@@ 1767-1797 (lines=31) @@ | ||
1764 | def get_comic_info(cls, soup, link): |
|
1765 | """Get information about a particular comics.""" |
|
1766 | imgs = soup.find('div', id='comic').find_all('img') |
|
1767 | assert all(i['title'] == i['alt'] for i in imgs) |
|
1768 | title = ' '.join(i['title'] for i in imgs) |
|
1769 | return { |
|
1770 | 'img': [i['src'] for i in imgs], |
|
1771 | 'title': title, |
|
1772 | } |
|
1773 | ||
1774 | ||
1775 | class RespawnComic(GenericNavigableComic): |
|
1776 | """Class to retrieve Respawn Comic.""" |
|
1777 | # Also on http://respawncomic.tumblr.com |
|
1778 | name = 'respawn' |
|
1779 | long_name = 'Respawn Comic' |
|
1780 | url = 'http://respawncomic.com ' |
|
1781 | _categories = ('RESPAWN', ) |
|
1782 | get_navi_link = get_a_rel_next |
|
1783 | get_first_comic_link = simulate_first_link |
|
1784 | first_url = 'http://respawncomic.com/comic/c0001/' |
|
1785 | ||
1786 | @classmethod |
|
1787 | def get_comic_info(cls, soup, link): |
|
1788 | """Get information about a particular comics.""" |
|
1789 | title = soup.find('meta', property='og:title')['content'] |
|
1790 | author = soup.find('meta', attrs={'name': 'shareaholic:article_author_name'})['content'] |
|
1791 | date_str = soup.find('meta', attrs={'name': 'shareaholic:article_published_time'})['content'] |
|
1792 | date_str = date_str[:10] |
|
1793 | day = string_to_date(date_str, "%Y-%m-%d") |
|
1794 | imgs = soup.find_all('meta', property='og:image') |
|
1795 | skip_imgs = { |
|
1796 | 'http://respawncomic.com/wp-content/uploads/2016/03/site/HAROLD2.png', |
|
1797 | 'http://respawncomic.com/wp-content/uploads/2016/03/site/DEVA.png' |
|
1798 | } |
|
1799 | return { |
|
1800 | 'title': title, |
|
@@ 1006-1033 (lines=28) @@ | ||
1003 | imgs = soup.find_all('img', src=comic_img_re) |
|
1004 | assert len(imgs) == 1 |
|
1005 | assert imgs[0]['alt'] == name |
|
1006 | return { |
|
1007 | 'num': num, |
|
1008 | 'name': name, |
|
1009 | 'img': [urljoin_wrapper(url, i['src']) for i in imgs], |
|
1010 | 'prefix': '%d-' % num, |
|
1011 | } |
|
1012 | ||
1013 | ||
1014 | class Mercworks(GenericNavigableComic): |
|
1015 | """Class to retrieve Mercworks comics.""" |
|
1016 | # Also on http://mercworks.tumblr.com |
|
1017 | name = 'mercworks' |
|
1018 | long_name = 'Mercworks' |
|
1019 | url = 'http://mercworks.net' |
|
1020 | get_first_comic_link = get_a_comicnavbase_comicnavfirst |
|
1021 | get_navi_link = get_a_rel_next |
|
1022 | ||
1023 | @classmethod |
|
1024 | def get_comic_info(cls, soup, link): |
|
1025 | """Get information about a particular comics.""" |
|
1026 | title = soup.find('meta', property='og:title')['content'] |
|
1027 | metadesc = soup.find('meta', property='og:description') |
|
1028 | desc = metadesc['content'] if metadesc else "" |
|
1029 | author = soup.find('meta', attrs={'name': 'shareaholic:article_author_name'})['content'] |
|
1030 | date_str = soup.find('meta', attrs={'name': 'shareaholic:article_published_time'})['content'] |
|
1031 | date_str = date_str[:10] |
|
1032 | day = string_to_date(date_str, "%Y-%m-%d") |
|
1033 | imgs = soup.find_all('meta', property='og:image') |
|
1034 | return { |
|
1035 | 'img': [i['content'] for i in imgs], |
|
1036 | 'title': title, |