SylvainDe / ComicBookMaker

    def get_url_from_archive_element(cls, td):

        return td.find('a')['href']

    @classmethod

    def get_comic_info(cls, soup, td):

        """Get information about a particular comics."""

        url = cls.get_url_from_archive_element(td)

        title = td.find('a').string

        month_and_day = td.previous_sibling.string

        link_re = re.compile('^%s/([0-9]+)/' % cls.url)

        year = link_re.match(url).groups()[0]

        date_str = month_and_day + ' ' + year

        day = string_to_date(date_str, '%b %d %Y')

        imgs = [soup.find('div', id='comic').find('img')]

        assert len(imgs) == 1, imgs

        assert all(i['title'] == i['alt'] == title for i in imgs)

        return {

            'month': day.month,

            'year': day.year,

            'day': day.day,

            'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs],

            'title': title,

        }

        link = td_comic.find('a')

        return urljoin_wrapper(cls.url, link['href'])

    @classmethod

    def get_comic_info(cls, soup, tr):

        """Get information about a particular comics."""

        td_num, td_comic, td_date, _ = tr.find_all('td')

        num = int(td_num.string)

        link = td_comic.find('a')

        title = link.string

        imgs = soup.find_all('img', id='comic_image')

        date_str = td_date.string

        day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y, %I:%M %p")

        assert len(imgs) == 1, imgs

        assert all(i.get('alt') == i.get('title') for i in imgs)

        return {

            'num': num,

            'title': title,

            'alt': imgs[0].get('alt', ''),

            'img': [i['src'] for i in imgs],

            'month': day.month,

            'year': day.year,

            'day': day.day,

        }