SylvainDe / ComicBookMaker

    _categories = ('DELETED', )

class ExtraFabulousComics(GenericNavigableComic):

    """Class to retrieve Extra Fabulous Comics."""

    # Also on https://extrafabulouscomics.tumblr.com

    name = 'efc'

    long_name = 'Extra Fabulous Comics'

    url = 'http://extrafabulouscomics.com'

    _categories = ('EFC', )

    get_navi_link = get_link_rel_next

    get_first_comic_link = simulate_first_link

    first_url = 'http://extrafabulouscomics.com/comic/buttfly/'

    @classmethod

    def get_comic_info(cls, soup, link):

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

        img_src_re = re.compile('^%s/wp-content/uploads/' % cls.url)

        imgs = soup.find_all('img', src=img_src_re)

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

        date_str = soup.find('meta', property='article:published_time')['content'][:10]

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

        return {

            'title': title,

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

            'month': day.month,

            'year': day.year,

            'day': day.day,

            'prefix': title + '-'

        }

        }

class LinsEditions(GenericNavigableComic):

    """Class to retrieve L.I.N.S. Editions comics."""

    # Also on https://linscomics.tumblr.com

    # Now on https://warandpeas.com

    name = 'lins'

    long_name = 'L.I.N.S. Editions'

    url = 'https://linsedition.com'

    _categories = ('LINS', )

    get_navi_link = get_link_rel_next

    get_first_comic_link = simulate_first_link

    first_url = 'https://linsedition.com/2011/09/07/l-i-n-s/'

    @classmethod

    def get_comic_info(cls, soup, link):

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

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

        imgs = soup.find_all('meta', property='og:image')

        date_str = soup.find('meta', property='article:published_time')['content'][:10]

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

        return {

            'title': title,

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

            'month': day.month,

            'year': day.year,

            'day': day.day,

        }

        }

class Mercworks(GenericNavigableComic):

    """Class to retrieve Mercworks comics."""

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

    name = 'mercworks'

    long_name = 'Mercworks'

    url = 'http://mercworks.net'

    get_first_comic_link = get_a_comicnavbase_comicnavfirst

    get_navi_link = get_link_rel_next

    @classmethod

    def get_comic_info(cls, soup, link):

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

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

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

        desc = metadesc['content'] if metadesc else ""

        date_str = soup.find('meta', property='article:published_time')['content'][:10]

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

        imgs = soup.find_all('meta', property='og:image')

        return {

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

            'title': title,

            'desc': desc,

            'day': day.day,

            'month': day.month,

            'year': day.year

        }

        }

class MarketoonistComics(GenericNavigableComic):

    """Class to retrieve Marketoonist Comics."""

    name = 'marketoonist'

    long_name = 'Marketoonist'

    url = 'https://marketoonist.com/cartoons'

    get_first_comic_link = simulate_first_link

    get_navi_link = get_link_rel_next

    first_url = 'https://marketoonist.com/2002/10/the-8-types-of-brand-managers-2.html'

    @classmethod

    def get_comic_info(cls, soup, link):

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

        imgs = soup.find_all('meta', property='og:image')

        date_str = soup.find('meta', property='article:published_time')['content'][:10]

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

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

        return {

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

            'day': day.day,

            'month': day.month,

            'year': day.year,

            'title': title,

        }

        }

class GenericLeMondeBlog(GenericNavigableComic):

    """Generic class to retrieve comics from Le Monde blogs."""

    _categories = ('LEMONDE', 'FRANCAIS')

    get_navi_link = get_link_rel_next

    get_first_comic_link = simulate_first_link

    first_url = NotImplemented

    @classmethod

    def get_comic_info(cls, soup, link):

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

        url2 = soup.find('link', rel='shortlink')['href']

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

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

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

        imgs = soup.find_all('meta', property='og:image')

        return {

            'title': title,

            'url2': url2,

            'img': [convert_iri_to_plain_ascii_uri(i['content']) for i in imgs],

            'month': day.month,

            'year': day.year,

            'day': day.day,

        }

        }

class SafelyEndangered(GenericNavigableComic):

    """Class to retrieve Safely Endangered comics."""

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

    name = 'endangered'

    long_name = 'Safely Endangered'

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

    get_navi_link = get_link_rel_next

    get_first_comic_link = simulate_first_link

    first_url = 'http://www.safelyendangered.com/comic/ignored/'

    @classmethod

    def get_comic_info(cls, soup, link):

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

        title = soup.find('h2', class_='post-title').string

        date_str = soup.find('span', class_='post-date').string

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

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

        alt = imgs[0]['alt']

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

        return {

            'day': day.day,

            'month': day.month,

            'year': day.year,

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

            'title': title,

            'alt': alt,

        }

        }

class MyExtraLife(GenericNavigableComic):

    """Class to retrieve My Extra Life comics."""

    name = 'extralife'

    long_name = 'My Extra Life'

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

    get_navi_link = get_link_rel_next

    @classmethod

    def get_first_comic_link(cls):

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

        return get_soup_at_url(cls.url).find('a', class_='comic_nav_link first_comic_link')

    @classmethod

    def get_comic_info(cls, soup, link):

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

        title = soup.find("h1", class_="comic_title").string

        date_str = soup.find("span", class_="comic_date").string

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

        imgs = soup.find_all("img", class_="comic")

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

        return {

            'title': title,

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

            'day': day.day,

            'month': day.month,

            'year': day.year

        }

        }

class JuliasDrawings(GenericListableComic):

    """Class to retrieve Julia's Drawings."""

    name = 'julia'

    long_name = "Julia's Drawings"

    url = 'https://drawings.jvns.ca'

    get_url_from_archive_element = get_href

    @classmethod

    def get_archive_elements(cls):

        articles = get_soup_at_url(cls.url).find_all('article', class_='li post')

        return [art.find('a') for art in reversed(articles)]

    @classmethod

    def get_comic_info(cls, soup, archive_elt):

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

        date_str = soup.find('meta', property='og:article:published_time')['content'][:10]

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

        title = soup.find('h3', class_='p-post-title').string

        imgs = soup.find('section', class_='post-content').find_all('img')

        return {

            'title': title,

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

            'month': day.month,

            'year': day.year,

            'day': day.day,

        }