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


        }


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
        }



        }


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
        }



        }


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 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 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
        }



        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,
        }



    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,
        }



        }


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
        }



        }


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 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,
        }



    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 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,
        }



		@@ 2516-2543 (lines=28) @@
2513		}
2514
2515
2516		class TalesOfAbsurdity(GenericNavigableComic):
2517		"""Class to retrieve Tales Of Absurdity comics."""
2518		# Also on http://tapastic.com/series/Tales-Of-Absurdity
2519		# Also on http://talesofabsurdity.tumblr.com
2520		name = 'absurdity'
2521		long_name = 'Tales of Absurdity'
2522		url = 'http://talesofabsurdity.com'
2523		get_first_comic_link = get_a_navi_navifirst
2524		get_navi_link = get_a_navi_comicnavnext_navinext
2525
2526		@classmethod
2527		def get_comic_info(cls, soup, link):
2528		"""Get information about a particular comics."""
2529		title = soup.find('h2', class_='post-title').string
2530		author = soup.find("span", class_="post-author").find("a").string
2531		date_str = soup.find("span", class_="post-date").string
2532		day = string_to_date(date_str, "%B %d, %Y")
2533		imgs = soup.find("div", id="comic").find_all("img")
2534		assert all(i['alt'] == i['title'] for i in imgs)
2535		alt = imgs[0]['alt'] if imgs else ""
2536		return {
2537		'img': [i['src'] for i in imgs],
2538		'title': title,
2539		'alt': alt,
2540		'author': author,
2541		'day': day.day,
2542		'month': day.month,
2543		'year': day.year
2544		}
2545
2546
		@@ 2486-2512 (lines=27) @@
2483		}
2484
2485
2486		class LastPlaceComics(GenericNavigableComic):
2487		"""Class to retrieve Last Place Comics."""
2488		name = 'lastplace'
2489		long_name = 'Last Place Comics'
2490		url = "http://lastplacecomics.com"
2491		get_first_comic_link = get_a_comicnavbase_comicnavfirst
2492		get_navi_link = get_link_rel_next
2493
2494		@classmethod
2495		def get_comic_info(cls, soup, link):
2496		"""Get information about a particular comics."""
2497		title = soup.find('h2', class_='post-title').string
2498		author = soup.find("span", class_="post-author").find("a").string
2499		date_str = soup.find("span", class_="post-date").string
2500		day = string_to_date(date_str, "%B %d, %Y")
2501		imgs = soup.find("div", id="comic").find_all("img")
2502		assert all(i['alt'] == i['title'] for i in imgs)
2503		assert len(imgs) <= 1
2504		alt = imgs[0]['alt'] if imgs else ""
2505		return {
2506		'img': [i['src'] for i in imgs],
2507		'title': title,
2508		'alt': alt,
2509		'author': author,
2510		'day': day.day,
2511		'month': day.month,
2512		'year': day.year
2513		}
2514
2515
		@@ 2376-2402 (lines=27) @@
2373		}
2374
2375
2376		class BiterComics(GenericNavigableComic):
2377		"""Class to retrieve Biter Comics."""
2378		name = "biter"
2379		long_name = "Biter Comics"
2380		url = "http://www.bitercomics.com"
2381		get_first_comic_link = get_a_navi_navifirst
2382		get_navi_link = get_link_rel_next
2383
2384		@classmethod
2385		def get_comic_info(cls, soup, link):
2386		"""Get information about a particular comics."""
2387		title = soup.find("h1", class_="entry-title").string
2388		author = soup.find("span", class_="author vcard").find("a").string
2389		date_str = soup.find("span", class_="entry-date").string
2390		day = string_to_date(date_str, "%B %d, %Y")
2391		imgs = soup.find("div", id="comic").find_all("img")
2392		assert all(i['alt'] == i['title'] for i in imgs)
2393		assert len(imgs) == 1
2394		alt = imgs[0]['alt']
2395		return {
2396		'img': [i['src'] for i in imgs],
2397		'title': title,
2398		'alt': alt,
2399		'author': author,
2400		'day': day.day,
2401		'month': day.month,
2402		'year': day.year
2403		}
2404
2405
		@@ 1808-1834 (lines=27) @@
1805		}
1806
1807
1808		class PicturesInBoxes(GenericNavigableComic):
1809		"""Class to retrieve Pictures In Boxes comics."""
1810		# Also on http://picturesinboxescomic.tumblr.com
1811		name = 'picturesinboxes'
1812		long_name = 'Pictures in Boxes'
1813		url = 'http://www.picturesinboxes.com'
1814		get_navi_link = get_a_navi_navinext
1815		get_first_comic_link = simulate_first_link
1816		first_url = 'http://www.picturesinboxes.com/2013/10/26/tetris/'
1817
1818		@classmethod
1819		def get_comic_info(cls, soup, link):
1820		"""Get information about a particular comics."""
1821		title = soup.find('h2', class_='post-title').string
1822		author = soup.find("span", class_="post-author").find("a").string
1823		date_str = soup.find('span', class_='post-date').string
1824		day = string_to_date(date_str, '%B %d, %Y')
1825		imgs = soup.find('div', class_='comicpane').find_all('img')
1826		assert imgs
1827		assert all(i['title'] == i['alt'] == title for i in imgs)
1828		return {
1829		'day': day.day,
1830		'month': day.month,
1831		'year': day.year,
1832		'img': [i['src'] for i in imgs],
1833		'title': title,
1834		'author': author,
1835		}
1836
1837
		@@ 2319-2344 (lines=26) @@
2316		}
2317
2318
2319		class GerbilWithAJetpack(GenericNavigableComic):
2320		"""Class to retrieve GerbilWithAJetpack comics."""
2321		name = 'gerbil'
2322		long_name = 'Gerbil With A Jetpack'
2323		url = 'http://gerbilwithajetpack.com'
2324		get_first_comic_link = get_a_navi_navifirst
2325		get_navi_link = get_a_rel_next
2326
2327		@classmethod
2328		def get_comic_info(cls, soup, link):
2329		"""Get information about a particular comics."""
2330		title = soup.find('h2', class_='post-title').string
2331		author = soup.find("span", class_="post-author").find("a").string
2332		date_str = soup.find("span", class_="post-date").string
2333		day = string_to_date(date_str, "%B %d, %Y")
2334		imgs = soup.find("div", id="comic").find_all("img")
2335		alt = imgs[0]['alt']
2336		assert all(i['alt'] == i['title'] == alt for i in imgs)
2337		return {
2338		'img': [i['src'] for i in imgs],
2339		'title': title,
2340		'alt': alt,
2341		'author': author,
2342		'day': day.day,
2343		'month': day.month,
2344		'year': day.year
2345		}
2346
2347
		@@ 2117-2142 (lines=26) @@
2114		return reversed(get_soup_at_url(archive_url).find('tbody').find_all('tr'))
2115
2116
2117		class HappleTea(GenericNavigableComic):
2118		"""Class to retrieve Happle Tea Comics."""
2119		name = 'happletea'
2120		long_name = 'Happle Tea'
2121		url = 'http://www.happletea.com'
2122		get_first_comic_link = get_a_navi_navifirst
2123		get_navi_link = get_link_rel_next
2124
2125		@classmethod
2126		def get_comic_info(cls, soup, link):
2127		"""Get information about a particular comics."""
2128		imgs = soup.find('div', id='comic').find_all('img')
2129		post = soup.find('div', class_='post-content')
2130		title = post.find('h2', class_='post-title').string
2131		author = post.find('a', rel='author').string
2132		date_str = post.find('span', class_='post-date').string
2133		day = string_to_date(date_str, "%B %d, %Y")
2134		assert all(i['alt'] == i['title'] for i in imgs)
2135		return {
2136		'title': title,
2137		'img': [i['src'] for i in imgs],
2138		'alt': ''.join(i['alt'] for i in imgs),
2139		'month': day.month,
2140		'year': day.year,
2141		'day': day.day,
2142		'author': author,
2143		}
2144
2145
		@@ 2657-2681 (lines=25) @@
2654		first_url = 'http://www.commitstrip.com/en/2012/02/22/interview/'
2655
2656
2657		class GenericBoumerie(GenericNavigableComic):
2658		"""Generic class to retrieve Boumeries comics in different languages."""
2659		get_first_comic_link = get_a_navi_navifirst
2660		get_navi_link = get_link_rel_next
2661		date_format = NotImplemented
2662		lang = NotImplemented
2663
2664		@classmethod
2665		def get_comic_info(cls, soup, link):
2666		"""Get information about a particular comics."""
2667		title = soup.find('h2', class_='post-title').string
2668		short_url = soup.find('link', rel='shortlink')['href']
2669		author = soup.find("span", class_="post-author").find("a").string
2670		date_str = soup.find('span', class_='post-date').string
2671		day = string_to_date(date_str, cls.date_format, cls.lang)
2672		imgs = soup.find('div', id='comic').find_all('img')
2673		assert all(i['alt'] == i['title'] for i in imgs)
2674		return {
2675		'short_url': short_url,
2676		'img': [i['src'] for i in imgs],
2677		'title': title,
2678		'author': author,
2679		'month': day.month,
2680		'year': day.year,
2681		'day': day.day,
2682		}
2683
2684
		@@ 2348-2372 (lines=25) @@
2345		}
2346
2347
2348		class EveryDayBlues(GenericNavigableComic):
2349		"""Class to retrieve EveryDayBlues Comics."""
2350		name = "blues"
2351		long_name = "Every Day Blues"
2352		url = "http://everydayblues.net"
2353		get_first_comic_link = get_a_navi_navifirst
2354		get_navi_link = get_link_rel_next
2355
2356		@classmethod
2357		def get_comic_info(cls, soup, link):
2358		"""Get information about a particular comics."""
2359		title = soup.find("h2", class_="post-title").string
2360		author = soup.find("span", class_="post-author").find("a").string
2361		date_str = soup.find("span", class_="post-date").string
2362		day = string_to_date(date_str, "%d. %B %Y", "de_DE.utf8")
2363		imgs = soup.find("div", id="comic").find_all("img")
2364		assert all(i['alt'] == i['title'] == title for i in imgs)
2365		assert len(imgs) <= 1
2366		return {
2367		'img': [i['src'] for i in imgs],
2368		'title': title,
2369		'author': author,
2370		'day': day.day,
2371		'month': day.month,
2372		'year': day.year
2373		}
2374
2375
		@@ 1697-1721 (lines=25) @@
1694		}
1695
1696
1697		class MouseBearComedy(GenericNavigableComic):
1698		"""Class to retrieve Mouse Bear Comedy comics."""
1699		# Also on http://mousebearcomedy.tumblr.com
1700		name = 'mousebear'
1701		long_name = 'Mouse Bear Comedy'
1702		url = 'http://www.mousebearcomedy.com'
1703		get_first_comic_link = get_a_navi_navifirst
1704		get_navi_link = get_a_navi_comicnavnext_navinext
1705
1706		@classmethod
1707		def get_comic_info(cls, soup, link):
1708		"""Get information about a particular comics."""
1709		title = soup.find('h2', class_='post-title').string
1710		author = soup.find("span", class_="post-author").find("a").string
1711		date_str = soup.find("span", class_="post-date").string
1712		day = string_to_date(date_str, '%B %d, %Y')
1713		imgs = soup.find("div", id="comic").find_all("img")
1714		assert all(i['alt'] == i['title'] == title for i in imgs)
1715		return {
1716		'day': day.day,
1717		'month': day.month,
1718		'year': day.year,
1719		'img': [i['src'] for i in imgs],
1720		'title': title,
1721		'author': author,
1722		}
1723
1724
		@@ 1104-1127 (lines=24) @@
1101		url = 'http://english.bouletcorp.com'
1102
1103
1104		class AmazingSuperPowers(GenericNavigableComic):
1105		"""Class to retrieve Amazing Super Powers comics."""
1106		name = 'asp'
1107		long_name = 'Amazing Super Powers'
1108		url = 'http://www.amazingsuperpowers.com'
1109		get_first_comic_link = get_a_navi_navifirst
1110		get_navi_link = get_a_navi_navinext
1111
1112		@classmethod
1113		def get_comic_info(cls, soup, link):
1114		"""Get information about a particular comics."""
1115		author = soup.find("span", class_="post-author").find("a").string
1116		date_str = soup.find('span', class_='post-date').string
1117		day = string_to_date(date_str, "%B %d, %Y")
1118		imgs = soup.find('div', id='comic').find_all('img')
1119		title = ' '.join(i['title'] for i in imgs)
1120		assert all(i['alt'] == i['title'] for i in imgs)
1121		return {
1122		'title': title,
1123		'author': author,
1124		'img': [img['src'] for img in imgs],
1125		'day': day.day,
1126		'month': day.month,
1127		'year': day.year
1128		}
1129
1130
		@@ 2736-2762 (lines=27) @@
2733		}
2734
2735
2736		class Optipess(GenericNavigableComic):
2737		"""Class to retrieve Optipess comics."""
2738		name = 'optipess'
2739		long_name = 'Optipess'
2740		url = 'http://www.optipess.com'
2741		get_first_comic_link = get_a_navi_navifirst
2742		get_navi_link = get_link_rel_next
2743
2744		@classmethod
2745		def get_comic_info(cls, soup, link):
2746		"""Get information about a particular comics."""
2747		title = soup.find('h2', class_='post-title').string
2748		author = soup.find("span", class_="post-author").find("a").string
2749		comic = soup.find('div', id='comic')
2750		imgs = comic.find_all('img') if comic else []
2751		alt = imgs[0]['title'] if imgs else ""
2752		assert all(i['alt'] == i['title'] == alt for i in imgs)
2753		date_str = soup.find('span', class_='post-date').string
2754		day = string_to_date(date_str, "%B %d, %Y")
2755		return {
2756		'title': title,
2757		'alt': alt,
2758		'author': author,
2759		'img': [i['src'] for i in imgs],
2760		'month': day.month,
2761		'year': day.year,
2762		'day': day.day,
2763		}
2764
2765
		@@ 1930-1956 (lines=27) @@
1927		url = 'http://tubeytoons.com'
1928
1929
1930		class CompletelySeriousComics(GenericNavigableComic):
1931		"""Class to retrieve Completely Serious comics."""
1932		name = 'completelyserious'
1933		long_name = 'Completely Serious Comics'
1934		url = 'http://completelyseriouscomics.com'
1935		get_first_comic_link = get_a_navi_navifirst
1936		get_navi_link = get_a_navi_navinext
1937
1938		@classmethod
1939		def get_comic_info(cls, soup, link):
1940		"""Get information about a particular comics."""
1941		title = soup.find('h2', class_='post-title').string
1942		author = soup.find('span', class_='post-author').contents[1].string
1943		date_str = soup.find('span', class_='post-date').string
1944		day = string_to_date(date_str, '%B %d, %Y')
1945		imgs = soup.find('div', class_='comicpane').find_all('img')
1946		assert imgs
1947		alt = imgs[0]['title']
1948		assert all(i['title'] == i['alt'] == alt for i in imgs)
1949		return {
1950		'month': day.month,
1951		'year': day.year,
1952		'day': day.day,
1953		'img': [i['src'] for i in imgs],
1954		'title': title,
1955		'alt': alt,
1956		'author': author,
1957		}
1958
1959
		@@ 1779-1804 (lines=26) @@
1776		}
1777
1778
1779		class SafelyEndangered(GenericNavigableComic):
1780		"""Class to retrieve Safely Endangered comics."""
1781		# Also on http://tumblr.safelyendangered.com
1782		name = 'endangered'
1783		long_name = 'Safely Endangered'
1784		url = 'http://www.safelyendangered.com'
1785		get_navi_link = get_link_rel_next
1786		get_first_comic_link = simulate_first_link
1787		first_url = 'http://www.safelyendangered.com/comic/ignored/'
1788
1789		@classmethod
1790		def get_comic_info(cls, soup, link):
1791		"""Get information about a particular comics."""
1792		title = soup.find('h2', class_='post-title').string
1793		date_str = soup.find('span', class_='post-date').string
1794		day = string_to_date(date_str, '%B %d, %Y')
1795		imgs = soup.find('div', id='comic').find_all('img')
1796		alt = imgs[0]['alt']
1797		assert all(i['alt'] == i['title'] for i in imgs)
1798		return {
1799		'day': day.day,
1800		'month': day.month,
1801		'year': day.year,
1802		'img': [i['src'] for i in imgs],
1803		'title': title,
1804		'alt': alt,
1805		}
1806
1807
		@@ 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

SylvainDe / ComicBookMaker

Code Duplication Length = 24-28 lines in 14 locations

comics.py 14 locations