SylvainDe / ComicBookMaker

    url = 'http://theawkwardyeti.com'

    get_first_comic_link = get_a_navi_navifirst

    get_navi_link = get_link_rel_next

    @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")

        assert all(idx > 0 or i['alt'] == i['title'] for idx, i in enumerate(imgs))

        return {

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

            'title': title,

            'day': day.day,

            'month': day.month,

            'year': day.year

        }

class PleasantThoughts(GenericNavigableComic):

    """Class to retrieve Pleasant Thoughts comics."""

    name = 'pleasant'

    long_name = 'Pleasant Thoughts'

    url = 'http://pleasant-thoughts.com'

    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."""

        post = soup.find('div', class_='post-content')

    def get_comic_info(cls, soup, link):

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

        post = soup.find('div', class_='post-content')

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

        imgs = post.find("div", class_="entry").find_all("img")

        return {

            'title': title,

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

        }

class MisterAndMe(GenericNavigableComic):

    """Class to retrieve Mister & Me Comics."""

    # Also on http://www.gocomics.com/mister-and-me

    # Also on https://tapastic.com/series/Mister-and-Me

    name = 'mister'

    long_name = 'Mister & Me'

    url = 'http://www.mister-and-me.com'

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

        author = soup.find("span", class_="post-author").find("a").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")

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

        assert len(imgs) <= 1

    @classmethod

    def get_first_comic_link(cls):

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

        return {'href': 'http://www.lonniemillsap.com/?p=42'}

    @classmethod

    def get_comic_info(cls, soup, link):

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

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

        post = soup.find('div', class_='post-content')

        author = post.find("span", class_="post-author").find("a").string

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

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

        imgs = post.find("div", class_="entry").find_all("img")

        return {

            'title': title,

            'author': author,

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

            'month': day.month,

            'year': day.year,

            'day': day.day,

        }

class LinsEditions(GenericNavigableComic):

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

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

    name = 'lins'

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

    url = 'https://linsedition.com'

    get_navi_link = get_link_rel_next

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

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

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

        imgs = div.find_all('img') if div else []

        title = imgs[0]['title'] if imgs else ""

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

        return {

            'month': day.month,

            'year': day.year,

            'day': day.day,

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

            'title': title,

            'author': author,

        }

class DepressedAlien(GenericNavigableComic):

    """Class to retrieve Depressed Alien Comics."""

    name = 'depressedalien'

    long_name = 'Depressed Alien'

    url = 'http://depressedalien.com'

    get_url_from_link = join_cls_url_to_href

    @classmethod

    def get_first_comic_link(cls):

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

        return get_soup_at_url(cls.url).find('img', attrs={'name': 'beginArrow'}).parent

    @classmethod

    def get_navi_link(cls, last_soup, next_):

        return last_soup.find('img', attrs={'name': 'rightArrow' if next_ else 'leftArrow'}).parent

    get_navi_link = get_link_rel_next

    @classmethod

    def get_comic_info(cls, soup, link):

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

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

        author = soup.find("span", class_="post-author").find("a").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")

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

        alt = imgs[0]['alt'] if imgs else ""

        return {

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

            'title': title,

            'alt': alt,

            'author': author,

            'day': day.day,

            'month': day.month,

            'year': day.year

        }

class PlanC(GenericNavigableComic):

    """Class to retrieve Plan C comics."""

    name = 'planc'

    long_name = 'Plan C'

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

    get_first_comic_link = get_a_navi_navifirst

    get_navi_link = get_a_navi_comicnavnext_navinext

    long_name = 'Completely Serious Comics'

    url = 'http://completelyseriouscomics.com'

    get_first_comic_link = get_a_navi_navifirst

    get_navi_link = get_a_navi_navinext

    @classmethod

    def get_comic_info(cls, soup, link):

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

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

        author = soup.find('span', class_='post-author').contents[1].string

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

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

        imgs = soup.find('div', class_='comicpane').find_all('img')

        assert imgs

        alt = imgs[0]['title']

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

        return {

            'month': day.month,

            'year': day.year,

            'day': day.day,

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

            'title': title,

            'alt': alt,

            'author': author,

        }

class PoorlyDrawnLines(GenericListableComic):

    """Class to retrieve Poorly Drawn Lines comics."""

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

        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')),

        }

class WarehouseComic(GenericNavigableComic):

    """Class to retrieve Warehouse Comic comics."""

    name = 'warehouse'

    long_name = 'Warehouse Comic'

    url = 'http://warehousecomic.com'

    get_first_comic_link = get_a_navi_navifirst

    get_navi_link = get_link_rel_next

    @classmethod

class GenericBouletCorp(GenericNavigableComic):

    """Generic class to retrieve BouletCorp comics in different languages."""

    # Also on http://bouletcorp.tumblr.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('div', id='centered_nav').find_all('a')[0]

    @classmethod

    def get_comic_info(cls, soup, link):

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

        url = cls.get_url_from_link(link)

        date_re = re.compile('^%s/([0-9]*)/([0-9]*)/([0-9]*)/' % cls.url)

        year, month, day = [int(s) for s in date_re.match(url).groups()]

        imgs = soup.find('div', id='notes').find('div', class_='storycontent').find_all('img')

        texts = '  '.join(t for t in (i.get('title') for i in imgs) if t)

        title = soup.find('title').string

        return {

            'img': [convert_iri_to_plain_ascii_uri(i['src']) for i in imgs if i.get('src') is not None],

            'title': title,

            'texts': texts,

            'year': year,

            'month': month,

            'day': day,

        }