|
@@ 4940-4956 (lines=17) @@
|
| 4937 |
|
link_re = NotImplemented |
| 4938 |
|
get_url_from_archive_element = join_cls_url_to_href |
| 4939 |
|
|
| 4940 |
|
@classmethod |
| 4941 |
|
def get_comic_info(cls, soup, link): |
| 4942 |
|
"""Get information about a particular comics.""" |
| 4943 |
|
href = link['href'] |
| 4944 |
|
num = int(cls.link_re.match(href).groups()[0]) |
| 4945 |
|
title = link.string |
| 4946 |
|
imgs = soup.find_all('img', id='comic') |
| 4947 |
|
assert len(imgs) == 1, imgs |
| 4948 |
|
year, month, day = [int(s) |
| 4949 |
|
for s in cls.img_re.match(imgs[0]['src']).groups()] |
| 4950 |
|
return { |
| 4951 |
|
'title': title, |
| 4952 |
|
'day': day, |
| 4953 |
|
'month': month, |
| 4954 |
|
'year': year, |
| 4955 |
|
'img': [i['src'] for i in imgs], |
| 4956 |
|
'num': num, |
| 4957 |
|
} |
| 4958 |
|
|
| 4959 |
|
@classmethod |
|
@@ 782-797 (lines=16) @@
|
| 779 |
|
get_navi_link = get_link_rel_next |
| 780 |
|
get_url_from_link = join_cls_url_to_href |
| 781 |
|
|
| 782 |
|
@classmethod |
| 783 |
|
def get_comic_info(cls, soup, link): |
| 784 |
|
"""Get information about a particular comics.""" |
| 785 |
|
short_url_re = re.compile('^%s/\\?p=([0-9]*)' % cls.url) |
| 786 |
|
short_url = cls.get_url_from_link(soup.find('link', rel='shortlink')) |
| 787 |
|
num = int(short_url_re.match(short_url).groups()[0]) |
| 788 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 789 |
|
assert len(imgs) == 1, imgs |
| 790 |
|
title = imgs[0]['alt'] |
| 791 |
|
title2 = imgs[0]['title'] |
| 792 |
|
return { |
| 793 |
|
'short_url': short_url, |
| 794 |
|
'title': title, |
| 795 |
|
'title2': title2, |
| 796 |
|
'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs], |
| 797 |
|
'num': num, |
| 798 |
|
} |
| 799 |
|
|
| 800 |
|
|