Code Duplication    Length = 23-27 lines in 3 locations

comics.py 3 locations

@@ 1407-1433 (lines=27) @@
1404
        }
1405
1406
1407
class ButterSafe(GenericListableComic):
1408
    """Class to retrieve Butter Safe comics."""
1409
    name = 'butter'
1410
    long_name = 'ButterSafe'
1411
    url = 'http://buttersafe.com'
1412
    get_url_from_archive_element = get_href
1413
    comic_link_re = re.compile('^%s/([0-9]*)/([0-9]*)/([0-9]*)/.*' % url)
1414
1415
    @classmethod
1416
    def get_archive_elements(cls):
1417
        archive_url = urljoin_wrapper(cls.url, 'archive/')
1418
        return reversed(get_soup_at_url(archive_url).find_all('a', href=cls.comic_link_re))
1419
1420
    @classmethod
1421
    def get_comic_info(cls, soup, link):
1422
        """Get information about a particular comics."""
1423
        url = cls.get_url_from_archive_element(link)
1424
        title = link.string
1425
        year, month, day = [int(s) for s in cls.comic_link_re.match(url).groups()]
1426
        img = soup.find('div', id='comic').find('img')
1427
        assert img['alt'] == title
1428
        return {
1429
            'title': title,
1430
            'day': day,
1431
            'month': month,
1432
            'year': year,
1433
            'img': [img['src']],
1434
        }
1435
1436
@@ 1473-1495 (lines=23) @@
1470
                        last_date = comic_date
1471
1472
1473
class AbstruseGoose(GenericListableComic):
1474
    """Class to retrieve AbstruseGoose Comics."""
1475
    name = 'abstruse'
1476
    long_name = 'Abstruse Goose'
1477
    url = 'http://abstrusegoose.com'
1478
    get_url_from_archive_element = get_href
1479
    comic_url_re = re.compile('^%s/([0-9]*)$' % url)
1480
    comic_img_re = re.compile('^%s/strips/.*' % url)
1481
1482
    @classmethod
1483
    def get_archive_elements(cls):
1484
        archive_url = urljoin_wrapper(cls.url, 'archive')
1485
        return get_soup_at_url(archive_url).find_all('a', href=cls.comic_url_re)
1486
1487
    @classmethod
1488
    def get_comic_info(cls, soup, archive_elt):
1489
        comic_url = cls.get_url_from_archive_element(archive_elt)
1490
        num = int(cls.comic_url_re.match(comic_url).groups()[0])
1491
        imgs = soup.find_all('img', src=cls.comic_img_re)
1492
        return {
1493
            'num': num,
1494
            'title': archive_elt.string,
1495
            'img': [i['src'] for i in imgs],
1496
        }
1497
1498
@@ 2374-2398 (lines=25) @@
2371
        }
2372
2373
2374
class JuliasDrawings(GenericListableComic):
2375
    """Class to retrieve Julia's Drawings."""
2376
    name = 'julia'
2377
    long_name = "Julia's Drawings"
2378
    url = 'https://drawings.jvns.ca'
2379
    get_url_from_archive_element = get_href
2380
2381
    @classmethod
2382
    def get_archive_elements(cls):
2383
        div = get_soup_at_url(cls.url).find('div', class_='drawings')
2384
        return reversed(div.find_all('a'))
2385
2386
    @classmethod
2387
    def get_comic_info(cls, soup, archive_elt):
2388
        """Get information about a particular comics."""
2389
        date_str = soup.find('meta', property='og:article:published_time')['content'][:10]
2390
        day = string_to_date(date_str, "%Y-%m-%d")
2391
        title = soup.find('h3', class_='p-post-title').string
2392
        imgs = soup.find('section', class_='post-content').find_all('img')
2393
        return {
2394
            'title': title,
2395
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
2396
            'month': day.month,
2397
            'year': day.year,
2398
            'day': day.day,
2399
        }
2400
2401