SylvainDe / ComicBookMaker

    url = 'http://www.horovitzcomics.com'

    _categories = ('HOROVITZ', )

    img_re = re.compile('.*comics/([0-9]*)/([0-9]*)/([0-9]*)/.*$')

    link_re = NotImplemented

    get_url_from_archive_element = join_cls_url_to_href

    @classmethod

    def get_comic_info(cls, soup, link):

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

        href = link['href']

        num = int(cls.link_re.match(href).groups()[0])

        title = link.string

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

        assert len(imgs) == 1

        year, month, day = [int(s)

                            for s in cls.img_re.match(imgs[0]['src']).groups()]

        return {

            'title': title,

            'day': day,

            'month': month,

            'year': year,

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

            'num': num,

    get_first_comic_link = get_div_navfirst_a

    get_navi_link = get_link_rel_next

    get_url_from_link = join_cls_url_to_href

    @classmethod

    def get_comic_info(cls, soup, link):

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

        short_url_re = re.compile('^%s/\\?p=([0-9]*)' % cls.url)

        short_url = cls.get_url_from_link(soup.find('link', rel='shortlink'))

        num = int(short_url_re.match(short_url).groups()[0])

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

        assert len(imgs) == 1

        title = imgs[0]['alt']

        title2 = imgs[0]['title']

        return {

            'short_url': short_url,

            'title': title,

            'title2': title2,

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

            'num': num,

        }