Code Duplication    Length = 22-27 lines in 2 locations

comics.py 2 locations

@@ 1309-1335 (lines=27) @@
1306
        }
1307
1308
1309
class ButterSafe(GenericListableComic):
1310
    """Class to retrieve Butter Safe comics."""
1311
    name = 'butter'
1312
    long_name = 'ButterSafe'
1313
    url = 'http://buttersafe.com'
1314
    get_url_from_archive_element = get_href
1315
    comic_link_re = re.compile('^%s/([0-9]*)/([0-9]*)/([0-9]*)/.*' % url)
1316
1317
    @classmethod
1318
    def get_archive_elements(cls):
1319
        archive_url = urljoin_wrapper(cls.url, 'archive/')
1320
        return reversed(get_soup_at_url(archive_url).find_all('a', href=cls.comic_link_re))
1321
1322
    @classmethod
1323
    def get_comic_info(cls, soup, link):
1324
        """Get information about a particular comics."""
1325
        url = cls.get_url_from_archive_element(link)
1326
        title = link.string
1327
        year, month, day = [int(s) for s in cls.comic_link_re.match(url).groups()]
1328
        img = soup.find('div', id='comic').find('img')
1329
        assert img['alt'] == title
1330
        return {
1331
            'title': title,
1332
            'day': day,
1333
            'month': month,
1334
            'year': year,
1335
            'img': [img['src']],
1336
        }
1337
1338
@@ 1374-1395 (lines=22) @@
1371
                        last_date = comic_date
1372
1373
1374
class AbstruseGoose(GenericListableComic):
1375
    """Class to retrieve AbstruseGoose Comics."""
1376
    name = 'abstruse'
1377
    long_name = 'Abstruse Goose'
1378
    url = 'http://abstrusegoose.com'
1379
    get_url_from_archive_element = get_href
1380
    comic_url_re = re.compile('^%s/([0-9]*)$' % url)
1381
    comic_img_re = re.compile('^%s/strips/.*' % url)
1382
1383
    @classmethod
1384
    def get_archive_elements(cls):
1385
        archive_url = urljoin_wrapper(cls.url, 'archive')
1386
        return get_soup_at_url(archive_url).find_all('a', href=cls.comic_url_re)
1387
1388
    @classmethod
1389
    def get_comic_info(cls, soup, archive_elt):
1390
        comic_url = cls.get_url_from_archive_element(archive_elt)
1391
        num = int(cls.comic_url_re.match(comic_url).groups()[0])
1392
        return {
1393
            'num': num,
1394
            'title': archive_elt.string,
1395
            'img': [soup.find('img', src=cls.comic_img_re)['src']]
1396
        }
1397
1398