Code Duplication    Length = 30-31 lines in 2 locations

comics.py 2 locations

@@ 2814-2844 (lines=31) @@
2811
    date_format = "%A, %d %B %Y"
2812
    lang = "fr_FR.utf8"
2813
2814
2815
class UnearthedComics(GenericNavigableComic):
2816
    """Class to retrieve Unearthed comics."""
2817
    # Also on http://tapastic.com/series/UnearthedComics
2818
    # Also on http://unearthedcomics.tumblr.com
2819
    name = 'unearthed'
2820
    long_name = 'Unearthed Comics'
2821
    url = 'http://unearthedcomics.com'
2822
    _categories = ('UNEARTHED', )
2823
    get_navi_link = get_link_rel_next
2824
    get_first_comic_link = simulate_first_link
2825
    first_url = 'http://unearthedcomics.com/comics/world-with-turn-signals/'
2826
2827
    @classmethod
2828
    def get_comic_info(cls, soup, link):
2829
        """Get information about a particular comics."""
2830
        short_url = soup.find('link', rel='shortlink')['href']
2831
        title_elt = soup.find('h1') or soup.find('h2')
2832
        title = title_elt.string if title_elt else ""
2833
        desc = soup.find('meta', property='og:description')
2834
        date_str = soup.find('time', class_='published updated hidden')['datetime']
2835
        day = string_to_date(date_str, "%Y-%m-%d")
2836
        post = soup.find('div', class_="entry content entry-content type-portfolio")
2837
        imgs = post.find_all('img')
2838
        return {
2839
            'title': title,
2840
            'description': desc,
2841
            'url2': short_url,
2842
            'img': [i['src'] for i in imgs],
2843
            'month': day.month,
2844
            'year': day.year,
2845
            'day': day.day,
2846
        }
2847
@@ 473-502 (lines=30) @@
470
    first_url = "http://uneanneeaulycee.blog.lemonde.fr/2016/06/13/la-semaine-du-bac-est-arrivee/"
471
472
473
class Rall(GenericNavigableComic):
474
    """Class to retrieve Ted Rall comics."""
475
    # Also on http://www.gocomics.com/tedrall
476
    name = 'rall'
477
    long_name = "Ted Rall"
478
    url = "http://rall.com/comic"
479
    _categories = ('RALL', )
480
    get_navi_link = get_link_rel_next
481
    get_first_comic_link = simulate_first_link
482
    # Not the first but I didn't find an efficient way to retrieve it
483
    first_url = "http://rall.com/2014/01/30/los-angeles-times-cartoon-well-miss-those-california-flowers"
484
485
    @classmethod
486
    def get_comic_info(cls, soup, link):
487
        """Get information about a particular comics."""
488
        title = soup.find('meta', property='og:title')['content']
489
        author = soup.find("span", class_="author vcard").find("a").string
490
        date_str = soup.find("span", class_="entry-date").string
491
        day = string_to_date(date_str, "%B %d, %Y")
492
        desc = soup.find('meta', property='og:description')['content']
493
        imgs = soup.find('div', class_='entry-content').find_all('img')
494
        imgs = imgs[:-7]  # remove social media buttons
495
        return {
496
            'title': title,
497
            'author': author,
498
            'month': day.month,
499
            'year': day.year,
500
            'day': day.day,
501
            'description': desc,
502
            'img': [i['src'] for i in imgs],
503
        }
504
505