Code Duplication    Length = 22-27 lines in 2 locations

comics.py 2 locations

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