Code Duplication    Length = 30-31 lines in 2 locations

comics.py 2 locations

@@ 2863-2893 (lines=31) @@
2860
    lang = "fr_FR.utf8"
2861
2862
2863
class UnearthedComics(GenericNavigableComic):
2864
    """Class to retrieve Unearthed comics."""
2865
    # Also on http://tapastic.com/series/UnearthedComics
2866
    # Also on https://unearthedcomics.tumblr.com
2867
    name = 'unearthed'
2868
    long_name = 'Unearthed Comics'
2869
    url = 'http://unearthedcomics.com'
2870
    _categories = ('UNEARTHED', )
2871
    get_navi_link = get_link_rel_next
2872
    get_first_comic_link = simulate_first_link
2873
    first_url = 'http://unearthedcomics.com/comics/world-with-turn-signals/'
2874
2875
    @classmethod
2876
    def get_comic_info(cls, soup, link):
2877
        """Get information about a particular comics."""
2878
        short_url = soup.find('link', rel='shortlink')['href']
2879
        title_elt = soup.find('h1') or soup.find('h2')
2880
        title = title_elt.string if title_elt else ""
2881
        desc = soup.find('meta', property='og:description')
2882
        date_str = soup.find('time', class_='published updated hidden')['datetime']
2883
        day = string_to_date(date_str, "%Y-%m-%d")
2884
        post = soup.find('div', class_="entry content entry-content type-portfolio")
2885
        imgs = post.find_all('img')
2886
        return {
2887
            'title': title,
2888
            'description': desc,
2889
            'url2': short_url,
2890
            'img': [i['src'] for i in imgs],
2891
            'month': day.month,
2892
            'year': day.year,
2893
            'day': day.day,
2894
        }
2895
2896
@@ 478-507 (lines=30) @@
475
    first_url = "http://uneanneeaulycee.blog.lemonde.fr/2016/06/13/la-semaine-du-bac-est-arrivee/"
476
477
478
class Rall(GenericNavigableComic):
479
    """Class to retrieve Ted Rall comics."""
480
    # Also on http://www.gocomics.com/tedrall
481
    name = 'rall'
482
    long_name = "Ted Rall"
483
    url = "http://rall.com/comic"
484
    _categories = ('RALL', )
485
    get_navi_link = get_link_rel_next
486
    get_first_comic_link = simulate_first_link
487
    # Not the first but I didn't find an efficient way to retrieve it
488
    first_url = "http://rall.com/2014/01/30/los-angeles-times-cartoon-well-miss-those-california-flowers"
489
490
    @classmethod
491
    def get_comic_info(cls, soup, link):
492
        """Get information about a particular comics."""
493
        title = soup.find('meta', property='og:title')['content']
494
        author = soup.find("span", class_="author vcard").find("a").string
495
        date_str = soup.find("span", class_="entry-date").string
496
        day = string_to_date(date_str, "%B %d, %Y")
497
        desc = soup.find('meta', property='og:description')['content']
498
        imgs = soup.find('div', class_='entry-content').find_all('img')
499
        imgs = imgs[:-7]  # remove social media buttons
500
        return {
501
            'title': title,
502
            'author': author,
503
            'month': day.month,
504
            'year': day.year,
505
            'day': day.day,
506
            'description': desc,
507
            'img': [i['src'] for i in imgs],
508
        }
509
510