|
@@ 1809-1828 (lines=20) @@
|
| 1806 |
|
get_first_comic_link = simulate_first_link |
| 1807 |
|
first_url = 'http://respawncomic.com/comic/c0001/' |
| 1808 |
|
|
| 1809 |
|
@classmethod |
| 1810 |
|
def get_comic_info(cls, soup, link): |
| 1811 |
|
"""Get information about a particular comics.""" |
| 1812 |
|
title = soup.find('meta', property='og:title')['content'] |
| 1813 |
|
author = soup.find('meta', attrs={'name': 'shareaholic:article_author_name'})['content'] |
| 1814 |
|
date_str = soup.find('meta', attrs={'name': 'shareaholic:article_published_time'})['content'] |
| 1815 |
|
date_str = date_str[:10] |
| 1816 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 1817 |
|
imgs = soup.find_all('meta', property='og:image') |
| 1818 |
|
skip_imgs = { |
| 1819 |
|
'http://respawncomic.com/wp-content/uploads/2016/03/site/HAROLD2.png', |
| 1820 |
|
'http://respawncomic.com/wp-content/uploads/2016/03/site/DEVA.png' |
| 1821 |
|
} |
| 1822 |
|
return { |
| 1823 |
|
'title': title, |
| 1824 |
|
'author': author, |
| 1825 |
|
'day': day.day, |
| 1826 |
|
'month': day.month, |
| 1827 |
|
'year': day.year, |
| 1828 |
|
'img': [i['content'] for i in imgs if i['content'] not in skip_imgs], |
| 1829 |
|
} |
| 1830 |
|
|
| 1831 |
|
|
|
@@ 526-541 (lines=16) @@
|
| 523 |
|
li = last_soup.find('li', class_='prev' if next_ else 'next') |
| 524 |
|
return li.find('a') if li else None |
| 525 |
|
|
| 526 |
|
@classmethod |
| 527 |
|
def get_comic_info(cls, soup, link): |
| 528 |
|
"""Get information about a particular comics.""" |
| 529 |
|
short_url = soup.find('link', rel='shortlink')['href'] |
| 530 |
|
title = soup.find('meta', attrs={'name': 'twitter:title'})['content'] |
| 531 |
|
imgs = soup.find_all('meta', property='og:image') |
| 532 |
|
date_str = soup.find('span', property='dc:date')['content'] |
| 533 |
|
date_str = date_str[:10] |
| 534 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 535 |
|
return { |
| 536 |
|
'short_url': short_url, |
| 537 |
|
'title': title, |
| 538 |
|
'img': [i['content'] for i in imgs], |
| 539 |
|
'day': day.day, |
| 540 |
|
'month': day.month, |
| 541 |
|
'year': day.year, |
| 542 |
|
} |
| 543 |
|
|
| 544 |
|
|
|
@@ 4528-4542 (lines=15) @@
|
| 4525 |
|
gocomics = 'http://www.gocomics.com' |
| 4526 |
|
return urljoin_wrapper(gocomics, link['href']) |
| 4527 |
|
|
| 4528 |
|
@classmethod |
| 4529 |
|
def get_comic_info(cls, soup, link): |
| 4530 |
|
"""Get information about a particular comics.""" |
| 4531 |
|
date_str = soup.find('meta', property='article:published_time')['content'] |
| 4532 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 4533 |
|
imgs = soup.find('picture', class_='img-fluid item-comic-image').find_all('img') |
| 4534 |
|
author = soup.find('meta', property='article:author')['content'] |
| 4535 |
|
tags = soup.find('meta', property='article:tag')['content'] |
| 4536 |
|
return { |
| 4537 |
|
'day': day.day, |
| 4538 |
|
'month': day.month, |
| 4539 |
|
'year': day.year, |
| 4540 |
|
'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs], |
| 4541 |
|
'author': author, |
| 4542 |
|
'tags': tags, |
| 4543 |
|
} |
| 4544 |
|
|
| 4545 |
|
|
|
@@ 2984-2998 (lines=15) @@
|
| 2981 |
|
# prev is next / next is prev |
| 2982 |
|
return last_soup.find('li', class_='previous' if next_ else 'next').find('a') |
| 2983 |
|
|
| 2984 |
|
@classmethod |
| 2985 |
|
def get_comic_info(cls, soup, link): |
| 2986 |
|
"""Get information about a particular comics.""" |
| 2987 |
|
date_str = soup.find('time', class_='published')['datetime'] |
| 2988 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 2989 |
|
author = soup.find('span', class_='blog-author').find('a').string |
| 2990 |
|
title = soup.find('meta', property='og:title')['content'] |
| 2991 |
|
imgs = soup.find_all('meta', itemprop='image') |
| 2992 |
|
return { |
| 2993 |
|
'img': [i['content'] for i in imgs], |
| 2994 |
|
'title': title, |
| 2995 |
|
'author': author, |
| 2996 |
|
'day': day.day, |
| 2997 |
|
'month': day.month, |
| 2998 |
|
'year': day.year, |
| 2999 |
|
} |
| 3000 |
|
|
| 3001 |
|
|
|
@@ 3052-3064 (lines=13) @@
|
| 3049 |
|
"""Get link to first comics.""" |
| 3050 |
|
return get_soup_at_url(cls.url).find('a', class_='webcomic-link webcomic1-link first-webcomic-link first-webcomic1-link') |
| 3051 |
|
|
| 3052 |
|
@classmethod |
| 3053 |
|
def get_comic_info(cls, soup, link): |
| 3054 |
|
"""Get information about a particular comics.""" |
| 3055 |
|
title = soup.find('meta', property='og:title')['content'] |
| 3056 |
|
imgs = soup.find('div', class_='webcomic-image').find_all('img') |
| 3057 |
|
date_str = soup.find('meta', property='article:published_time')['content'][:10] |
| 3058 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 3059 |
|
return { |
| 3060 |
|
'title': title, |
| 3061 |
|
'day': day.day, |
| 3062 |
|
'month': day.month, |
| 3063 |
|
'year': day.year, |
| 3064 |
|
'img': [i['src'] for i in imgs], |
| 3065 |
|
} |
| 3066 |
|
|
| 3067 |
|
|
SylvainDe /
ComicBookMaker
