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

Code Duplication Length = 24-28 lines in 14 locations

comics.py 14 locations


            'year': day.year
        }


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'
    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
        }


            'year': day.year
        }


class LastPlaceComics(GenericNavigableComic):
    """Class to retrieve Last Place Comics."""
    name = 'lastplace'
    long_name = 'Last Place Comics'
    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
        }


            '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
        }


            'alt': alt,
        }


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,
        }


            'description': description,
        }


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
        }


        archive_url = urljoin_wrapper(cls.url, 'archive-2')
        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,
        }


    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."""
    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,
        }


            'year': day.year
        }


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
        }


            'alt': alt,
        }


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,
        }


    long_name = 'Boulet Corp English'
    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
        }


            'day': day.day,
        }


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,
        }


    long_name = 'Tubey Toons'
    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,
        }


            'img': [i['content'] for i in imgs if i['content'] not in skip_imgs],
        }


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,
        }


            'day': day.day,
        }


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,
        }


		@@ 2516-2543 (lines=28) @@
2513		'year': day.year
2514		}
2515
2516
2517		class TalesOfAbsurdity(GenericNavigableComic):
2518		"""Class to retrieve Tales Of Absurdity comics."""
2519		# Also on http://tapastic.com/series/Tales-Of-Absurdity
2520		# Also on http://talesofabsurdity.tumblr.com
2521		name = 'absurdity'
2522		long_name = 'Tales of Absurdity'
2523		url = 'http://talesofabsurdity.com'
2524		get_first_comic_link = get_a_navi_navifirst
2525		get_navi_link = get_a_navi_comicnavnext_navinext
2526
2527		@classmethod
2528		def get_comic_info(cls, soup, link):
2529		"""Get information about a particular comics."""
2530		title = soup.find('h2', class_='post-title').string
2531		author = soup.find("span", class_="post-author").find("a").string
2532		date_str = soup.find("span", class_="post-date").string
2533		day = string_to_date(date_str, "%B %d, %Y")
2534		imgs = soup.find("div", id="comic").find_all("img")
2535		assert all(i['alt'] == i['title'] for i in imgs)
2536		alt = imgs[0]['alt'] if imgs else ""
2537		return {
2538		'img': [i['src'] for i in imgs],
2539		'title': title,
2540		'alt': alt,
2541		'author': author,
2542		'day': day.day,
2543		'month': day.month,
2544		'year': day.year
2545		}
2546
		@@ 2486-2512 (lines=27) @@
2483		'year': day.year
2484		}
2485
2486
2487		class LastPlaceComics(GenericNavigableComic):
2488		"""Class to retrieve Last Place Comics."""
2489		name = 'lastplace'
2490		long_name = 'Last Place Comics'
2491		url = "http://lastplacecomics.com"
2492		get_first_comic_link = get_a_comicnavbase_comicnavfirst
2493		get_navi_link = get_link_rel_next
2494
2495		@classmethod
2496		def get_comic_info(cls, soup, link):
2497		"""Get information about a particular comics."""
2498		title = soup.find('h2', class_='post-title').string
2499		author = soup.find("span", class_="post-author").find("a").string
2500		date_str = soup.find("span", class_="post-date").string
2501		day = string_to_date(date_str, "%B %d, %Y")
2502		imgs = soup.find("div", id="comic").find_all("img")
2503		assert all(i['alt'] == i['title'] for i in imgs)
2504		assert len(imgs) <= 1
2505		alt = imgs[0]['alt'] if imgs else ""
2506		return {
2507		'img': [i['src'] for i in imgs],
2508		'title': title,
2509		'alt': alt,
2510		'author': author,
2511		'day': day.day,
2512		'month': day.month,
2513		'year': day.year
2514		}
2515
		@@ 2376-2402 (lines=27) @@
2373		'year': day.year
2374		}
2375
2376
2377		class BiterComics(GenericNavigableComic):
2378		"""Class to retrieve Biter Comics."""
2379		name = "biter"
2380		long_name = "Biter Comics"
2381		url = "http://www.bitercomics.com"
2382		get_first_comic_link = get_a_navi_navifirst
2383		get_navi_link = get_link_rel_next
2384
2385		@classmethod
2386		def get_comic_info(cls, soup, link):
2387		"""Get information about a particular comics."""
2388		title = soup.find("h1", class_="entry-title").string
2389		author = soup.find("span", class_="author vcard").find("a").string
2390		date_str = soup.find("span", class_="entry-date").string
2391		day = string_to_date(date_str, "%B %d, %Y")
2392		imgs = soup.find("div", id="comic").find_all("img")
2393		assert all(i['alt'] == i['title'] for i in imgs)
2394		assert len(imgs) == 1
2395		alt = imgs[0]['alt']
2396		return {
2397		'img': [i['src'] for i in imgs],
2398		'title': title,
2399		'alt': alt,
2400		'author': author,
2401		'day': day.day,
2402		'month': day.month,
2403		'year': day.year
2404		}
2405
		@@ 1808-1834 (lines=27) @@
1805		'alt': alt,
1806		}
1807
1808
1809		class PicturesInBoxes(GenericNavigableComic):
1810		"""Class to retrieve Pictures In Boxes comics."""
1811		# Also on http://picturesinboxescomic.tumblr.com
1812		name = 'picturesinboxes'
1813		long_name = 'Pictures in Boxes'
1814		url = 'http://www.picturesinboxes.com'
1815		get_navi_link = get_a_navi_navinext
1816		get_first_comic_link = simulate_first_link
1817		first_url = 'http://www.picturesinboxes.com/2013/10/26/tetris/'
1818
1819		@classmethod
1820		def get_comic_info(cls, soup, link):
1821		"""Get information about a particular comics."""
1822		title = soup.find('h2', class_='post-title').string
1823		author = soup.find("span", class_="post-author").find("a").string
1824		date_str = soup.find('span', class_='post-date').string
1825		day = string_to_date(date_str, '%B %d, %Y')
1826		imgs = soup.find('div', class_='comicpane').find_all('img')
1827		assert imgs
1828		assert all(i['title'] == i['alt'] == title for i in imgs)
1829		return {
1830		'day': day.day,
1831		'month': day.month,
1832		'year': day.year,
1833		'img': [i['src'] for i in imgs],
1834		'title': title,
1835		'author': author,
1836		}
1837
		@@ 2319-2344 (lines=26) @@
2316		'description': description,
2317		}
2318
2319
2320		class GerbilWithAJetpack(GenericNavigableComic):
2321		"""Class to retrieve GerbilWithAJetpack comics."""
2322		name = 'gerbil'
2323		long_name = 'Gerbil With A Jetpack'
2324		url = 'http://gerbilwithajetpack.com'
2325		get_first_comic_link = get_a_navi_navifirst
2326		get_navi_link = get_a_rel_next
2327
2328		@classmethod
2329		def get_comic_info(cls, soup, link):
2330		"""Get information about a particular comics."""
2331		title = soup.find('h2', class_='post-title').string
2332		author = soup.find("span", class_="post-author").find("a").string
2333		date_str = soup.find("span", class_="post-date").string
2334		day = string_to_date(date_str, "%B %d, %Y")
2335		imgs = soup.find("div", id="comic").find_all("img")
2336		alt = imgs[0]['alt']
2337		assert all(i['alt'] == i['title'] == alt for i in imgs)
2338		return {
2339		'img': [i['src'] for i in imgs],
2340		'title': title,
2341		'alt': alt,
2342		'author': author,
2343		'day': day.day,
2344		'month': day.month,
2345		'year': day.year
2346		}
2347
		@@ 2117-2142 (lines=26) @@
2114		archive_url = urljoin_wrapper(cls.url, 'archive-2')
2115		return reversed(get_soup_at_url(archive_url).find('tbody').find_all('tr'))
2116
2117
2118		class HappleTea(GenericNavigableComic):
2119		"""Class to retrieve Happle Tea Comics."""
2120		name = 'happletea'
2121		long_name = 'Happle Tea'
2122		url = 'http://www.happletea.com'
2123		get_first_comic_link = get_a_navi_navifirst
2124		get_navi_link = get_link_rel_next
2125
2126		@classmethod
2127		def get_comic_info(cls, soup, link):
2128		"""Get information about a particular comics."""
2129		imgs = soup.find('div', id='comic').find_all('img')
2130		post = soup.find('div', class_='post-content')
2131		title = post.find('h2', class_='post-title').string
2132		author = post.find('a', rel='author').string
2133		date_str = post.find('span', class_='post-date').string
2134		day = string_to_date(date_str, "%B %d, %Y")
2135		assert all(i['alt'] == i['title'] for i in imgs)
2136		return {
2137		'title': title,
2138		'img': [i['src'] for i in imgs],
2139		'alt': ''.join(i['alt'] for i in imgs),
2140		'month': day.month,
2141		'year': day.year,
2142		'day': day.day,
2143		'author': author,
2144		}
2145
		@@ 2657-2681 (lines=25) @@
2654		url = 'http://www.commitstrip.com/en'
2655		first_url = 'http://www.commitstrip.com/en/2012/02/22/interview/'
2656
2657
2658		class GenericBoumerie(GenericNavigableComic):
2659		"""Generic class to retrieve Boumeries comics in different languages."""
2660		get_first_comic_link = get_a_navi_navifirst
2661		get_navi_link = get_link_rel_next
2662		date_format = NotImplemented
2663		lang = NotImplemented
2664
2665		@classmethod
2666		def get_comic_info(cls, soup, link):
2667		"""Get information about a particular comics."""
2668		title = soup.find('h2', class_='post-title').string
2669		short_url = soup.find('link', rel='shortlink')['href']
2670		author = soup.find("span", class_="post-author").find("a").string
2671		date_str = soup.find('span', class_='post-date').string
2672		day = string_to_date(date_str, cls.date_format, cls.lang)
2673		imgs = soup.find('div', id='comic').find_all('img')
2674		assert all(i['alt'] == i['title'] for i in imgs)
2675		return {
2676		'short_url': short_url,
2677		'img': [i['src'] for i in imgs],
2678		'title': title,
2679		'author': author,
2680		'month': day.month,
2681		'year': day.year,
2682		'day': day.day,
2683		}
2684
		@@ 2348-2372 (lines=25) @@
2345		'year': day.year
2346		}
2347
2348
2349		class EveryDayBlues(GenericNavigableComic):
2350		"""Class to retrieve EveryDayBlues Comics."""
2351		name = "blues"
2352		long_name = "Every Day Blues"
2353		url = "http://everydayblues.net"
2354		get_first_comic_link = get_a_navi_navifirst
2355		get_navi_link = get_link_rel_next
2356
2357		@classmethod
2358		def get_comic_info(cls, soup, link):
2359		"""Get information about a particular comics."""
2360		title = soup.find("h2", class_="post-title").string
2361		author = soup.find("span", class_="post-author").find("a").string
2362		date_str = soup.find("span", class_="post-date").string
2363		day = string_to_date(date_str, "%d. %B %Y", "de_DE.utf8")
2364		imgs = soup.find("div", id="comic").find_all("img")
2365		assert all(i['alt'] == i['title'] == title for i in imgs)
2366		assert len(imgs) <= 1
2367		return {
2368		'img': [i['src'] for i in imgs],
2369		'title': title,
2370		'author': author,
2371		'day': day.day,
2372		'month': day.month,
2373		'year': day.year
2374		}
2375
		@@ 1697-1721 (lines=25) @@
1694		'alt': alt,
1695		}
1696
1697
1698		class MouseBearComedy(GenericNavigableComic):
1699		"""Class to retrieve Mouse Bear Comedy comics."""
1700		# Also on http://mousebearcomedy.tumblr.com
1701		name = 'mousebear'
1702		long_name = 'Mouse Bear Comedy'
1703		url = 'http://www.mousebearcomedy.com'
1704		get_first_comic_link = get_a_navi_navifirst
1705		get_navi_link = get_a_navi_comicnavnext_navinext
1706
1707		@classmethod
1708		def get_comic_info(cls, soup, link):
1709		"""Get information about a particular comics."""
1710		title = soup.find('h2', class_='post-title').string
1711		author = soup.find("span", class_="post-author").find("a").string
1712		date_str = soup.find("span", class_="post-date").string
1713		day = string_to_date(date_str, '%B %d, %Y')
1714		imgs = soup.find("div", id="comic").find_all("img")
1715		assert all(i['alt'] == i['title'] == title for i in imgs)
1716		return {
1717		'day': day.day,
1718		'month': day.month,
1719		'year': day.year,
1720		'img': [i['src'] for i in imgs],
1721		'title': title,
1722		'author': author,
1723		}
1724
		@@ 1104-1127 (lines=24) @@
1101		long_name = 'Boulet Corp English'
1102		url = 'http://english.bouletcorp.com'
1103
1104
1105		class AmazingSuperPowers(GenericNavigableComic):
1106		"""Class to retrieve Amazing Super Powers comics."""
1107		name = 'asp'
1108		long_name = 'Amazing Super Powers'
1109		url = 'http://www.amazingsuperpowers.com'
1110		get_first_comic_link = get_a_navi_navifirst
1111		get_navi_link = get_a_navi_navinext
1112
1113		@classmethod
1114		def get_comic_info(cls, soup, link):
1115		"""Get information about a particular comics."""
1116		author = soup.find("span", class_="post-author").find("a").string
1117		date_str = soup.find('span', class_='post-date').string
1118		day = string_to_date(date_str, "%B %d, %Y")
1119		imgs = soup.find('div', id='comic').find_all('img')
1120		title = ' '.join(i['title'] for i in imgs)
1121		assert all(i['alt'] == i['title'] for i in imgs)
1122		return {
1123		'title': title,
1124		'author': author,
1125		'img': [img['src'] for img in imgs],
1126		'day': day.day,
1127		'month': day.month,
1128		'year': day.year
1129		}
1130
		@@ 2736-2762 (lines=27) @@
2733		'day': day.day,
2734		}
2735
2736
2737		class Optipess(GenericNavigableComic):
2738		"""Class to retrieve Optipess comics."""
2739		name = 'optipess'
2740		long_name = 'Optipess'
2741		url = 'http://www.optipess.com'
2742		get_first_comic_link = get_a_navi_navifirst
2743		get_navi_link = get_link_rel_next
2744
2745		@classmethod
2746		def get_comic_info(cls, soup, link):
2747		"""Get information about a particular comics."""
2748		title = soup.find('h2', class_='post-title').string
2749		author = soup.find("span", class_="post-author").find("a").string
2750		comic = soup.find('div', id='comic')
2751		imgs = comic.find_all('img') if comic else []
2752		alt = imgs[0]['title'] if imgs else ""
2753		assert all(i['alt'] == i['title'] == alt for i in imgs)
2754		date_str = soup.find('span', class_='post-date').string
2755		day = string_to_date(date_str, "%B %d, %Y")
2756		return {
2757		'title': title,
2758		'alt': alt,
2759		'author': author,
2760		'img': [i['src'] for i in imgs],
2761		'month': day.month,
2762		'year': day.year,
2763		'day': day.day,
2764		}
2765
		@@ 1930-1956 (lines=27) @@
1927		long_name = 'Tubey Toons'
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
		@@ 1779-1804 (lines=26) @@
1776		'img': [i['content'] for i in imgs if i['content'] not in skip_imgs],
1777		}
1778
1779
1780		class SafelyEndangered(GenericNavigableComic):
1781		"""Class to retrieve Safely Endangered comics."""
1782		# Also on http://tumblr.safelyendangered.com
1783		name = 'endangered'
1784		long_name = 'Safely Endangered'
1785		url = 'http://www.safelyendangered.com'
1786		get_navi_link = get_link_rel_next
1787		get_first_comic_link = simulate_first_link
1788		first_url = 'http://www.safelyendangered.com/comic/ignored/'
1789
1790		@classmethod
1791		def get_comic_info(cls, soup, link):
1792		"""Get information about a particular comics."""
1793		title = soup.find('h2', class_='post-title').string
1794		date_str = soup.find('span', class_='post-date').string
1795		day = string_to_date(date_str, '%B %d, %Y')
1796		imgs = soup.find('div', id='comic').find_all('img')
1797		alt = imgs[0]['alt']
1798		assert all(i['alt'] == i['title'] for i in imgs)
1799		return {
1800		'day': day.day,
1801		'month': day.month,
1802		'year': day.year,
1803		'img': [i['src'] for i in imgs],
1804		'title': title,
1805		'alt': alt,
1806		}
1807
		@@ 2017-2041 (lines=25) @@
2014		'day': day.day,
2015		}
2016
2017
2018		class ChuckleADuck(GenericNavigableComic):
2019		"""Class to retrieve Chuckle-A-Duck comics."""
2020		name = 'chuckleaduck'
2021		long_name = 'Chuckle-A-duck'
2022		url = 'http://chuckleaduck.com'
2023		get_first_comic_link = get_div_navfirst_a
2024		get_navi_link = get_link_rel_next
2025
2026		@classmethod
2027		def get_comic_info(cls, soup, link):
2028		"""Get information about a particular comics."""
2029		date_str = soup.find('span', class_='post-date').string
2030		day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y")
2031		author = soup.find('span', class_='post-author').string
2032		div = soup.find('div', id='comic')
2033		imgs = div.find_all('img') if div else []
2034		title = imgs[0]['title'] if imgs else ""
2035		assert all(i['title'] == i['alt'] == title for i in imgs)
2036		return {
2037		'month': day.month,
2038		'year': day.year,
2039		'day': day.day,
2040		'img': [i['src'] for i in imgs],
2041		'title': title,
2042		'author': author,
2043		}
2044

SylvainDe / ComicBookMaker

Code Duplication Length = 24-28 lines in 14 locations

comics.py 14 locations