|
@@ 909-934 (lines=26) @@
|
| 906 |
|
} |
| 907 |
|
|
| 908 |
|
|
| 909 |
|
class MyExtraLife(GenericNavigableComic): |
| 910 |
|
"""Class to retrieve My Extra Life comics.""" |
| 911 |
|
name = 'extralife' |
| 912 |
|
long_name = 'My Extra Life' |
| 913 |
|
url = 'http://www.myextralife.com' |
| 914 |
|
get_navi_link = get_link_rel_next |
| 915 |
|
|
| 916 |
|
@classmethod |
| 917 |
|
def get_first_comic_link(cls): |
| 918 |
|
"""Get link to first comics.""" |
| 919 |
|
return get_soup_at_url(cls.url).find('a', class_='comic_nav_link first_comic_link') |
| 920 |
|
|
| 921 |
|
@classmethod |
| 922 |
|
def get_comic_info(cls, soup, link): |
| 923 |
|
"""Get information about a particular comics.""" |
| 924 |
|
title = soup.find("h1", class_="comic_title").string |
| 925 |
|
date_str = soup.find("span", class_="comic_date").string |
| 926 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 927 |
|
imgs = soup.find_all("img", class_="comic") |
| 928 |
|
assert all(i['alt'] == i['title'] == title for i in imgs) |
| 929 |
|
return { |
| 930 |
|
'title': title, |
| 931 |
|
'img': [i['src'] for i in imgs if i["src"]], |
| 932 |
|
'day': day.day, |
| 933 |
|
'month': day.month, |
| 934 |
|
'year': day.year |
| 935 |
|
} |
| 936 |
|
|
| 937 |
|
|
|
@@ 2248-2270 (lines=23) @@
|
| 2245 |
|
} |
| 2246 |
|
|
| 2247 |
|
|
| 2248 |
|
class LinsEditions(GenericNavigableComic): |
| 2249 |
|
"""Class to retrieve L.I.N.S. Editions comics.""" |
| 2250 |
|
# Also on http://linscomics.tumblr.com |
| 2251 |
|
name = 'lins' |
| 2252 |
|
long_name = 'L.I.N.S. Editions' |
| 2253 |
|
url = 'https://linsedition.com' |
| 2254 |
|
get_navi_link = get_link_rel_next |
| 2255 |
|
get_first_comic_link = simulate_first_link |
| 2256 |
|
first_url = 'https://linsedition.com/2011/09/07/l-i-n-s/' |
| 2257 |
|
|
| 2258 |
|
@classmethod |
| 2259 |
|
def get_comic_info(cls, soup, link): |
| 2260 |
|
"""Get information about a particular comics.""" |
| 2261 |
|
title = soup.find('meta', property='og:title')['content'] |
| 2262 |
|
imgs = soup.find_all('meta', property='og:image') |
| 2263 |
|
date_str = soup.find('meta', property='article:published_time')['content'][:10] |
| 2264 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 2265 |
|
return { |
| 2266 |
|
'title': title, |
| 2267 |
|
'img': [i['content'] for i in imgs], |
| 2268 |
|
'month': day.month, |
| 2269 |
|
'year': day.year, |
| 2270 |
|
'day': day.day, |
| 2271 |
|
} |
| 2272 |
|
|
| 2273 |
|
|
|
@@ 378-398 (lines=21) @@
|
| 375 |
|
} |
| 376 |
|
|
| 377 |
|
|
| 378 |
|
class GenericLeMondeBlog(GenericNavigableComic): |
| 379 |
|
"""Generic class to retrieve comics from Le Monde blogs.""" |
| 380 |
|
get_navi_link = get_link_rel_next |
| 381 |
|
get_first_comic_link = simulate_first_link |
| 382 |
|
first_url = NotImplemented |
| 383 |
|
|
| 384 |
|
@classmethod |
| 385 |
|
def get_comic_info(cls, soup, link): |
| 386 |
|
"""Get information about a particular comics.""" |
| 387 |
|
url2 = soup.find('link', rel='shortlink')['href'] |
| 388 |
|
title = soup.find('meta', property='og:title')['content'] |
| 389 |
|
date_str = soup.find("span", class_="entry-date").string |
| 390 |
|
day = string_to_date(date_str, "%d %B %Y", "fr_FR.utf8") |
| 391 |
|
imgs = soup.find_all('meta', property='og:image') |
| 392 |
|
return { |
| 393 |
|
'title': title, |
| 394 |
|
'url2': url2, |
| 395 |
|
'img': [convert_iri_to_plain_ascii_uri(i['content']) for i in imgs], |
| 396 |
|
'month': day.month, |
| 397 |
|
'year': day.year, |
| 398 |
|
'day': day.day, |
| 399 |
|
} |
| 400 |
|
|
| 401 |
|
|