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'

    get_navi_link = get_link_rel_next

    @classmethod

    def get_first_comic_link(cls):

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

        return {'href': '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,

        }

    url = "http://itsthetie.com"

    get_first_comic_link = get_div_navfirst_a

    get_navi_link = get_a_rel_next

    @classmethod

    def get_comic_info(cls, soup, link):

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

        title = soup.find('h1', class_='comic-title').find('a').string

        date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string

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

        # Bonus images may or may not be in meta og:image.

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

        imgs_src = [i['content'] for i in imgs]

        bonus = soup.find_all('img', attrs={'data-oversrc': True})

        bonus_src = [b['data-oversrc'] for b in bonus]

        all_imgs_src = imgs_src + [s for s in bonus_src if s not in imgs_src]

        all_imgs_src = [s for s in all_imgs_src if not s.endswith("/2016/01/bonus-panel.png")]

        tag_meta = soup.find('meta', property='article:tag')

        tags = tag_meta['content'] if tag_meta else ""

        return {

            'title': title,

            'month': day.month,

            'year': day.year,

            'day': day.day,

            'img': all_imgs_src,

            'tags': tags,

        }

class PenelopeBagieu(GenericNavigableComic):

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

        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 = ''

        return {

            'month': day.month,

            'year': day.year,

            'day': day.day,

            'img': img_src,

            'title': title,

            'alt': alt,

            'tags': ' '.join(t.string for t in soup.find('div', class_='postmeta').find_all('a', rel='tag')),

        }

                if not img['src'].endswith(

                    ('link.gif', '32.png', 'twpbookad.jpg',

                     'merchad.jpg', 'header.gif', 'tipjar.jpg'))]

        return {

            'title': title.string if title else None,

            'title2': '  '.join(img.get('alt') for img in imgs if img.get('alt')),

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

        }

class DeadlyPanel(GenericEmptyComic, GenericNavigableComic):

    """Class to retrieve Deadly Panel comics."""

    # Also on https://tapastic.com/series/deadlypanel

    name = 'deadly'

    long_name = 'Deadly Panel'

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

    get_first_comic_link = get_a_navi_navifirst

    get_navi_link = get_a_navi_comicnavnext_navinext

    @classmethod

    def get_comic_info(cls, soup, link):

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

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

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

        return {

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

        }