|
@@ 2997-3027 (lines=31) @@
|
| 2994 |
|
lang = "fr_FR.utf8" |
| 2995 |
|
|
| 2996 |
|
|
| 2997 |
|
class UnearthedComics(GenericNavigableComic): |
| 2998 |
|
"""Class to retrieve Unearthed comics.""" |
| 2999 |
|
# Also on http://tapastic.com/series/UnearthedComics |
| 3000 |
|
# Also on https://unearthedcomics.tumblr.com |
| 3001 |
|
name = 'unearthed' |
| 3002 |
|
long_name = 'Unearthed Comics' |
| 3003 |
|
url = 'http://unearthedcomics.com' |
| 3004 |
|
_categories = ('UNEARTHED', ) |
| 3005 |
|
get_navi_link = get_link_rel_next |
| 3006 |
|
get_first_comic_link = simulate_first_link |
| 3007 |
|
first_url = 'http://unearthedcomics.com/comics/world-with-turn-signals/' |
| 3008 |
|
|
| 3009 |
|
@classmethod |
| 3010 |
|
def get_comic_info(cls, soup, link): |
| 3011 |
|
"""Get information about a particular comics.""" |
| 3012 |
|
short_url = soup.find('link', rel='shortlink')['href'] |
| 3013 |
|
title_elt = soup.find('h1') or soup.find('h2') |
| 3014 |
|
title = title_elt.string if title_elt else "" |
| 3015 |
|
desc = soup.find('meta', property='og:description') |
| 3016 |
|
date_str = soup.find('time', class_='published updated hidden')['datetime'] |
| 3017 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 3018 |
|
post = soup.find('div', class_="entry content entry-content type-portfolio") |
| 3019 |
|
imgs = post.find_all('img') |
| 3020 |
|
return { |
| 3021 |
|
'title': title, |
| 3022 |
|
'description': desc, |
| 3023 |
|
'url2': short_url, |
| 3024 |
|
'img': [i['src'] for i in imgs], |
| 3025 |
|
'month': day.month, |
| 3026 |
|
'year': day.year, |
| 3027 |
|
'day': day.day, |
| 3028 |
|
} |
| 3029 |
|
|
| 3030 |
|
|
|
@@ 551-580 (lines=30) @@
|
| 548 |
|
first_url = 'http://morgannavarro.blog.lemonde.fr/2015/09/09/le-doute/' |
| 549 |
|
|
| 550 |
|
|
| 551 |
|
class Rall(GenericComicNotWorking, GenericNavigableComic): |
| 552 |
|
"""Class to retrieve Ted Rall comics.""" |
| 553 |
|
# Also on http://www.gocomics.com/tedrall |
| 554 |
|
name = 'rall' |
| 555 |
|
long_name = "Ted Rall" |
| 556 |
|
url = "http://rall.com/comic" |
| 557 |
|
_categories = ('RALL', ) |
| 558 |
|
get_navi_link = get_link_rel_next |
| 559 |
|
get_first_comic_link = simulate_first_link |
| 560 |
|
# Not the first but I didn't find an efficient way to retrieve it |
| 561 |
|
first_url = "http://rall.com/2014/01/30/los-angeles-times-cartoon-well-miss-those-california-flowers" |
| 562 |
|
|
| 563 |
|
@classmethod |
| 564 |
|
def get_comic_info(cls, soup, link): |
| 565 |
|
"""Get information about a particular comics.""" |
| 566 |
|
title = soup.find('meta', property='og:title')['content'] |
| 567 |
|
author = soup.find("span", class_="author vcard").find("a").string |
| 568 |
|
date_str = soup.find("span", class_="entry-date").string |
| 569 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 570 |
|
desc = soup.find('meta', property='og:description')['content'] |
| 571 |
|
imgs = soup.find('div', class_='entry-content').find_all('img') |
| 572 |
|
imgs = imgs[:-7] # remove social media buttons |
| 573 |
|
return { |
| 574 |
|
'title': title, |
| 575 |
|
'author': author, |
| 576 |
|
'month': day.month, |
| 577 |
|
'year': day.year, |
| 578 |
|
'day': day.day, |
| 579 |
|
'description': desc, |
| 580 |
|
'img': [i['src'] for i in imgs], |
| 581 |
|
} |
| 582 |
|
|
| 583 |
|
|