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

Code Duplication Length = 21-29 lines in 23 locations

comics.py 23 locations



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

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


class Penmen(GenericNavigableComic):
    """Class to retrieve Penmen comics."""

        }


class ImogenQuest(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 PleasantThoughts(GenericNavigableComic):
    """Class to retrieve Pleasant Thoughts comics."""


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 BoumerieEn(GenericBoumerie):
    """Class to retrieve Boumeries comics in English."""


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
        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."""


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."""

    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(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 TalesOfAbsurdity(GenericNavigableComic):
    """Class to retrieve Tales Of Absurdity comics."""
    # Also on http://tapastic.com/series/Tales-Of-Absurdity
    # Also on http://talesofabsurdity.tumblr.com
    name = 'absurdity'
    long_name = 'Tales of Absurdity'
    url = 'http://talesofabsurdity.com'
    _categories = ('ABSURDITY', )
    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'] for i in imgs)
        alt = imgs[0]['alt'] if imgs else ""
        return {
            'img': [i['src'] for i in imgs],
            'title': title,
            'alt': alt,
            'author': author,
            'day': day.day,
            'month': day.month,
            'year': day.year
        }


class EndlessOrigami(GenericComicNotWorking, GenericNavigableComic):  # Nav not working
    """Class to retrieve Endless Origami Comics."""


class MisterAndMe(GenericNavigableComic):
    """Class to retrieve Mister & Me Comics."""
    # Also on http://www.gocomics.com/mister-and-me
    # Also on https://tapastic.com/series/Mister-and-Me
    name = 'mister'
    long_name = 'Mister & Me'
    url = 'http://www.mister-and-me.com'
    get_first_comic_link = get_a_comicnavbase_comicnavfirst
    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")
        assert all(i['alt'] == i['title'] for i in imgs)
        assert len(imgs) <= 1
        alt = imgs[0]['alt'] if imgs else ""
        return {
            'img': [i['src'] for i in imgs],
            'title': title,
            'alt': alt,
            'author': author,
            'day': day.day,
            'month': day.month,
            'year': day.year
        }


class LastPlaceComics(GenericNavigableComic):
    """Class to retrieve Last Place Comics."""


class Optipess(GenericNavigableComic):
    """Class to retrieve Optipess comics."""
    name = 'optipess'
    long_name = 'Optipess'
    url = 'http://www.optipess.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
        comic = soup.find('div', id='comic')
        imgs = comic.find_all('img') if comic else []
        alt = imgs[0]['title'] if imgs else ""
        assert all(i['alt'] == i['title'] == alt for i in imgs)
        date_str = soup.find('span', class_='post-date').string
        day = string_to_date(date_str, "%B %d, %Y")
        return {
            'title': title,
            'alt': alt,
            'author': author,
            'img': [i['src'] for i in imgs],
            'month': day.month,
            'year': day.year,
            'day': day.day,
        }


class PainTrainComic(GenericNavigableComic):
    """Class to retrieve Pain Train Comics."""


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
        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."""


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."""


class EndlessOrigami(GenericComicNotWorking, GenericNavigableComic):  # Nav not working
    """Class to retrieve Endless Origami Comics."""
    name = "origami"
    long_name = "Endless Origami"
    url = "http://endlessorigami.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")
        assert all(i['alt'] == i['title'] for i in imgs)
        alt = imgs[0]['alt'] if imgs else ""
        return {
            'img': [i['src'] for i in imgs],
            'title': title,
            'alt': alt,
            'author': author,
            'day': day.day,
            'month': day.month,
            'year': day.year
        }


class PlanC(GenericNavigableComic):
    """Class to retrieve Plan C 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."""


class Penmen(GenericNavigableComic):
    """Class to retrieve Penmen comics."""
    name = 'penmen'
    long_name = 'Penmen'
    url = 'http://penmen.com'
    get_navi_link = get_link_rel_next
    get_first_comic_link = simulate_first_link
    first_url = 'http://penmen.com/index.php/2016/09/12/penmen-announces-grin-big-brand-clothing/'

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('title').string
        imgs = soup.find('div', class_='entry-content').find_all('img')
        short_url = soup.find('link', rel='shortlink')['href']
        tags = ' '.join(t.string for t in soup.find_all('a', rel='tag'))
        date_str = soup.find('time')['datetime'][:10]
        day = string_to_date(date_str, "%Y-%m-%d")
        return {
            'title': title,
            'short_url': short_url,
            'img': [i['src'] for i in imgs],
            'tags': tags,
            'month': day.month,
            'year': day.year,
            'day': day.day,
        }


class TheDoghouseDiaries(GenericDeletedComic, GenericNavigableComic):
    """Class to retrieve The Dog House Diaries comics."""


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(GenericNavigableComic):
    """Class to retrieve L.I.N.S. Editions comics."""


class ChuckleADuck(GenericNavigableComic):
    """Class to retrieve Chuckle-A-Duck comics."""
    name = 'chuckleaduck'
    long_name = 'Chuckle-A-duck'
    url = 'http://chuckleaduck.com'
    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."""
        date_str = soup.find('span', class_='post-date').string
        day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y")
        author = soup.find('span', class_='post-author').string
        div = soup.find('div', id='comic')
        imgs = div.find_all('img') if div else []
        title = imgs[0]['title'] if imgs else ""
        assert all(i['title'] == i['alt'] == title for i in imgs)
        return {
            'month': day.month,
            'year': day.year,
            'day': day.day,
            'img': [i['src'] for i in imgs],
            'title': title,
            'author': author,
        }


class DepressedAlien(GenericNavigableComic):
    """Class to retrieve Depressed Alien Comics."""

    get_url_from_link = join_cls_url_to_href
    get_first_comic_link = simulate_first_link
    first_url = 'http://www.earthexplodes.com/comics/000/'

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

    @classmethod
    def get_comic_info(cls, soup, link):
        """Get information about a particular comics."""
        title = soup.find('title').string
        imgs = soup.find('div', id='image').find_all('img')
        alt = imgs[0].get('title', '')
        return {
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
            'title': title,
            'alt': alt,
        }


class PomComics(GenericNavigableComic):
    """Class to retrieve PomComics."""
    name = 'pom'
    long_name = 'Pom Comics / Piece of Me'
    url = 'http://www.pomcomic.com'
    get_url_from_link = join_cls_url_to_href

    @classmethod

        }


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 PlanC(GenericNavigableComic):
    """Class to retrieve Plan C comics."""
    name = 'planc'
    long_name = 'Plan C'
    url = 'http://www.plancomic.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
        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 {
            'title': title,
            'img': [i['src'] for i in imgs],
            'month': day.month,
            'year': day.year,
            'day': day.day,
        }


class BuniComic(GenericNavigableComic):
    """Class to retrieve Buni Comics."""
SylvainDe / ComicBookMaker

Code Duplication Length = 21-29 lines in 23 locations

comics.py 23 locations
