|
@@ 4319-4333 (lines=15) @@
|
| 4316 |
|
gocomics = 'http://www.gocomics.com' |
| 4317 |
|
return urljoin_wrapper(gocomics, link['href']) |
| 4318 |
|
|
| 4319 |
|
@classmethod |
| 4320 |
|
def get_comic_info(cls, soup, link): |
| 4321 |
|
"""Get information about a particular comics.""" |
| 4322 |
|
date_str = soup.find('meta', property='article:published_time')['content'] |
| 4323 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 4324 |
|
imgs = soup.find('picture', class_='img-fluid item-comic-image').find_all('img') |
| 4325 |
|
author = soup.find('meta', property='article:author')['content'] |
| 4326 |
|
tags = soup.find('meta', property='article:tag')['content'] |
| 4327 |
|
return { |
| 4328 |
|
'day': day.day, |
| 4329 |
|
'month': day.month, |
| 4330 |
|
'year': day.year, |
| 4331 |
|
'img': [i['src'] for i in imgs], |
| 4332 |
|
'author': author, |
| 4333 |
|
'tags': tags, |
| 4334 |
|
} |
| 4335 |
|
|
| 4336 |
|
|
|
@@ 3003-3015 (lines=13) @@
|
| 3000 |
|
"""Get link to first comics.""" |
| 3001 |
|
return get_soup_at_url(cls.url).find('a', class_='webcomic-link webcomic1-link first-webcomic-link first-webcomic1-link') |
| 3002 |
|
|
| 3003 |
|
@classmethod |
| 3004 |
|
def get_comic_info(cls, soup, link): |
| 3005 |
|
"""Get information about a particular comics.""" |
| 3006 |
|
title = soup.find('meta', property='og:title')['content'] |
| 3007 |
|
imgs = soup.find('div', class_='webcomic-image').find_all('img') |
| 3008 |
|
date_str = soup.find('meta', property='article:published_time')['content'][:10] |
| 3009 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 3010 |
|
return { |
| 3011 |
|
'title': title, |
| 3012 |
|
'day': day.day, |
| 3013 |
|
'month': day.month, |
| 3014 |
|
'year': day.year, |
| 3015 |
|
'img': [i['src'] for i in imgs], |
| 3016 |
|
} |
| 3017 |
|
|
| 3018 |
|
|
|
@@ 2707-2718 (lines=12) @@
|
| 2704 |
|
get_first_comic_link = simulate_first_link |
| 2705 |
|
first_url = NotImplemented |
| 2706 |
|
|
| 2707 |
|
@classmethod |
| 2708 |
|
def get_comic_info(cls, soup, link): |
| 2709 |
|
"""Get information about a particular comics.""" |
| 2710 |
|
desc = soup.find('meta', property='og:description')['content'] |
| 2711 |
|
title = soup.find('meta', property='og:title')['content'] |
| 2712 |
|
imgs = soup.find('div', class_='entry-content').find_all('img') |
| 2713 |
|
title2 = ' '.join(i.get('title', '') for i in imgs) |
| 2714 |
|
return { |
| 2715 |
|
'title': title, |
| 2716 |
|
'title2': title2, |
| 2717 |
|
'description': desc, |
| 2718 |
|
'img': [urljoin_wrapper(cls.url, convert_iri_to_plain_ascii_uri(i['src'])) for i in imgs], |
| 2719 |
|
} |
| 2720 |
|
|
| 2721 |
|
|