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

Code Duplication Length = 24-27 lines in 13 locations

comics.py 13 locations


        }


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 LastPlaceComics(GenericNavigableComic):
    """Class to retrieve Last Place Comics."""
    name = 'lastplace'
    long_name = 'LastPlaceComics'
    url = "http://lastplacecomics.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 EndlessOrigami(GenericNavigableComic):
    """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 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 SafelyEndangered(GenericNavigableComic):
    """Class to retrieve Safely Endangered comics."""
    # Also on http://tumblr.safelyendangered.com
    name = 'endangered'
    long_name = 'Safely Endangered'
    url = 'http://www.safelyendangered.com'
    get_navi_link = get_link_rel_next
    get_first_comic_link = simulate_first_link
    first_url = 'http://www.safelyendangered.com/comic/ignored/'

    @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')
        alt = imgs[0]['alt']
        assert all(i['alt'] == i['title'] for i in imgs)
        return {
            'day': day.day,
            'month': day.month,
            'year': day.year,
            'img': [i['src'] for i in imgs],
            'title': title,
            'alt': alt,
        }



        }


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,
        }



    url = 'http://tubeytoons.com'


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

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



        }


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

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



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


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

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



        }


class 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
        }



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


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

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



        }


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

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



		@@ 2734-2760 (lines=27) @@
2731		}
2732
2733
2734		class Optipess(GenericNavigableComic):
2735		"""Class to retrieve Optipess comics."""
2736		name = 'optipess'
2737		long_name = 'Optipess'
2738		url = 'http://www.optipess.com'
2739		get_first_comic_link = get_a_navi_navifirst
2740		get_navi_link = get_link_rel_next
2741
2742		@classmethod
2743		def get_comic_info(cls, soup, link):
2744		"""Get information about a particular comics."""
2745		title = soup.find('h2', class_='post-title').string
2746		author = soup.find("span", class_="post-author").find("a").string
2747		comic = soup.find('div', id='comic')
2748		imgs = comic.find_all('img') if comic else []
2749		alt = imgs[0]['title'] if imgs else ""
2750		assert all(i['alt'] == i['title'] == alt for i in imgs)
2751		date_str = soup.find('span', class_='post-date').string
2752		day = string_to_date(date_str, "%B %d, %Y")
2753		return {
2754		'title': title,
2755		'alt': alt,
2756		'author': author,
2757		'img': [i['src'] for i in imgs],
2758		'month': day.month,
2759		'year': day.year,
2760		'day': day.day,
2761		}
2762
2763
		@@ 2484-2510 (lines=27) @@
2481		}
2482
2483
2484		class LastPlaceComics(GenericNavigableComic):
2485		"""Class to retrieve Last Place Comics."""
2486		name = 'lastplace'
2487		long_name = 'LastPlaceComics'
2488		url = "http://lastplacecomics.com"
2489		get_first_comic_link = get_a_comicnavbase_comicnavfirst
2490		get_navi_link = get_link_rel_next
2491
2492		@classmethod
2493		def get_comic_info(cls, soup, link):
2494		"""Get information about a particular comics."""
2495		title = soup.find('h2', class_='post-title').string
2496		author = soup.find("span", class_="post-author").find("a").string
2497		date_str = soup.find("span", class_="post-date").string
2498		day = string_to_date(date_str, "%B %d, %Y")
2499		imgs = soup.find("div", id="comic").find_all("img")
2500		assert all(i['alt'] == i['title'] for i in imgs)
2501		assert len(imgs) <= 1
2502		alt = imgs[0]['alt'] if imgs else ""
2503		return {
2504		'img': [i['src'] for i in imgs],
2505		'title': title,
2506		'alt': alt,
2507		'author': author,
2508		'day': day.day,
2509		'month': day.month,
2510		'year': day.year
2511		}
2512
2513
		@@ 2545-2570 (lines=26) @@
2542		}
2543
2544
2545		class EndlessOrigami(GenericNavigableComic):
2546		"""Class to retrieve Endless Origami Comics."""
2547		name = "origami"
2548		long_name = "Endless Origami"
2549		url = "http://endlessorigami.com"
2550		get_first_comic_link = get_a_navi_navifirst
2551		get_navi_link = get_link_rel_next
2552
2553		@classmethod
2554		def get_comic_info(cls, soup, link):
2555		"""Get information about a particular comics."""
2556		title = soup.find('h2', class_='post-title').string
2557		author = soup.find("span", class_="post-author").find("a").string
2558		date_str = soup.find("span", class_="post-date").string
2559		day = string_to_date(date_str, "%B %d, %Y")
2560		imgs = soup.find("div", id="comic").find_all("img")
2561		assert all(i['alt'] == i['title'] for i in imgs)
2562		alt = imgs[0]['alt'] if imgs else ""
2563		return {
2564		'img': [i['src'] for i in imgs],
2565		'title': title,
2566		'alt': alt,
2567		'author': author,
2568		'day': day.day,
2569		'month': day.month,
2570		'year': day.year
2571		}
2572
2573
		@@ 2317-2342 (lines=26) @@
2314		}
2315
2316
2317		class GerbilWithAJetpack(GenericNavigableComic):
2318		"""Class to retrieve GerbilWithAJetpack comics."""
2319		name = 'gerbil'
2320		long_name = 'Gerbil With A Jetpack'
2321		url = 'http://gerbilwithajetpack.com'
2322		get_first_comic_link = get_a_navi_navifirst
2323		get_navi_link = get_a_rel_next
2324
2325		@classmethod
2326		def get_comic_info(cls, soup, link):
2327		"""Get information about a particular comics."""
2328		title = soup.find('h2', class_='post-title').string
2329		author = soup.find("span", class_="post-author").find("a").string
2330		date_str = soup.find("span", class_="post-date").string
2331		day = string_to_date(date_str, "%B %d, %Y")
2332		imgs = soup.find("div", id="comic").find_all("img")
2333		alt = imgs[0]['alt']
2334		assert all(i['alt'] == i['title'] == alt for i in imgs)
2335		return {
2336		'img': [i['src'] for i in imgs],
2337		'title': title,
2338		'alt': alt,
2339		'author': author,
2340		'day': day.day,
2341		'month': day.month,
2342		'year': day.year
2343		}
2344
2345
		@@ 1781-1806 (lines=26) @@
1778		}
1779
1780
1781		class SafelyEndangered(GenericNavigableComic):
1782		"""Class to retrieve Safely Endangered comics."""
1783		# Also on http://tumblr.safelyendangered.com
1784		name = 'endangered'
1785		long_name = 'Safely Endangered'
1786		url = 'http://www.safelyendangered.com'
1787		get_navi_link = get_link_rel_next
1788		get_first_comic_link = simulate_first_link
1789		first_url = 'http://www.safelyendangered.com/comic/ignored/'
1790
1791		@classmethod
1792		def get_comic_info(cls, soup, link):
1793		"""Get information about a particular comics."""
1794		title = soup.find('h2', class_='post-title').string
1795		date_str = soup.find('span', class_='post-date').string
1796		day = string_to_date(date_str, '%B %d, %Y')
1797		imgs = soup.find('div', id='comic').find_all('img')
1798		alt = imgs[0]['alt']
1799		assert all(i['alt'] == i['title'] for i in imgs)
1800		return {
1801		'day': day.day,
1802		'month': day.month,
1803		'year': day.year,
1804		'img': [i['src'] for i in imgs],
1805		'title': title,
1806		'alt': alt,
1807		}
1808
1809
		@@ 2017-2041 (lines=25) @@
2014		}
2015
2016
2017		class ChuckleADuck(GenericNavigableComic):
2018		"""Class to retrieve Chuckle-A-Duck comics."""
2019		name = 'chuckleaduck'
2020		long_name = 'Chuckle-A-duck'
2021		url = 'http://chuckleaduck.com'
2022		get_first_comic_link = get_div_navfirst_a
2023		get_navi_link = get_link_rel_next
2024
2025		@classmethod
2026		def get_comic_info(cls, soup, link):
2027		"""Get information about a particular comics."""
2028		date_str = soup.find('span', class_='post-date').string
2029		day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y")
2030		author = soup.find('span', class_='post-author').string
2031		div = soup.find('div', id='comic')
2032		imgs = div.find_all('img') if div else []
2033		title = imgs[0]['title'] if imgs else ""
2034		assert all(i['title'] == i['alt'] == title for i in imgs)
2035		return {
2036		'month': day.month,
2037		'year': day.year,
2038		'day': day.day,
2039		'img': [i['src'] for i in imgs],
2040		'title': title,
2041		'author': author,
2042		}
2043
2044
		@@ 1931-1957 (lines=27) @@
1928		url = 'http://tubeytoons.com'
1929
1930
1931		class CompletelySeriousComics(GenericNavigableComic):
1932		"""Class to retrieve Completely Serious comics."""
1933		name = 'completelyserious'
1934		long_name = 'Completely Serious Comics'
1935		url = 'http://completelyseriouscomics.com'
1936		get_first_comic_link = get_a_navi_navifirst
1937		get_navi_link = get_a_navi_navinext
1938
1939		@classmethod
1940		def get_comic_info(cls, soup, link):
1941		"""Get information about a particular comics."""
1942		title = soup.find('h2', class_='post-title').string
1943		author = soup.find('span', class_='post-author').contents[1].string
1944		date_str = soup.find('span', class_='post-date').string
1945		day = string_to_date(date_str, '%B %d, %Y')
1946		imgs = soup.find('div', class_='comicpane').find_all('img')
1947		assert imgs
1948		alt = imgs[0]['title']
1949		assert all(i['title'] == i['alt'] == alt for i in imgs)
1950		return {
1951		'month': day.month,
1952		'year': day.year,
1953		'day': day.day,
1954		'img': [i['src'] for i in imgs],
1955		'title': title,
1956		'alt': alt,
1957		'author': author,
1958		}
1959
1960
		@@ 1810-1836 (lines=27) @@
1807		}
1808
1809
1810		class PicturesInBoxes(GenericNavigableComic):
1811		"""Class to retrieve Pictures In Boxes comics."""
1812		# Also on http://picturesinboxescomic.tumblr.com
1813		name = 'picturesinboxes'
1814		long_name = 'Pictures in Boxes'
1815		url = 'http://www.picturesinboxes.com'
1816		get_navi_link = get_a_navi_navinext
1817		get_first_comic_link = simulate_first_link
1818		first_url = 'http://www.picturesinboxes.com/2013/10/26/tetris/'
1819
1820		@classmethod
1821		def get_comic_info(cls, soup, link):
1822		"""Get information about a particular comics."""
1823		title = soup.find('h2', class_='post-title').string
1824		author = soup.find("span", class_="post-author").find("a").string
1825		date_str = soup.find('span', class_='post-date').string
1826		day = string_to_date(date_str, '%B %d, %Y')
1827		imgs = soup.find('div', class_='comicpane').find_all('img')
1828		assert imgs
1829		assert all(i['title'] == i['alt'] == title for i in imgs)
1830		return {
1831		'day': day.day,
1832		'month': day.month,
1833		'year': day.year,
1834		'img': [i['src'] for i in imgs],
1835		'title': title,
1836		'author': author,
1837		}
1838
1839
		@@ 1699-1723 (lines=25) @@
1696		}
1697
1698
1699		class MouseBearComedy(GenericNavigableComic):
1700		"""Class to retrieve Mouse Bear Comedy comics."""
1701		# Also on http://mousebearcomedy.tumblr.com
1702		name = 'mousebear'
1703		long_name = 'Mouse Bear Comedy'
1704		url = 'http://www.mousebearcomedy.com'
1705		get_first_comic_link = get_a_navi_navifirst
1706		get_navi_link = get_a_navi_comicnavnext_navinext
1707
1708		@classmethod
1709		def get_comic_info(cls, soup, link):
1710		"""Get information about a particular comics."""
1711		title = soup.find('h2', class_='post-title').string
1712		author = soup.find("span", class_="post-author").find("a").string
1713		date_str = soup.find("span", class_="post-date").string
1714		day = string_to_date(date_str, '%B %d, %Y')
1715		imgs = soup.find("div", id="comic").find_all("img")
1716		assert all(i['alt'] == i['title'] == title for i in imgs)
1717		return {
1718		'day': day.day,
1719		'month': day.month,
1720		'year': day.year,
1721		'img': [i['src'] for i in imgs],
1722		'title': title,
1723		'author': author,
1724		}
1725
1726
		@@ 1114-1137 (lines=24) @@
1111		url = 'http://english.bouletcorp.com'
1112
1113
1114		class AmazingSuperPowers(GenericNavigableComic):
1115		"""Class to retrieve Amazing Super Powers comics."""
1116		name = 'asp'
1117		long_name = 'Amazing Super Powers'
1118		url = 'http://www.amazingsuperpowers.com'
1119		get_first_comic_link = get_a_navi_navifirst
1120		get_navi_link = get_a_navi_navinext
1121
1122		@classmethod
1123		def get_comic_info(cls, soup, link):
1124		"""Get information about a particular comics."""
1125		author = soup.find("span", class_="post-author").find("a").string
1126		date_str = soup.find('span', class_='post-date').string
1127		day = string_to_date(date_str, "%B %d, %Y")
1128		imgs = soup.find('div', id='comic').find_all('img')
1129		title = ' '.join(i['title'] for i in imgs)
1130		assert all(i['alt'] == i['title'] for i in imgs)
1131		return {
1132		'title': title,
1133		'author': author,
1134		'img': [img['src'] for img in imgs],
1135		'day': day.day,
1136		'month': day.month,
1137		'year': day.year
1138		}
1139
1140
		@@ 2374-2400 (lines=27) @@
2371		}
2372
2373
2374		class BiterComics(GenericNavigableComic):
2375		"""Class to retrieve Biter Comics."""
2376		name = "biter"
2377		long_name = "Biter Comics"
2378		url = "http://www.bitercomics.com"
2379		get_first_comic_link = get_a_navi_navifirst
2380		get_navi_link = get_link_rel_next
2381
2382		@classmethod
2383		def get_comic_info(cls, soup, link):
2384		"""Get information about a particular comics."""
2385		title = soup.find("h1", class_="entry-title").string
2386		author = soup.find("span", class_="author vcard").find("a").string
2387		date_str = soup.find("span", class_="entry-date").string
2388		day = string_to_date(date_str, "%B %d, %Y")
2389		imgs = soup.find("div", id="comic").find_all("img")
2390		assert all(i['alt'] == i['title'] for i in imgs)
2391		assert len(imgs) == 1
2392		alt = imgs[0]['alt']
2393		return {
2394		'img': [i['src'] for i in imgs],
2395		'title': title,
2396		'alt': alt,
2397		'author': author,
2398		'day': day.day,
2399		'month': day.month,
2400		'year': day.year
2401		}
2402
2403
		@@ 2116-2141 (lines=26) @@
2113		return reversed(get_soup_at_url(archive_url).find('tbody').find_all('tr'))
2114
2115
2116		class HappleTea(GenericNavigableComic):
2117		"""Class to retrieve Happle Tea Comics."""
2118		name = 'happletea'
2119		long_name = 'Happle Tea'
2120		url = 'http://www.happletea.com'
2121		get_first_comic_link = get_a_navi_navifirst
2122		get_navi_link = get_link_rel_next
2123
2124		@classmethod
2125		def get_comic_info(cls, soup, link):
2126		"""Get information about a particular comics."""
2127		imgs = soup.find('div', id='comic').find_all('img')
2128		post = soup.find('div', class_='post-content')
2129		title = post.find('h2', class_='post-title').string
2130		author = post.find('a', rel='author').string
2131		date_str = post.find('span', class_='post-date').string
2132		day = string_to_date(date_str, "%B %d, %Y")
2133		assert all(i['alt'] == i['title'] for i in imgs)
2134		return {
2135		'title': title,
2136		'img': [i['src'] for i in imgs],
2137		'alt': ''.join(i['alt'] for i in imgs),
2138		'month': day.month,
2139		'year': day.year,
2140		'day': day.day,
2141		'author': author,
2142		}
2143
2144
		@@ 2346-2370 (lines=25) @@
2343		}
2344
2345
2346		class EveryDayBlues(GenericNavigableComic):
2347		"""Class to retrieve EveryDayBlues Comics."""
2348		name = "blues"
2349		long_name = "Every Day Blues"
2350		url = "http://everydayblues.net"
2351		get_first_comic_link = get_a_navi_navifirst
2352		get_navi_link = get_link_rel_next
2353
2354		@classmethod
2355		def get_comic_info(cls, soup, link):
2356		"""Get information about a particular comics."""
2357		title = soup.find("h2", class_="post-title").string
2358		author = soup.find("span", class_="post-author").find("a").string
2359		date_str = soup.find("span", class_="post-date").string
2360		day = string_to_date(date_str, "%d. %B %Y", "de_DE.utf8")
2361		imgs = soup.find("div", id="comic").find_all("img")
2362		assert all(i['alt'] == i['title'] == title for i in imgs)
2363		assert len(imgs) <= 1
2364		return {
2365		'img': [i['src'] for i in imgs],
2366		'title': title,
2367		'author': author,
2368		'day': day.day,
2369		'month': day.month,
2370		'year': day.year
2371		}
2372
2373

SylvainDe / ComicBookMaker

Code Duplication Length = 24-27 lines in 13 locations

comics.py 13 locations