|
@@ 1720-1746 (lines=27) @@
|
| 1717 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 1718 |
|
date_str = soup.find("span", class_="post-date").string |
| 1719 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 1720 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 1721 |
|
assert all(i['alt'] == i['title'] == title for i in imgs) |
| 1722 |
|
return { |
| 1723 |
|
'day': day.day, |
| 1724 |
|
'month': day.month, |
| 1725 |
|
'year': day.year, |
| 1726 |
|
'img': [i['src'] for i in imgs], |
| 1727 |
|
'title': title, |
| 1728 |
|
'author': author, |
| 1729 |
|
} |
| 1730 |
|
|
| 1731 |
|
|
| 1732 |
|
class BigFootJustice(GenericNavigableComic): |
| 1733 |
|
"""Class to retrieve Big Foot Justice comics.""" |
| 1734 |
|
# Also on http://tapastic.com/series/bigfoot-justice |
| 1735 |
|
name = 'bigfoot' |
| 1736 |
|
long_name = 'Big Foot Justice' |
| 1737 |
|
url = 'http://bigfootjustice.com' |
| 1738 |
|
get_first_comic_link = get_a_navi_navifirst |
| 1739 |
|
get_navi_link = get_a_navi_comicnavnext_navinext |
| 1740 |
|
|
| 1741 |
|
@classmethod |
| 1742 |
|
def get_comic_info(cls, soup, link): |
| 1743 |
|
"""Get information about a particular comics.""" |
| 1744 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 1745 |
|
assert all(i['title'] == i['alt'] for i in imgs) |
| 1746 |
|
title = ' '.join(i['title'] for i in imgs) |
| 1747 |
|
return { |
| 1748 |
|
'img': [i['src'] for i in imgs], |
| 1749 |
|
'title': title, |
|
@@ 2174-2197 (lines=24) @@
|
| 2171 |
|
|
| 2172 |
|
@classmethod |
| 2173 |
|
def get_comic_info(cls, soup, link): |
| 2174 |
|
"""Get information about a particular comics.""" |
| 2175 |
|
title = soup.find('meta', attrs={'name': 'twitter:title'})['content'] |
| 2176 |
|
description = soup.find('meta', attrs={'name': 'description'})['content'] |
| 2177 |
|
tags_prop = soup.find('meta', property='article:tag') |
| 2178 |
|
tags = tags_prop['content'] if tags_prop else "" |
| 2179 |
|
date_str = soup.find('meta', property='article:published_time')['content'][:10] |
| 2180 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 2181 |
|
imgs = soup.find_all('img', attrs={'data-recalc-dims': "1"}) |
| 2182 |
|
assert len(imgs) == 1 |
| 2183 |
|
return { |
| 2184 |
|
'title': title, |
| 2185 |
|
'description': description, |
| 2186 |
|
'tags': tags, |
| 2187 |
|
'alt': "".join(i['alt'] for i in imgs), |
| 2188 |
|
'img': [i['src'].rsplit('?', 1)[0] for i in imgs], |
| 2189 |
|
'month': day.month, |
| 2190 |
|
'year': day.year, |
| 2191 |
|
'day': day.day, |
| 2192 |
|
} |
| 2193 |
|
|
| 2194 |
|
|
| 2195 |
|
class AnythingComic(GenericComic): |
| 2196 |
|
"""Class to retrieve Anything Comics.""" |
| 2197 |
|
# Also on http://tapastic.com/series/anything |
| 2198 |
|
name = 'anythingcomic' |
| 2199 |
|
long_name = 'Anything Comic' |
| 2200 |
|
url = 'http://www.anythingcomic.com' |
SylvainDe /
ComicBookMaker
