|
@@ 387-412 (lines=26) @@
|
| 384 |
|
_categories = ('DELETED', ) |
| 385 |
|
|
| 386 |
|
|
| 387 |
|
class ExtraFabulousComics(GenericNavigableComic): |
| 388 |
|
"""Class to retrieve Extra Fabulous Comics.""" |
| 389 |
|
# Also on https://extrafabulouscomics.tumblr.com |
| 390 |
|
name = 'efc' |
| 391 |
|
long_name = 'Extra Fabulous Comics' |
| 392 |
|
url = 'http://extrafabulouscomics.com' |
| 393 |
|
_categories = ('EFC', ) |
| 394 |
|
get_navi_link = get_link_rel_next |
| 395 |
|
get_first_comic_link = simulate_first_link |
| 396 |
|
first_url = 'http://extrafabulouscomics.com/comic/buttfly/' |
| 397 |
|
|
| 398 |
|
@classmethod |
| 399 |
|
def get_comic_info(cls, soup, link): |
| 400 |
|
"""Get information about a particular comics.""" |
| 401 |
|
img_src_re = re.compile('^%s/wp-content/uploads/' % cls.url) |
| 402 |
|
imgs = soup.find_all('img', src=img_src_re) |
| 403 |
|
title = soup.find('meta', property='og:title')['content'] |
| 404 |
|
date_str = soup.find('meta', property='article:published_time')['content'][:10] |
| 405 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 406 |
|
return { |
| 407 |
|
'title': title, |
| 408 |
|
'img': [i['src'] for i in imgs], |
| 409 |
|
'month': day.month, |
| 410 |
|
'year': day.year, |
| 411 |
|
'day': day.day, |
| 412 |
|
'prefix': title + '-' |
| 413 |
|
} |
| 414 |
|
|
| 415 |
|
|
|
@@ 2427-2451 (lines=25) @@
|
| 2424 |
|
} |
| 2425 |
|
|
| 2426 |
|
|
| 2427 |
|
class LinsEditions(GenericNavigableComic): |
| 2428 |
|
"""Class to retrieve L.I.N.S. Editions comics.""" |
| 2429 |
|
# Also on https://linscomics.tumblr.com |
| 2430 |
|
# Now on https://warandpeas.com |
| 2431 |
|
name = 'lins' |
| 2432 |
|
long_name = 'L.I.N.S. Editions' |
| 2433 |
|
url = 'https://linsedition.com' |
| 2434 |
|
_categories = ('LINS', ) |
| 2435 |
|
get_navi_link = get_link_rel_next |
| 2436 |
|
get_first_comic_link = simulate_first_link |
| 2437 |
|
first_url = 'https://linsedition.com/2011/09/07/l-i-n-s/' |
| 2438 |
|
|
| 2439 |
|
@classmethod |
| 2440 |
|
def get_comic_info(cls, soup, link): |
| 2441 |
|
"""Get information about a particular comics.""" |
| 2442 |
|
title = soup.find('meta', property='og:title')['content'] |
| 2443 |
|
imgs = soup.find_all('meta', property='og:image') |
| 2444 |
|
date_str = soup.find('meta', property='article:published_time')['content'][:10] |
| 2445 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 2446 |
|
return { |
| 2447 |
|
'title': title, |
| 2448 |
|
'img': [i['content'] for i in imgs], |
| 2449 |
|
'month': day.month, |
| 2450 |
|
'year': day.year, |
| 2451 |
|
'day': day.day, |
| 2452 |
|
} |
| 2453 |
|
|
| 2454 |
|
|
|
@@ 1074-1098 (lines=25) @@
|
| 1071 |
|
} |
| 1072 |
|
|
| 1073 |
|
|
| 1074 |
|
class Mercworks(GenericNavigableComic): |
| 1075 |
|
"""Class to retrieve Mercworks comics.""" |
| 1076 |
|
# Also on http://mercworks.tumblr.com |
| 1077 |
|
name = 'mercworks' |
| 1078 |
|
long_name = 'Mercworks' |
| 1079 |
|
url = 'http://mercworks.net' |
| 1080 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 1081 |
|
get_navi_link = get_link_rel_next |
| 1082 |
|
|
| 1083 |
|
@classmethod |
| 1084 |
|
def get_comic_info(cls, soup, link): |
| 1085 |
|
"""Get information about a particular comics.""" |
| 1086 |
|
title = soup.find('meta', property='og:title')['content'] |
| 1087 |
|
metadesc = soup.find('meta', property='og:description') |
| 1088 |
|
desc = metadesc['content'] if metadesc else "" |
| 1089 |
|
date_str = soup.find('meta', property='article:published_time')['content'][:10] |
| 1090 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 1091 |
|
imgs = soup.find_all('meta', property='og:image') |
| 1092 |
|
return { |
| 1093 |
|
'img': [i['content'] for i in imgs], |
| 1094 |
|
'title': title, |
| 1095 |
|
'desc': desc, |
| 1096 |
|
'day': day.day, |
| 1097 |
|
'month': day.month, |
| 1098 |
|
'year': day.year |
| 1099 |
|
} |
| 1100 |
|
|
| 1101 |
|
|
|
@@ 3389-3410 (lines=22) @@
|
| 3386 |
|
} |
| 3387 |
|
|
| 3388 |
|
|
| 3389 |
|
class MarketoonistComics(GenericNavigableComic): |
| 3390 |
|
"""Class to retrieve Marketoonist Comics.""" |
| 3391 |
|
name = 'marketoonist' |
| 3392 |
|
long_name = 'Marketoonist' |
| 3393 |
|
url = 'https://marketoonist.com/cartoons' |
| 3394 |
|
get_first_comic_link = simulate_first_link |
| 3395 |
|
get_navi_link = get_link_rel_next |
| 3396 |
|
first_url = 'https://marketoonist.com/2002/10/the-8-types-of-brand-managers-2.html' |
| 3397 |
|
|
| 3398 |
|
@classmethod |
| 3399 |
|
def get_comic_info(cls, soup, link): |
| 3400 |
|
"""Get information about a particular comics.""" |
| 3401 |
|
imgs = soup.find_all('meta', property='og:image') |
| 3402 |
|
date_str = soup.find('meta', property='article:published_time')['content'][:10] |
| 3403 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 3404 |
|
title = soup.find('meta', property='og:title')['content'] |
| 3405 |
|
return { |
| 3406 |
|
'img': [i['content'] for i in imgs], |
| 3407 |
|
'day': day.day, |
| 3408 |
|
'month': day.month, |
| 3409 |
|
'year': day.year, |
| 3410 |
|
'title': title, |
| 3411 |
|
} |
| 3412 |
|
|
| 3413 |
|
|
|
@@ 416-437 (lines=22) @@
|
| 413 |
|
} |
| 414 |
|
|
| 415 |
|
|
| 416 |
|
class GenericLeMondeBlog(GenericNavigableComic): |
| 417 |
|
"""Generic class to retrieve comics from Le Monde blogs.""" |
| 418 |
|
_categories = ('LEMONDE', 'FRANCAIS') |
| 419 |
|
get_navi_link = get_link_rel_next |
| 420 |
|
get_first_comic_link = simulate_first_link |
| 421 |
|
first_url = NotImplemented |
| 422 |
|
|
| 423 |
|
@classmethod |
| 424 |
|
def get_comic_info(cls, soup, link): |
| 425 |
|
"""Get information about a particular comics.""" |
| 426 |
|
url2 = soup.find('link', rel='shortlink')['href'] |
| 427 |
|
title = soup.find('meta', property='og:title')['content'] |
| 428 |
|
date_str = soup.find("span", class_="entry-date").string |
| 429 |
|
day = string_to_date(date_str, "%d %B %Y", "fr_FR.utf8") |
| 430 |
|
imgs = soup.find_all('meta', property='og:image') |
| 431 |
|
return { |
| 432 |
|
'title': title, |
| 433 |
|
'url2': url2, |
| 434 |
|
'img': [convert_iri_to_plain_ascii_uri(i['content']) for i in imgs], |
| 435 |
|
'month': day.month, |
| 436 |
|
'year': day.year, |
| 437 |
|
'day': day.day, |
| 438 |
|
} |
| 439 |
|
|
| 440 |
|
|