Code Duplication    Length = 19-20 lines in 2 locations

comics.py 2 locations

@@ 2393-2412 (lines=20) @@
2390
        link = td_comic.find('a')
2391
        return urljoin_wrapper(cls.url, link['href'])
2392
2393
    @classmethod
2394
    def get_comic_info(cls, soup, tr):
2395
        """Get information about a particular comics."""
2396
        td_num, td_comic, td_date, _ = tr.find_all('td')
2397
        num = int(td_num.string)
2398
        link = td_comic.find('a')
2399
        title = link.string
2400
        imgs = soup.find_all('img', id='comic_image')
2401
        date_str = td_date.string
2402
        day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y, %I:%M %p")
2403
        assert len(imgs) == 1, imgs
2404
        assert all(i.get('alt') == i.get('title') for i in imgs)
2405
        return {
2406
            'num': num,
2407
            'title': title,
2408
            'alt': imgs[0].get('alt', ''),
2409
            'img': [i['src'] for i in imgs],
2410
            'month': day.month,
2411
            'year': day.year,
2412
            'day': day.day,
2413
        }
2414
2415
@@ 2010-2028 (lines=19) @@
2007
    def get_url_from_archive_element(cls, td):
2008
        return td.find('a')['href']
2009
2010
    @classmethod
2011
    def get_comic_info(cls, soup, td):
2012
        """Get information about a particular comics."""
2013
        url = cls.get_url_from_archive_element(td)
2014
        title = td.find('a').string
2015
        month_and_day = td.previous_sibling.string
2016
        link_re = re.compile('^%s/([0-9]+)/' % cls.url)
2017
        year = link_re.match(url).groups()[0]
2018
        date_str = month_and_day + ' ' + year
2019
        day = string_to_date(date_str, '%b %d %Y')
2020
        imgs = [soup.find('div', id='comic').find('img')]
2021
        assert len(imgs) == 1, imgs
2022
        assert all(i['title'] == i['alt'] == title for i in imgs)
2023
        return {
2024
            'month': day.month,
2025
            'year': day.year,
2026
            'day': day.day,
2027
            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],
2028
            'title': title,
2029
        }
2030
2031