Code Duplication    Length = 22-27 lines in 2 locations

comics.py 2 locations

@@ 1386-1412 (lines=27) @@
1383
        }
1384
1385
1386
class ButterSafe(GenericListableComic):
1387
    """Class to retrieve Butter Safe comics."""
1388
    name = 'butter'
1389
    long_name = 'ButterSafe'
1390
    url = 'http://buttersafe.com'
1391
    get_url_from_archive_element = get_href
1392
    comic_link_re = re.compile('^%s/([0-9]*)/([0-9]*)/([0-9]*)/.*' % url)
1393
1394
    @classmethod
1395
    def get_archive_elements(cls):
1396
        archive_url = urljoin_wrapper(cls.url, 'archive/')
1397
        return reversed(get_soup_at_url(archive_url).find_all('a', href=cls.comic_link_re))
1398
1399
    @classmethod
1400
    def get_comic_info(cls, soup, link):
1401
        """Get information about a particular comics."""
1402
        url = cls.get_url_from_archive_element(link)
1403
        title = link.string
1404
        year, month, day = [int(s) for s in cls.comic_link_re.match(url).groups()]
1405
        img = soup.find('div', id='comic').find('img')
1406
        assert img['alt'] == title
1407
        return {
1408
            'title': title,
1409
            'day': day,
1410
            'month': month,
1411
            'year': year,
1412
            'img': [img['src']],
1413
        }
1414
1415
@@ 1452-1473 (lines=22) @@
1449
                        last_date = comic_date
1450
1451
1452
class AbstruseGoose(GenericListableComic):
1453
    """Class to retrieve AbstruseGoose Comics."""
1454
    name = 'abstruse'
1455
    long_name = 'Abstruse Goose'
1456
    url = 'http://abstrusegoose.com'
1457
    get_url_from_archive_element = get_href
1458
    comic_url_re = re.compile('^%s/([0-9]*)$' % url)
1459
    comic_img_re = re.compile('^%s/strips/.*' % url)
1460
1461
    @classmethod
1462
    def get_archive_elements(cls):
1463
        archive_url = urljoin_wrapper(cls.url, 'archive')
1464
        return get_soup_at_url(archive_url).find_all('a', href=cls.comic_url_re)
1465
1466
    @classmethod
1467
    def get_comic_info(cls, soup, archive_elt):
1468
        comic_url = cls.get_url_from_archive_element(archive_elt)
1469
        num = int(cls.comic_url_re.match(comic_url).groups()[0])
1470
        return {
1471
            'num': num,
1472
            'title': archive_elt.string,
1473
            'img': [soup.find('img', src=cls.comic_img_re)['src']]
1474
        }
1475
1476