@@ 4666-4682 (lines=17) @@ | ||
4663 | url = 'http://brooklyncartoons.tumblr.com' |
|
4664 | ||
4665 | ||
4666 | class GemmaCorrellTumblr(GenericTumblrV1): |
|
4667 | # Also on http://www.gemmacorrell.com/portfolio/comics/ |
|
4668 | name = 'gemma-tumblr' |
|
4669 | long_name = 'Gemma Correll (from Tumblr)' |
|
4670 | url = 'http://gemmacorrell.tumblr.com' |
|
4671 | ||
4672 | ||
4673 | class RobotatertotTumblr(GenericTumblrV1): |
|
4674 | """Class to retrieve Robotatertot comics.""" |
|
4675 | # Also on https://www.instagram.com/robotatertotcomics |
|
4676 | name = 'robotatertot-tumblr' |
|
4677 | long_name = 'Robotatertot (from Tumblr)' |
|
4678 | url = 'https://robotatertot.tumblr.com' |
|
4679 | ||
4680 | ||
4681 | class HuffyPenguin(GenericTumblrV1): |
|
4682 | """Class to retrieve Huffy Penguin comics.""" |
|
4683 | name = 'huffypenguin' |
|
4684 | long_name = 'Huffy Penguin' |
|
4685 | url = 'http://huffy-penguin.tumblr.com' |
|
@@ 763-778 (lines=16) @@ | ||
760 | get_first_comic_link = get_div_navfirst_a |
|
761 | get_navi_link = get_link_rel_next |
|
762 | get_url_from_link = join_cls_url_to_href |
|
763 | ||
764 | @classmethod |
|
765 | def get_comic_info(cls, soup, link): |
|
766 | """Get information about a particular comics.""" |
|
767 | short_url_re = re.compile('^%s/\\?p=([0-9]*)' % cls.url) |
|
768 | short_url = cls.get_url_from_link(soup.find('link', rel='shortlink')) |
|
769 | num = int(short_url_re.match(short_url).groups()[0]) |
|
770 | imgs = soup.find('div', id='comic').find_all('img') |
|
771 | assert len(imgs) == 1 |
|
772 | title = imgs[0]['alt'] |
|
773 | title2 = imgs[0]['title'] |
|
774 | return { |
|
775 | 'short_url': short_url, |
|
776 | 'title': title, |
|
777 | 'title2': title2, |
|
778 | 'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs], |
|
779 | 'num': num, |
|
780 | } |
|
781 |