular comics."""
3324		title = soup.find('title').string
3325		imgs = soup.find_all('meta', property='og:image')
3326		return {
3327		'img': [i['content'] for i in imgs],
3328		'title': title,
3329		}
3330
3331
3332		class Ubertool(GenericNavigableComic):
		@@ 3607-3627 (lines=21) @@
3604		_categories = ('BLOGSPOT', )
3605
3606		@classmethod
3607		def get_navi_link(cls, last_soup, next_):
3608		"""Get link to next or previous comic."""
3609		return last_soup.find('a', id='Blog1_blog-pager-newer-link' if next_ else 'Blog1_blog-pager-older-link')
3610
3611
3612		class TuMourrasMoinsBete(GenericBlogspotComic):
3613		"""Class to retrieve Tu Mourras Moins Bete comics."""
3614		name = 'mourrasmoinsbete'
3615		long_name = 'Tu Mourras Moins Bete'
3616		url = 'http://tumourrasmoinsbete.blogspot.fr'
3617		_categories = ('FRANCAIS', )
3618		first_url = 'http://tumourrasmoinsbete.blogspot.fr/2008/06/essai.html'
3619
3620		@classmethod
3621		def get_comic_info(cls, soup, link):
3622		"""Get information about a particular comics."""
3623		title = soup.find('title').string
3624		imgs = soup.find('div', itemprop='description articleBody').find_all('img')
3625		author = soup.find('span', itemprop='author').string
3626		return {
3627		'img': [i['src'] for i in imgs],
3628		'author': author,
3629		'title': title,
3630		}
		@@ 3263-3283 (lines=21) @@
3260		long_name = 'Sheldon Comics'
3261		url = 'http://www.sheldoncomics.com'
3262
3263		@classmethod
3264		def get_first_comic_link(cls):
3265		"""Get link to first comics."""
3266		return get_soup_at_url(cls.url).find("a", id="nav-first")
3267
3268		@classmethod
3269		def get_navi_link(cls, last_soup, next_):
3270		"""Get link to next or previous comic."""
3271		for link in last_soup.find_all("a", id="nav-next" if next_ else "nav-prev"):
3272		if link['href'] != 'http://www.sheldoncomics.com':
3273		return link
3274		return None
3275
3276		@classmethod
3277		def get_comic_info(cls, soup, link):
3278		"""Get information about a particular comics."""
3279		imgs = soup.find("div", id="comic-foot").find_all("img")
3280		assert all(i['alt'] == i['title'] for i in imgs)
3281		assert len(imgs) == 1, imgs
3282		title = imgs[0]['title']
3283		return {
3284		'title': title,
3285		'img': [i['src'] for i in imgs],
3286		}
		@@ 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