SylvainDe / ComicBookMaker

class BoumerieFr(GenericBoumerie):

    """Class to retrieve Boumeries comics in French."""

    name = 'boumeries_fr'

    long_name = 'Boumeries (Fr)'

    url = 'http://bd.boumerie.com'

    date_format = "%A, %d %B %Y"

    lang = "fr_FR.utf8"

class UnearthedComics(GenericNavigableComic):

    """Class to retrieve Unearthed comics."""

    # Also on http://tapastic.com/series/UnearthedComics

    # Also on http://unearthedcomics.tumblr.com

    name = 'unearthed'

    long_name = 'Unearthed Comics'

    url = 'http://unearthedcomics.com'

    get_navi_link = get_link_rel_next

    @classmethod

    def get_first_comic_link(cls):

        """Get link to first comics."""

        return {'href': 'http://unearthedcomics.com/comics/world-with-turn-signals/'}

    @classmethod

    def get_comic_info(cls, soup, link):

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

        short_url = soup.find('link', rel='shortlink')['href']

        title_elt = soup.find('h1') or soup.find('h2')

        title = title_elt.string if title_elt else ""

        desc = soup.find('meta', property='og:description')

        date_str = soup.find('time', class_='published updated hidden')['datetime']

        day = string_to_date(date_str, "%Y-%m-%d")

        post = soup.find('div', class_="entry content entry-content type-portfolio")

        imgs = post.find_all('img')

        return {

            'title': title,

            'description': desc,

            'url2': short_url,

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

        return "http://uneanneeaulycee.blog.lemonde.fr/2016/06/13/la-semaine-du-bac-est-arrivee/"

class Rall(GenericNavigableComic):

    """Class to retrieve Ted Rall comics."""

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

    name = 'rall'

    long_name = "Ted Rall"

    url = "http://rall.com/comic"

    get_navi_link = get_link_rel_next

    @classmethod

    def get_first_comic_link(cls):

        """Get link to first comics."""

        # Not the first but I didn't find an efficient way to retrieve it

        return {'href': "http://rall.com/2014/01/30/los-angeles-times-cartoon-well-miss-those-california-flowers"}

    @classmethod

    def get_comic_info(cls, soup, link):

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

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

        author = soup.find("span", class_="author vcard").find("a").string

        date_str = soup.find("span", class_="entry-date").string

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

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

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

        imgs = imgs[:-7]  # remove social media buttons

        return {

            'title': title,

            'author': author,

            'month': day.month,

            'year': day.year,

            'day': day.day,

            'description': desc,

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

        }