@@ 405-430 (lines=26) @@ | ||
402 | _categories = ('DELETED', ) |
|
403 | ||
404 | ||
405 | class ExtraFabulousComics(GenericNavigableComic): |
|
406 | """Class to retrieve Extra Fabulous Comics.""" |
|
407 | # Also on https://extrafabulouscomics.tumblr.com |
|
408 | name = 'efc' |
|
409 | long_name = 'Extra Fabulous Comics' |
|
410 | url = 'http://extrafabulouscomics.com' |
|
411 | _categories = ('EFC', ) |
|
412 | get_navi_link = get_link_rel_next |
|
413 | get_first_comic_link = simulate_first_link |
|
414 | first_url = 'http://extrafabulouscomics.com/comic/buttfly/' |
|
415 | ||
416 | @classmethod |
|
417 | def get_comic_info(cls, soup, link): |
|
418 | """Get information about a particular comics.""" |
|
419 | img_src_re = re.compile('^%s/wp-content/uploads/' % cls.url) |
|
420 | imgs = soup.find_all('img', src=img_src_re) |
|
421 | title = soup.find('meta', property='og:title')['content'] |
|
422 | date_str = soup.find('meta', property='article:published_time')['content'][:10] |
|
423 | day = string_to_date(date_str, "%Y-%m-%d") |
|
424 | return { |
|
425 | 'title': title, |
|
426 | 'img': [i['src'] for i in imgs], |
|
427 | 'month': day.month, |
|
428 | 'year': day.year, |
|
429 | 'day': day.day, |
|
430 | 'prefix': title + '-' |
|
431 | } |
|
432 | ||
433 | ||
@@ 2411-2435 (lines=25) @@ | ||
2408 | } |
|
2409 | ||
2410 | ||
2411 | class LinsEditions(GenericNavigableComic): |
|
2412 | """Class to retrieve L.I.N.S. Editions comics.""" |
|
2413 | # Also on https://linscomics.tumblr.com |
|
2414 | # Now on https://warandpeas.com |
|
2415 | name = 'lins' |
|
2416 | long_name = 'L.I.N.S. Editions' |
|
2417 | url = 'https://linsedition.com' |
|
2418 | _categories = ('LINS', ) |
|
2419 | get_navi_link = get_link_rel_next |
|
2420 | get_first_comic_link = simulate_first_link |
|
2421 | first_url = 'https://linsedition.com/2011/09/07/l-i-n-s/' |
|
2422 | ||
2423 | @classmethod |
|
2424 | def get_comic_info(cls, soup, link): |
|
2425 | """Get information about a particular comics.""" |
|
2426 | title = soup.find('meta', property='og:title')['content'] |
|
2427 | imgs = soup.find_all('meta', property='og:image') |
|
2428 | date_str = soup.find('meta', property='article:published_time')['content'][:10] |
|
2429 | day = string_to_date(date_str, "%Y-%m-%d") |
|
2430 | return { |
|
2431 | 'title': title, |
|
2432 | 'img': [i['content'] for i in imgs], |
|
2433 | 'month': day.month, |
|
2434 | 'year': day.year, |
|
2435 | 'day': day.day, |
|
2436 | } |
|
2437 | ||
2438 | ||
@@ 1092-1116 (lines=25) @@ | ||
1089 | } |
|
1090 | ||
1091 | ||
1092 | class Mercworks(GenericNavigableComic): |
|
1093 | """Class to retrieve Mercworks comics.""" |
|
1094 | # Also on http://mercworks.tumblr.com |
|
1095 | name = 'mercworks' |
|
1096 | long_name = 'Mercworks' |
|
1097 | url = 'http://mercworks.net' |
|
1098 | get_first_comic_link = get_a_comicnavbase_comicnavfirst |
|
1099 | get_navi_link = get_link_rel_next |
|
1100 | ||
1101 | @classmethod |
|
1102 | def get_comic_info(cls, soup, link): |
|
1103 | """Get information about a particular comics.""" |
|
1104 | title = soup.find('meta', property='og:title')['content'] |
|
1105 | metadesc = soup.find('meta', property='og:description') |
|
1106 | desc = metadesc['content'] if metadesc else "" |
|
1107 | date_str = soup.find('meta', property='article:published_time')['content'][:10] |
|
1108 | day = string_to_date(date_str, "%Y-%m-%d") |
|
1109 | imgs = soup.find_all('meta', property='og:image') |
|
1110 | return { |
|
1111 | 'img': [i['content'] for i in imgs], |
|
1112 | 'title': title, |
|
1113 | 'desc': desc, |
|
1114 | 'day': day.day, |
|
1115 | 'month': day.month, |
|
1116 | 'year': day.year |
|
1117 | } |
|
1118 | ||
1119 | ||
@@ 3418-3439 (lines=22) @@ | ||
3415 | } |
|
3416 | ||
3417 | ||
3418 | class MarketoonistComics(GenericNavigableComic): |
|
3419 | """Class to retrieve Marketoonist Comics.""" |
|
3420 | name = 'marketoonist' |
|
3421 | long_name = 'Marketoonist' |
|
3422 | url = 'https://marketoonist.com/cartoons' |
|
3423 | get_first_comic_link = simulate_first_link |
|
3424 | get_navi_link = get_link_rel_next |
|
3425 | first_url = 'https://marketoonist.com/2002/10/the-8-types-of-brand-managers-2.html' |
|
3426 | ||
3427 | @classmethod |
|
3428 | def get_comic_info(cls, soup, link): |
|
3429 | """Get information about a particular comics.""" |
|
3430 | imgs = soup.find_all('meta', property='og:image') |
|
3431 | date_str = soup.find('meta', property='article:published_time')['content'][:10] |
|
3432 | day = string_to_date(date_str, "%Y-%m-%d") |
|
3433 | title = soup.find('meta', property='og:title')['content'] |
|
3434 | return { |
|
3435 | 'img': [i['content'] for i in imgs], |
|
3436 | 'day': day.day, |
|
3437 | 'month': day.month, |
|
3438 | 'year': day.year, |
|
3439 | 'title': title, |
|
3440 | } |
|
3441 | ||
3442 | ||
@@ 434-455 (lines=22) @@ | ||
431 | } |
|
432 | ||
433 | ||
434 | class GenericLeMondeBlog(GenericNavigableComic): |
|
435 | """Generic class to retrieve comics from Le Monde blogs.""" |
|
436 | _categories = ('LEMONDE', 'FRANCAIS') |
|
437 | get_navi_link = get_link_rel_next |
|
438 | get_first_comic_link = simulate_first_link |
|
439 | first_url = NotImplemented |
|
440 | ||
441 | @classmethod |
|
442 | def get_comic_info(cls, soup, link): |
|
443 | """Get information about a particular comics.""" |
|
444 | url2 = soup.find('link', rel='shortlink')['href'] |
|
445 | title = soup.find('meta', property='og:title')['content'] |
|
446 | date_str = soup.find("span", class_="entry-date").string |
|
447 | day = string_to_date(date_str, "%d %B %Y", "fr_FR.utf8") |
|
448 | imgs = soup.find_all('meta', property='og:image') |
|
449 | return { |
|
450 | 'title': title, |
|
451 | 'url2': url2, |
|
452 | 'img': [convert_iri_to_plain_ascii_uri(i['content']) for i in imgs], |
|
453 | 'month': day.month, |
|
454 | 'year': day.year, |
|
455 | 'day': day.day, |
|
456 | } |
|
457 | ||
458 |