Code Duplication    Length = 23-27 lines in 3 locations

comics.py 3 locations

@@ 1430-1456 (lines=27) @@
1427
        }
1428
1429
1430
class ButterSafe(GenericListableComic):
1431
    """Class to retrieve Butter Safe comics."""
1432
    name = 'butter'
1433
    long_name = 'ButterSafe'
1434
    url = 'http://buttersafe.com'
1435
    get_url_from_archive_element = get_href
1436
    comic_link_re = re.compile('^%s/([0-9]*)/([0-9]*)/([0-9]*)/.*' % url)
1437
1438
    @classmethod
1439
    def get_archive_elements(cls):
1440
        archive_url = urljoin_wrapper(cls.url, 'archive/')
1441
        return reversed(get_soup_at_url(archive_url).find_all('a', href=cls.comic_link_re))
1442
1443
    @classmethod
1444
    def get_comic_info(cls, soup, link):
1445
        """Get information about a particular comics."""
1446
        url = cls.get_url_from_archive_element(link)
1447
        title = link.string
1448
        year, month, day = [int(s) for s in cls.comic_link_re.match(url).groups()]
1449
        img = soup.find('div', id='comic').find('img')
1450
        assert img['alt'] == title
1451
        return {
1452
            'title': title,
1453
            'day': day,
1454
            'month': month,
1455
            'year': year,
1456
            'img': [img['src']],
1457
        }
1458
1459
@@ 2426-2450 (lines=25) @@
2423
        }
2424
2425
2426
class JuliasDrawings(GenericListableComic):
2427
    """Class to retrieve Julia's Drawings."""
2428
    name = 'julia'
2429
    long_name = "Julia's Drawings"
2430
    url = 'https://drawings.jvns.ca'
2431
    get_url_from_archive_element = get_href
2432
2433
    @classmethod
2434
    def get_archive_elements(cls):
2435
        div = get_soup_at_url(cls.url).find('div', class_='drawings')
2436
        return reversed(div.find_all('a'))
2437
2438
    @classmethod
2439
    def get_comic_info(cls, soup, archive_elt):
2440
        """Get information about a particular comics."""
2441
        date_str = soup.find('meta', property='og:article:published_time')['content'][:10]
2442
        day = string_to_date(date_str, "%Y-%m-%d")
2443
        title = soup.find('h3', class_='p-post-title').string
2444
        imgs = soup.find('section', class_='post-content').find_all('img')
2445
        return {
2446
            'title': title,
2447
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
2448
            'month': day.month,
2449
            'year': day.year,
2450
            'day': day.day,
2451
        }
2452
2453
@@ 1496-1518 (lines=23) @@
1493
                        last_date = comic_date
1494
1495
1496
class AbstruseGoose(GenericListableComic):
1497
    """Class to retrieve AbstruseGoose Comics."""
1498
    name = 'abstruse'
1499
    long_name = 'Abstruse Goose'
1500
    url = 'http://abstrusegoose.com'
1501
    get_url_from_archive_element = get_href
1502
    comic_url_re = re.compile('^%s/([0-9]*)$' % url)
1503
    comic_img_re = re.compile('^%s/strips/.*' % url)
1504
1505
    @classmethod
1506
    def get_archive_elements(cls):
1507
        archive_url = urljoin_wrapper(cls.url, 'archive')
1508
        return get_soup_at_url(archive_url).find_all('a', href=cls.comic_url_re)
1509
1510
    @classmethod
1511
    def get_comic_info(cls, soup, archive_elt):
1512
        comic_url = cls.get_url_from_archive_element(archive_elt)
1513
        num = int(cls.comic_url_re.match(comic_url).groups()[0])
1514
        imgs = soup.find_all('img', src=cls.comic_img_re)
1515
        return {
1516
            'num': num,
1517
            'title': archive_elt.string,
1518
            'img': [i['src'] for i in imgs],
1519
        }
1520
1521