Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update CNN

Browse Source
This commit is contained in:
Kovid Goyal 2015-01-31 22:56:58 +05:30
parent 1235bc5ab2
commit c9a0f23173
1 changed files with 22 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
recipes/cnn.recipe
View File

@ -18,8 +18,9 @@ class CNN(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
oldest_article = 15 oldest_article = 15
#recursions = 1 ignore_duplicate_articles = {'url'}
#match_regexps = [r'http://sportsillustrated.cnn.com/.*/[1-9].html'] # recursions = 1
# match_regexps = [r'http://sportsillustrated.cnn.com/.*/[1-9].html']
max_articles_per_feed = 25 max_articles_per_feed = 25
extra_css = ''' extra_css = '''
@ -36,25 +37,18 @@ class CNN(BasicNewsRecipe):
(re.compile(r'<style.*?</style>', re.DOTALL), lambda m: ''), (re.compile(r'<style.*?</style>', re.DOTALL), lambda m: ''),
] ]
keep_only_tags = [dict(id=['cnnContentContainer', 'storycontent'])] keep_only_tags = [
remove_tags = [ dict(id=['body-text', 'storycontent']),
{'class':['cnn_strybtntools', 'cnn_strylftcntnt', dict(attrs={'class':['pg-headline', 'metadata']}),
'cnn_strybtntools', 'cnn_strybtntoolsbttm', 'cnn_strybtmcntnt', ]
'cnn_strycntntrgt', 'hed_side', 'foot', 'cnn_strylftcntnt cnn_strylftcexpbx']}, remove_tags = [
{'class':['cnn_html_media_title_new', 'cnn_html_media_title_new cnn_html_media_title_none',
'cnnArticleGalleryCaptionControlText', 'articleGalleryNavContainer']},
{'id':['articleGalleryNav00JumpPrev', 'articleGalleryNav00Prev',
'articleGalleryNav00Next', 'articleGalleryNav00JumpNext']},
{'style':['display:none']},
dict(id=['ie_column']),
] ]
feeds = [ feeds = [
('Top News', 'http://rss.cnn.com/rss/cnn_topstories.rss'), ('Top News', 'http://rss.cnn.com/rss/cnn_topstories.rss'),
('World', 'http://rss.cnn.com/rss/cnn_world.rss'), ('World', 'http://rss.cnn.com/rss/cnn_world.rss'),
('U.S.', 'http://rss.cnn.com/rss/cnn_us.rss'), ('U.S.', 'http://rss.cnn.com/rss/cnn_us.rss'),
#('Sports', 'http://rss.cnn.com/rss/si_topstories.rss'), # ('Sports', 'http://rss.cnn.com/rss/si_topstories.rss'),
('Business', 'http://rss.cnn.com/rss/money_latest.rss'), ('Business', 'http://rss.cnn.com/rss/money_latest.rss'),
('Politics', 'http://rss.cnn.com/rss/cnn_allpolitics.rss'), ('Politics', 'http://rss.cnn.com/rss/cnn_allpolitics.rss'),
('Law', 'http://rss.cnn.com/rss/cnn_law.rss'), ('Law', 'http://rss.cnn.com/rss/cnn_law.rss'),
@ -67,9 +61,21 @@ class CNN(BasicNewsRecipe):
('Most Popular', 'http://rss.cnn.com/rss/cnn_mostpopular.rss') ('Most Popular', 'http://rss.cnn.com/rss/cnn_mostpopular.rss')
] ]
def preprocess_html(self, soup):
body = soup.find('body')
for h2 in soup.findAll(attrs={'class':'pg-headline'}):
h2.extract()
body.insert(0, h2)
for img in soup.findAll('img', attrs={'data-src-medium':True}):
img['src'] = img['data-src-medium']
return soup
def get_article_url(self, article): def get_article_url(self, article):
ans = BasicNewsRecipe.get_article_url(self, article) ans = BasicNewsRecipe.get_article_url(self, article)
return ans.partition('?')[0] ans = ans.partition('?')[0]
if '.com/videos/' in ans:
ans = None
return ans
def get_masthead_url(self): def get_masthead_url(self):
masthead = 'http://i.cdn.turner.com/cnn/.element/img/3.0/global/header/intl/hdr-globe-central.gif' masthead = 'http://i.cdn.turner.com/cnn/.element/img/3.0/global/header/intl/hdr-globe-central.gif'