|
@@ 2999-3035 (lines=37) @@
|
| 2996 |
|
def get_comic_info(cls, soup, link): |
| 2997 |
|
"""Get information about a particular comics.""" |
| 2998 |
|
title = soup.find('h2', class_='post-title').string |
| 2999 |
|
short_url = soup.find('link', rel='shortlink')['href'] |
| 3000 |
|
short_url_re = re.compile('^%s/\\?p=([0-9]*)' % cls.url) |
| 3001 |
|
num = int(short_url_re.match(short_url).groups()[0]) |
| 3002 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 3003 |
|
alt = imgs[0]['title'] |
| 3004 |
|
assert all(i['alt'] == i['title'] == alt for i in imgs) |
| 3005 |
|
date_str = soup.find('span', class_='post-date').string |
| 3006 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 3007 |
|
tags = ' '.join(t['content'] for t in soup.find_all('meta', property='article:tag')) |
| 3008 |
|
author = soup.find('span', class_='post-author').string |
| 3009 |
|
return { |
| 3010 |
|
'short_url': short_url, |
| 3011 |
|
'num': num, |
| 3012 |
|
'img': [i['src'] for i in imgs], |
| 3013 |
|
'month': day.month, |
| 3014 |
|
'year': day.year, |
| 3015 |
|
'day': day.day, |
| 3016 |
|
'title': title, |
| 3017 |
|
'tags': tags, |
| 3018 |
|
'alt': alt, |
| 3019 |
|
'author': author, |
| 3020 |
|
} |
| 3021 |
|
|
| 3022 |
|
|
| 3023 |
|
class SystemComic(GenericNavigableComic): |
| 3024 |
|
"""Class to retrieve System Comic.""" |
| 3025 |
|
name = 'system' |
| 3026 |
|
long_name = 'System Comic' |
| 3027 |
|
url = 'http://www.systemcomic.com' |
| 3028 |
|
get_navi_link = get_a_rel_next |
| 3029 |
|
|
| 3030 |
|
@classmethod |
| 3031 |
|
def get_first_comic_link(cls): |
| 3032 |
|
"""Get link to first comics.""" |
| 3033 |
|
return get_soup_at_url(cls.url).find('li', class_='first').find('a') |
| 3034 |
|
|
| 3035 |
|
@classmethod |
| 3036 |
|
def get_comic_info(cls, soup, link): |
| 3037 |
|
"""Get information about a particular comics.""" |
| 3038 |
|
title = soup.find('meta', property='og:title')['content'] |
|
@@ 782-816 (lines=35) @@
|
| 779 |
|
'num': num, |
| 780 |
|
} |
| 781 |
|
|
| 782 |
|
|
| 783 |
|
class Garfield(GenericNavigableComic): |
| 784 |
|
"""Class to retrieve Garfield comics.""" |
| 785 |
|
# Also on http://www.gocomics.com/garfield |
| 786 |
|
name = 'garfield' |
| 787 |
|
long_name = 'Garfield' |
| 788 |
|
url = 'https://garfield.com' |
| 789 |
|
_categories = ('GARFIELD', ) |
| 790 |
|
get_first_comic_link = simulate_first_link |
| 791 |
|
first_url = 'https://garfield.com/comic/1978/06/19' |
| 792 |
|
|
| 793 |
|
@classmethod |
| 794 |
|
def get_navi_link(cls, last_soup, next_): |
| 795 |
|
"""Get link to next or previous comic.""" |
| 796 |
|
return last_soup.find('a', class_='comic-arrow-right' if next_ else 'comic-arrow-left') |
| 797 |
|
|
| 798 |
|
@classmethod |
| 799 |
|
def get_comic_info(cls, soup, link): |
| 800 |
|
"""Get information about a particular comics.""" |
| 801 |
|
url = cls.get_url_from_link(link) |
| 802 |
|
date_re = re.compile('^%s/comic/([0-9]*)/([0-9]*)/([0-9]*)' % cls.url) |
| 803 |
|
year, month, day = [int(s) for s in date_re.match(url).groups()] |
| 804 |
|
imgs = soup.find('div', class_='comic-display').find_all('img', class_='img-responsive') |
| 805 |
|
return { |
| 806 |
|
'month': month, |
| 807 |
|
'year': year, |
| 808 |
|
'day': day, |
| 809 |
|
'img': [i['src'] for i in imgs], |
| 810 |
|
} |
| 811 |
|
|
| 812 |
|
|
| 813 |
|
class Dilbert(GenericNavigableComic): |
| 814 |
|
"""Class to retrieve Dilbert comics.""" |
| 815 |
|
# Also on http://www.gocomics.com/dilbert-classics |
| 816 |
|
name = 'dilbert' |
| 817 |
|
long_name = 'Dilbert' |
| 818 |
|
url = 'http://dilbert.com' |
| 819 |
|
get_url_from_link = join_cls_url_to_href |
SylvainDe /
ComicBookMaker
