|
@@ 2869-2905 (lines=37) @@
|
| 2866 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2867 |
|
get_navi_link = get_a_navi_navinext |
| 2868 |
|
|
| 2869 |
|
@classmethod |
| 2870 |
|
def get_comic_info(cls, soup, link): |
| 2871 |
|
"""Get information about a particular comics.""" |
| 2872 |
|
title = soup.find('h2', class_='post-title').string |
| 2873 |
|
short_url = soup.find('link', rel='shortlink')['href'] |
| 2874 |
|
short_url_re = re.compile('^%s/\\?p=([0-9]*)' % cls.url) |
| 2875 |
|
num = int(short_url_re.match(short_url).groups()[0]) |
| 2876 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 2877 |
|
alt = imgs[0]['title'] |
| 2878 |
|
assert all(i['alt'] == i['title'] == alt for i in imgs) |
| 2879 |
|
date_str = soup.find('span', class_='post-date').string |
| 2880 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2881 |
|
tags = ' '.join(t['content'] for t in soup.find_all('meta', property='article:tag')) |
| 2882 |
|
author = soup.find('span', class_='post-author').string |
| 2883 |
|
return { |
| 2884 |
|
'short_url': short_url, |
| 2885 |
|
'num': num, |
| 2886 |
|
'img': [i['src'] for i in imgs], |
| 2887 |
|
'month': day.month, |
| 2888 |
|
'year': day.year, |
| 2889 |
|
'day': day.day, |
| 2890 |
|
'title': title, |
| 2891 |
|
'tags': tags, |
| 2892 |
|
'alt': alt, |
| 2893 |
|
'author': author, |
| 2894 |
|
} |
| 2895 |
|
|
| 2896 |
|
|
| 2897 |
|
class AHamADay(GenericNavigableComic): |
| 2898 |
|
"""Class to retrieve class A Ham A Day comics.""" |
| 2899 |
|
name = 'ham' |
| 2900 |
|
long_name = 'A Ham A Day' |
| 2901 |
|
url = 'http://www.ahammaday.com' |
| 2902 |
|
get_url_from_link = join_cls_url_to_href |
| 2903 |
|
get_first_comic_link = simulate_first_link |
| 2904 |
|
first_url = 'http://www.ahammaday.com/today/3/6/french' |
| 2905 |
|
|
| 2906 |
|
@classmethod |
| 2907 |
|
def get_navi_link(cls, last_soup, next_): |
| 2908 |
|
"""Get link to next or previous comic.""" |
|
@@ 758-792 (lines=35) @@
|
| 755 |
|
"""Class to retrieve Garfield comics.""" |
| 756 |
|
# Also on http://www.gocomics.com/garfield |
| 757 |
|
name = 'garfield' |
| 758 |
|
long_name = 'Garfield' |
| 759 |
|
url = 'https://garfield.com' |
| 760 |
|
_categories = ('GARFIELD', ) |
| 761 |
|
get_first_comic_link = simulate_first_link |
| 762 |
|
first_url = 'https://garfield.com/comic/1978/06/19' |
| 763 |
|
|
| 764 |
|
@classmethod |
| 765 |
|
def get_navi_link(cls, last_soup, next_): |
| 766 |
|
"""Get link to next or previous comic.""" |
| 767 |
|
return last_soup.find('a', class_='comic-arrow-right' if next_ else 'comic-arrow-left') |
| 768 |
|
|
| 769 |
|
@classmethod |
| 770 |
|
def get_comic_info(cls, soup, link): |
| 771 |
|
"""Get information about a particular comics.""" |
| 772 |
|
url = cls.get_url_from_link(link) |
| 773 |
|
date_re = re.compile('^%s/comic/([0-9]*)/([0-9]*)/([0-9]*)' % cls.url) |
| 774 |
|
year, month, day = [int(s) for s in date_re.match(url).groups()] |
| 775 |
|
imgs = soup.find('div', class_='comic-display').find_all('img', class_='img-responsive') |
| 776 |
|
return { |
| 777 |
|
'month': month, |
| 778 |
|
'year': year, |
| 779 |
|
'day': day, |
| 780 |
|
'img': [i['src'] for i in imgs], |
| 781 |
|
} |
| 782 |
|
|
| 783 |
|
|
| 784 |
|
class Dilbert(GenericNavigableComic): |
| 785 |
|
"""Class to retrieve Dilbert comics.""" |
| 786 |
|
# Also on http://www.gocomics.com/dilbert-classics |
| 787 |
|
name = 'dilbert' |
| 788 |
|
long_name = 'Dilbert' |
| 789 |
|
url = 'http://dilbert.com' |
| 790 |
|
get_url_from_link = join_cls_url_to_href |
| 791 |
|
get_first_comic_link = simulate_first_link |
| 792 |
|
first_url = 'http://dilbert.com/strip/1989-04-16' |
| 793 |
|
|
| 794 |
|
@classmethod |
| 795 |
|
def get_navi_link(cls, last_soup, next_): |
SylvainDe /
ComicBookMaker
