@@ 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 | ||
@@ 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 | ||
@@ 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 | ||
@@ 2444-2468 (lines=25) @@ | ||
2441 | } |
|
2442 | ||
2443 | ||
2444 | class LinsEditions(GenericNavigableComic): |
|
2445 | """Class to retrieve L.I.N.S. Editions comics.""" |
|
2446 | # Also on https://linscomics.tumblr.com |
|
2447 | # Now on https://warandpeas.com |
|
2448 | name = 'lins' |
|
2449 | long_name = 'L.I.N.S. Editions' |
|
2450 | url = 'https://linsedition.com' |
|
2451 | _categories = ('LINS', ) |
|
2452 | get_navi_link = get_link_rel_next |
|
2453 | get_first_comic_link = simulate_first_link |
|
2454 | first_url = 'https://linsedition.com/2011/09/07/l-i-n-s/' |
|
2455 | ||
2456 | @classmethod |
|
2457 | def get_comic_info(cls, soup, link): |
|
2458 | """Get information about a particular comics.""" |
|
2459 | title = soup.find('meta', property='og:title')['content'] |
|
2460 | imgs = soup.find_all('meta', property='og:image') |
|
2461 | date_str = soup.find('meta', property='article:published_time')['content'][:10] |
|
2462 | day = string_to_date(date_str, "%Y-%m-%d") |
|
2463 | return { |
|
2464 | 'title': title, |
|
2465 | 'img': [i['content'] for i in imgs], |
|
2466 | 'month': day.month, |
|
2467 | 'year': day.year, |
|
2468 | 'day': day.day, |
|
2469 | } |
|
2470 | ||
2471 | ||
@@ 3451-3472 (lines=22) @@ | ||
3448 | } |
|
3449 | ||
3450 | ||
3451 | class MarketoonistComics(GenericNavigableComic): |
|
3452 | """Class to retrieve Marketoonist Comics.""" |
|
3453 | name = 'marketoonist' |
|
3454 | long_name = 'Marketoonist' |
|
3455 | url = 'https://marketoonist.com/cartoons' |
|
3456 | get_first_comic_link = simulate_first_link |
|
3457 | get_navi_link = get_link_rel_next |
|
3458 | first_url = 'https://marketoonist.com/2002/10/the-8-types-of-brand-managers-2.html' |
|
3459 | ||
3460 | @classmethod |
|
3461 | def get_comic_info(cls, soup, link): |
|
3462 | """Get information about a particular comics.""" |
|
3463 | imgs = soup.find_all('meta', property='og:image') |
|
3464 | date_str = soup.find('meta', property='article:published_time')['content'][:10] |
|
3465 | day = string_to_date(date_str, "%Y-%m-%d") |
|
3466 | title = soup.find('meta', property='og:title')['content'] |
|
3467 | return { |
|
3468 | 'img': [i['content'] for i in imgs], |
|
3469 | 'day': day.day, |
|
3470 | 'month': day.month, |
|
3471 | 'year': day.year, |
|
3472 | 'title': title, |
|
3473 | } |
|
3474 | ||
3475 |