|
@@ 2617-2647 (lines=31) @@
|
| 2614 |
|
|
| 2615 |
|
|
| 2616 |
|
class BuniComic(GenericNavigableComic): |
| 2617 |
|
"""Class to retrieve Buni Comics.""" |
| 2618 |
|
name = 'buni' |
| 2619 |
|
long_name = 'BuniComics' |
| 2620 |
|
url = 'http://www.bunicomic.com' |
| 2621 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 2622 |
|
get_navi_link = get_link_rel_next |
| 2623 |
|
|
| 2624 |
|
@classmethod |
| 2625 |
|
def get_comic_info(cls, soup, link): |
| 2626 |
|
"""Get information about a particular comics.""" |
| 2627 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 2628 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2629 |
|
assert len(imgs) == 1 |
| 2630 |
|
return { |
| 2631 |
|
'img': [i['src'] for i in imgs], |
| 2632 |
|
'title': imgs[0]['title'], |
| 2633 |
|
} |
| 2634 |
|
|
| 2635 |
|
|
| 2636 |
|
class GenericCommitStrip(GenericNavigableComic): |
| 2637 |
|
"""Generic class to retrieve Commit Strips in different languages.""" |
| 2638 |
|
get_navi_link = get_a_rel_next |
| 2639 |
|
|
| 2640 |
|
@classmethod |
| 2641 |
|
def get_comic_info(cls, soup, link): |
| 2642 |
|
"""Get information about a particular comics.""" |
| 2643 |
|
desc = soup.find('meta', property='og:description')['content'] |
| 2644 |
|
title = soup.find('meta', property='og:title')['content'] |
| 2645 |
|
imgs = soup.find('div', class_='entry-content').find_all('img') |
| 2646 |
|
title2 = ' '.join(i.get('title', '') for i in imgs) |
| 2647 |
|
return { |
| 2648 |
|
'title': title, |
| 2649 |
|
'title2': title2, |
| 2650 |
|
'description': desc, |
|
@@ 437-466 (lines=30) @@
|
| 434 |
|
class UneAnneeAuLycee(GenericLeMondeBlog): |
| 435 |
|
"""Class to retrieve Une Annee Au Lycee comics.""" |
| 436 |
|
name = 'lycee' |
| 437 |
|
long_name = 'Une Annee au Lycee' |
| 438 |
|
url = 'http://uneanneeaulycee.blog.lemonde.fr' |
| 439 |
|
|
| 440 |
|
@classmethod |
| 441 |
|
def get_first_comic_url(cls): |
| 442 |
|
return "http://uneanneeaulycee.blog.lemonde.fr/2016/06/13/la-semaine-du-bac-est-arrivee/" |
| 443 |
|
|
| 444 |
|
|
| 445 |
|
class Rall(GenericNavigableComic): |
| 446 |
|
"""Class to retrieve Ted Rall comics.""" |
| 447 |
|
# Also on http://www.gocomics.com/tedrall |
| 448 |
|
name = 'rall' |
| 449 |
|
long_name = "Ted Rall" |
| 450 |
|
url = "http://rall.com/comic" |
| 451 |
|
get_navi_link = get_link_rel_next |
| 452 |
|
|
| 453 |
|
@classmethod |
| 454 |
|
def get_first_comic_link(cls): |
| 455 |
|
"""Get link to first comics.""" |
| 456 |
|
# Not the first but I didn't find an efficient way to retrieve it |
| 457 |
|
return {'href': "http://rall.com/2014/01/30/los-angeles-times-cartoon-well-miss-those-california-flowers"} |
| 458 |
|
|
| 459 |
|
@classmethod |
| 460 |
|
def get_comic_info(cls, soup, link): |
| 461 |
|
"""Get information about a particular comics.""" |
| 462 |
|
title = soup.find('meta', property='og:title')['content'] |
| 463 |
|
author = soup.find("span", class_="author vcard").find("a").string |
| 464 |
|
date_str = soup.find("span", class_="entry-date").string |
| 465 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 466 |
|
desc = soup.find('meta', property='og:description')['content'] |
| 467 |
|
imgs = soup.find('div', class_='entry-content').find_all('img') |
| 468 |
|
imgs = imgs[:-7] # remove social media buttons |
| 469 |
|
return { |
SylvainDe /
ComicBookMaker
