SylvainDe / ComicBookMaker

class DinosaurComics(GenericListableComic):

    """Class to retrieve Dinosaur Comics comics."""

    name = 'dinosaur'

    long_name = 'Dinosaur Comics'

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

    get_url_from_archive_element = get_href

    comic_link_re = re.compile('^%s/index.php\\?comic=([0-9]*)$' % url)

    @classmethod

    def get_archive_elements(cls):

        archive_url = urljoin_wrapper(cls.url, 'archive.php')

        # first link is random -> skip it

        return reversed(get_soup_at_url(archive_url).find_all('a', href=cls.comic_link_re)[1:])

    @classmethod

    def get_comic_info(cls, soup, link):

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

        url = cls.get_url_from_archive_element(link)

        num = int(cls.comic_link_re.match(url).groups()[0])

        date_str = link.string

        text = link.next_sibling.string

        day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y")

        comic_img_re = re.compile('^%s/comics/' % cls.url)

        img = soup.find('img', src=comic_img_re)

        return {

            'month': day.month,

            'year': day.year,

            'day': day.day,

            'img': [img.get('src')],

            'title': img.get('title'),

            'text': text,

class CalvinAndHobbes(GenericComic):

    """Class to retrieve Calvin and Hobbes comics."""

    # Also on http://www.gocomics.com/calvinandhobbes/

    name = 'calvin'

    long_name = 'Calvin and Hobbes'

    # This is not through any official webpage but eh...

    url = 'http://marcel-oehler.marcellosendos.ch/comics/ch/'

    @classmethod

    def get_next_comic(cls, last_comic):

        """Generator to get the next comic. Implementation of GenericComic's abstract method."""

        last_date = get_date_for_comic(

            last_comic) if last_comic else date(1985, 11, 1)

        link_re = re.compile('^([0-9]*)/([0-9]*)/')

        img_re = re.compile('')

        for link in get_soup_at_url(cls.url).find_all('a', href=link_re):

            url = link['href']

            year, month = link_re.match(url).groups()

            if date(int(year), int(month), 1) + timedelta(days=31) >= last_date:

                img_re = re.compile('^%s%s([0-9]*)' % (year, month))

                month_url = urljoin_wrapper(cls.url, url)

                for img in get_soup_at_url(month_url).find_all('img', src=img_re):

                    img_src = img['src']

                    day = int(img_re.match(img_src).groups()[0])

                    comic_date = date(int(year), int(month), day)

                    if comic_date > last_date:

                        yield {