|
@@ 3440-3463 (lines=24) @@
|
| 3437 |
|
def get_comic_info(cls, soup, link): |
| 3438 |
|
"""Get information about a particular comics.""" |
| 3439 |
|
title = soup.find('meta', property='og:title')['content'] |
| 3440 |
|
desc = soup.find('meta', property='og:description')['content'] |
| 3441 |
|
date_str = soup.find('time', class_='published')['datetime'] |
| 3442 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 3443 |
|
author = soup.find('a', rel='author').string |
| 3444 |
|
div_content = (soup.find('div', class_="body entry-content") or |
| 3445 |
|
soup.find('div', class_="special-content")) |
| 3446 |
|
imgs = div_content.find_all('img') |
| 3447 |
|
imgs = [i for i in imgs if i.get('src') is not None] |
| 3448 |
|
assert all('title' not in i or i['alt'] == i['title'] for i in imgs) |
| 3449 |
|
alt = imgs[0].get('alt', "") if imgs else [] |
| 3450 |
|
return { |
| 3451 |
|
'title': title, |
| 3452 |
|
'alt': alt, |
| 3453 |
|
'description': desc, |
| 3454 |
|
'author': author, |
| 3455 |
|
'day': day.day, |
| 3456 |
|
'month': day.month, |
| 3457 |
|
'year': day.year, |
| 3458 |
|
'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs], |
| 3459 |
|
} |
| 3460 |
|
|
| 3461 |
|
|
| 3462 |
|
class GloryOwlComix(GenericNavigableComic): |
| 3463 |
|
"""Class to retrieve Glory Owl comics.""" |
| 3464 |
|
name = 'gloryowl' |
| 3465 |
|
long_name = 'Glory Owl' |
| 3466 |
|
url = 'http://gloryowlcomix.blogspot.fr' |
|
@@ 3373-3396 (lines=24) @@
|
| 3370 |
|
def get_first_comic_link(cls): |
| 3371 |
|
"""Get link to first comics.""" |
| 3372 |
|
return get_soup_at_url(cls.url).find('a', class_='first') |
| 3373 |
|
|
| 3374 |
|
@classmethod |
| 3375 |
|
def get_navi_link(cls, last_soup, next_): |
| 3376 |
|
"""Get link to next or previous comic.""" |
| 3377 |
|
return last_soup.find('a', class_='next' if next_ else 'prev') |
| 3378 |
|
|
| 3379 |
|
@classmethod |
| 3380 |
|
def get_comic_info(cls, soup, link): |
| 3381 |
|
"""Get information about a particular comics.""" |
| 3382 |
|
title = soup.find('meta', property='og:title')['content'] |
| 3383 |
|
date_str = soup.find('time')["datetime"] |
| 3384 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 3385 |
|
imgs = soup.find_all('meta', property='og:image') |
| 3386 |
|
return { |
| 3387 |
|
'title': title, |
| 3388 |
|
'img': [i['content'] for i in imgs], |
| 3389 |
|
'day': day.day, |
| 3390 |
|
'month': day.month, |
| 3391 |
|
'year': day.year, |
| 3392 |
|
} |
| 3393 |
|
|
| 3394 |
|
|
| 3395 |
|
class TuMourrasMoinsBete(GenericNavigableComic): |
| 3396 |
|
"""Class to retrieve Tu Mourras Moins Bete comics.""" |
| 3397 |
|
name = 'mourrasmoinsbete' |
| 3398 |
|
long_name = 'Tu Mourras Moins Bete' |
| 3399 |
|
url = 'http://tumourrasmoinsbete.blogspot.fr' |
|
@@ 3183-3206 (lines=24) @@
|
| 3180 |
|
|
| 3181 |
|
class EarthExplodes(GenericNavigableComic): |
| 3182 |
|
"""Class to retrieve The Earth Explodes comics.""" |
| 3183 |
|
name = 'earthexplodes' |
| 3184 |
|
long_name = 'The Earth Explodes' |
| 3185 |
|
url = 'http://www.earthexplodes.com' |
| 3186 |
|
get_url_from_link = join_cls_url_to_href |
| 3187 |
|
get_first_comic_link = simulate_first_link |
| 3188 |
|
first_url = 'http://www.earthexplodes.com/comics/000/' |
| 3189 |
|
|
| 3190 |
|
@classmethod |
| 3191 |
|
def get_navi_link(cls, last_soup, next_): |
| 3192 |
|
"""Get link to next or previous comic.""" |
| 3193 |
|
return last_soup.find('a', id='next' if next_ else 'prev') |
| 3194 |
|
|
| 3195 |
|
@classmethod |
| 3196 |
|
def get_comic_info(cls, soup, link): |
| 3197 |
|
"""Get information about a particular comics.""" |
| 3198 |
|
title = soup.find('title').string |
| 3199 |
|
imgs = soup.find('div', id='image').find_all('img') |
| 3200 |
|
alt = imgs[0].get('title', '') |
| 3201 |
|
return { |
| 3202 |
|
'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs], |
| 3203 |
|
'title': title, |
| 3204 |
|
'alt': alt, |
| 3205 |
|
} |
| 3206 |
|
|
| 3207 |
|
|
| 3208 |
|
class PomComics(GenericNavigableComic): |
| 3209 |
|
"""Class to retrieve PomComics.""" |