Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Wired Daily Edition

Browse Source
This commit is contained in:
Kovid Goyal 2014-03-17 09:16:05 +05:30
parent 3bdf4921c7
commit e6e4a61ecc
1 changed files with 8 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
recipes/wired_daily.recipe
View File

@ -2,10 +2,8 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.chardet import xml_to_unicode
class Wired_Daily(BasicNewsRecipe): class Wired_Daily(BasicNewsRecipe):
@ -14,22 +12,13 @@ class Wired_Daily(BasicNewsRecipe):
description = 'Technology news' description = 'Technology news'
timefmt = ' [%Y%b%d %H%M]' timefmt = ' [%Y%b%d %H%M]'
language = 'en' language = 'en'
use_embedded_content = False
no_stylesheets = True no_stylesheets = True
preprocess_regexps = [(re.compile(r'<head.*</head>', re.DOTALL), lambda m: keep_only_tags = [ # dict(name= 'div', id ='liveblog-hdr'),
'<head></head>')] dict(name='div', attrs={'class': 'post'})]
remove_tags_before = dict(name='div', id='content')
remove_tags = [dict(id=['header', 'commenting_module', 'post_nav',
'social_tools', 'sidebar', 'footer', 'social_wishlist', 'pgwidget',
'outerWrapper', 'inf_widget']),
{'class':['entryActions', 'advertisement', 'entryTags']},
dict(name=['noscript', 'script']),
dict(name='h4', attrs={'class':re.compile(r'rat\d+')}),
{'class':lambda x: x and x.startswith('contentjump')},
dict(name='li', attrs={'class':['entryCategories', 'entryEdit']})]
remove_tags = [dict(name='div', attrs={'class': 'social-top'})]
feeds = [ feeds = [
('Top News', 'http://feeds.wired.com/wired/index'), ('Top News', 'http://feeds.wired.com/wired/index'),
@ -49,11 +38,8 @@ class Wired_Daily(BasicNewsRecipe):
('Science', 'http://www.wired.com/wiredscience/feed/'), ('Science', 'http://www.wired.com/wiredscience/feed/'),
] ]
def populate_article_metadata(self, article, soup, first): def preprocess_html(self, soup):
if article.text_summary: for img in soup.findAll('img', attrs={'data-lazy-src':True}):
article.text_summary = xml_to_unicode(article.text_summary, img['src'] = img['data-lazy-src']
resolve_entities=True)[0] return soup
def print_version(self, url):
return url + '/all/1'