|
@@ 781-815 (lines=35) @@
|
| 778 |
|
'img': [i['src'] for i in imgs], |
| 779 |
|
} |
| 780 |
|
|
| 781 |
|
|
| 782 |
|
class Dilbert(GenericNavigableComic): |
| 783 |
|
"""Class to retrieve Dilbert comics.""" |
| 784 |
|
# Also on http://www.gocomics.com/dilbert-classics |
| 785 |
|
name = 'dilbert' |
| 786 |
|
long_name = 'Dilbert' |
| 787 |
|
url = 'http://dilbert.com' |
| 788 |
|
get_url_from_link = join_cls_url_to_href |
| 789 |
|
get_first_comic_link = simulate_first_link |
| 790 |
|
first_url = 'http://dilbert.com/strip/1989-04-16' |
| 791 |
|
|
| 792 |
|
@classmethod |
| 793 |
|
def get_navi_link(cls, last_soup, next_): |
| 794 |
|
"""Get link to next or previous comic.""" |
| 795 |
|
link = last_soup.find('div', class_='nav-comic nav-right' if next_ else 'nav-comic nav-left') |
| 796 |
|
return link.find('a') if link else None |
| 797 |
|
|
| 798 |
|
@classmethod |
| 799 |
|
def get_comic_info(cls, soup, link): |
| 800 |
|
"""Get information about a particular comics.""" |
| 801 |
|
title = soup.find('meta', property='og:title')['content'] |
| 802 |
|
imgs = soup.find_all('meta', property='og:image') |
| 803 |
|
desc = soup.find('meta', property='og:description')['content'] |
| 804 |
|
date_str = soup.find('meta', property='article:publish_date')['content'] |
| 805 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 806 |
|
author = soup.find('meta', property='article:author')['content'] |
| 807 |
|
tags = soup.find('meta', property='article:tag')['content'] |
| 808 |
|
return { |
| 809 |
|
'title': title, |
| 810 |
|
'description': desc, |
| 811 |
|
'img': [i['content'] for i in imgs], |
| 812 |
|
'author': author, |
| 813 |
|
'tags': tags, |
| 814 |
|
'day': day.day, |
| 815 |
|
'month': day.month, |
| 816 |
|
'year': day.year |
| 817 |
|
} |
| 818 |
|
|
|
@@ 2981-3017 (lines=37) @@
|
| 2978 |
|
'year': day.year, |
| 2979 |
|
} |
| 2980 |
|
|
| 2981 |
|
|
| 2982 |
|
class LittleLifeLines(GenericNavigableComic): |
| 2983 |
|
"""Class to retrieve Little Life Lines comics.""" |
| 2984 |
|
# Also on https://little-life-lines.tumblr.com |
| 2985 |
|
name = 'life' |
| 2986 |
|
long_name = 'Little Life Lines' |
| 2987 |
|
url = 'http://www.littlelifelines.com' |
| 2988 |
|
get_url_from_link = join_cls_url_to_href |
| 2989 |
|
get_first_comic_link = simulate_first_link |
| 2990 |
|
first_url = 'http://www.littlelifelines.com/comics/well-done' |
| 2991 |
|
|
| 2992 |
|
@classmethod |
| 2993 |
|
def get_navi_link(cls, last_soup, next_): |
| 2994 |
|
"""Get link to next or previous comic.""" |
| 2995 |
|
# prev is next / next is prev |
| 2996 |
|
li = last_soup.find('li', class_='prev' if next_ else 'next') |
| 2997 |
|
return li.find('a') if li else None |
| 2998 |
|
|
| 2999 |
|
@classmethod |
| 3000 |
|
def get_comic_info(cls, soup, link): |
| 3001 |
|
"""Get information about a particular comics.""" |
| 3002 |
|
title = soup.find('meta', property='og:title')['content'] |
| 3003 |
|
desc = soup.find('meta', property='og:description')['content'] |
| 3004 |
|
date_str = soup.find('time', class_='published')['datetime'] |
| 3005 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 3006 |
|
author = soup.find('a', rel='author').string |
| 3007 |
|
div_content = soup.find('div', class_="body entry-content") |
| 3008 |
|
imgs = div_content.find_all('img') |
| 3009 |
|
imgs = [i for i in imgs if i.get('src') is not None] |
| 3010 |
|
alt = imgs[0]['alt'] |
| 3011 |
|
return { |
| 3012 |
|
'title': title, |
| 3013 |
|
'alt': alt, |
| 3014 |
|
'description': desc, |
| 3015 |
|
'author': author, |
| 3016 |
|
'day': day.day, |
| 3017 |
|
'month': day.month, |
| 3018 |
|
'year': day.year, |
| 3019 |
|
'img': [i['src'] for i in imgs], |
| 3020 |
|
} |
SylvainDe /
ComicBookMaker
