SylvainDe / ComicBookMaker

class PenelopeBagieu(GenericNavigableComic):

    """Class to retrieve comics from Penelope Bagieu's blog."""

    name = 'bagieu'

    long_name = 'Ma vie est tout a fait fascinante (Bagieu)'

    url = 'http://www.penelope-jolicoeur.com'

    _categories = ('FRANCAIS', )

    get_navi_link = get_link_rel_next

    get_first_comic_link = simulate_first_link

    first_url = 'http://www.penelope-jolicoeur.com/2007/02/ma-vie-mon-oeuv.html'

    @classmethod

    def get_comic_info(cls, soup, link):

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

        date_str = soup.find('h2', class_='date-header').string

        day = string_to_date(date_str, "%A %d %B %Y", "fr_FR.utf8")

        imgs = soup.find('div', class_='entry-body').find_all('img')

        title = soup.find('h3', class_='entry-header').string

        return {

            'title': title,

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

            'month': day.month,

            'year': day.year,

            'day': day.day,

        }

class OneOneOneOneComic(GenericNavigableComic):

    """Class to retrieve 1111 Comics."""

    """Class to retrieve the Wondermark comics."""

    name = 'wondermark'

    long_name = 'Wondermark'

    url = 'http://wondermark.com'

    get_url_from_archive_element = get_href

    @classmethod

    def get_archive_elements(cls):

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

        return reversed(get_soup_at_url(archive_url).find_all('a', rel='bookmark'))

    @classmethod

    def get_comic_info(cls, soup, link):

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

        date_str = soup.find('div', class_='postdate').find('em').string

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

        div = soup.find('div', id='comic')

        if div:

            img = div.find('img')

            img_src = [img['src']]

            alt = img['alt']

            assert alt == img['title']

            title = soup.find('meta', property='og:title')['content']

        else:

            img_src = []

            alt = ''

            title = ''