Improved recipe for CNN

This commit is contained in:
Kovid Goyal 2010-01-04 22:34:33 -07:00
parent 25593455d4
commit 536e629356
2 changed files with 36 additions and 37 deletions

View File

@ -4,13 +4,14 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
Profile to download CNN Profile to download CNN
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class CNN(BasicNewsRecipe): class CNN(BasicNewsRecipe):
title = 'CNN' title = 'CNN'
description = 'Global news' description = 'Global news'
timefmt = ' [%d %b %Y]' timefmt = ' [%d %b %Y]'
__author__ = 'Kovid Goyal and Sujata Raman' __author__ = 'Krittika Goyal and Sujata Raman'
language = 'en' language = 'en'
no_stylesheets = True no_stylesheets = True
@ -18,7 +19,8 @@ class CNN(BasicNewsRecipe):
oldest_article = 15 oldest_article = 15
recursions = 1 recursions = 1
match_regexps = [r'http://sportsillustrated.cnn.com/.*/[1-9].html'] match_regexps = [r'http://sportsillustrated.cnn.com/.*/[1-9].html']
max_articles_per_feed = 25
extra_css = ''' extra_css = '''
.cnn_strycntntlft{font-family :Arial,Helvetica,sans-serif;} .cnn_strycntntlft{font-family :Arial,Helvetica,sans-serif;}
h2{font-family :Arial,Helvetica,sans-serif; font-size:x-small} h2{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
@ -44,7 +46,7 @@ class CNN(BasicNewsRecipe):
.cnnInlineT1Caption{font-family :Arial,Helvetica,sans-serif; font-size:x-small;font-weight:bold;} .cnnInlineT1Caption{font-family :Arial,Helvetica,sans-serif; font-size:x-small;font-weight:bold;}
.cnnInlineT1Credit{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#333333;} .cnnInlineT1Credit{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#333333;}
.col10{color:#5A637E;} .col10{color:#5A637E;}
.cnnInlineRailBulletList{color:black;} .cnnInlineRailBulletList{color:black;}
.cnnLine0{font-family :Arial,Helvetica,sans-serif; color:#666666;font-weight:bold;} .cnnLine0{font-family :Arial,Helvetica,sans-serif; color:#666666;font-weight:bold;}
.cnnTimeStamp{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#333333;} .cnnTimeStamp{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#333333;}
.galleryhedDek{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#575757;} .galleryhedDek{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#575757;}
@ -55,31 +57,22 @@ class CNN(BasicNewsRecipe):
.captionname{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#575757;} .captionname{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#575757;}
inStoryIE{{font-family :Arial,Helvetica,sans-serif; font-size:x-small;} inStoryIE{{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
''' '''
keep_only_tags = [
dict(name='div', attrs={'class':["cnnWCBoxContent","cnnContent","cnnMainBodySecs","cnn_storyarea","cnn_strycntntlft","cnn_strytmstmp"]}),
dict(name='div', attrs={'id':["contentBody","content"]}),
dict(name='td', attrs={'id':["cnnRecapStory"]}),
dict(name='td', attrs={'class':["cnnBigSideLeft"]}),
]
remove_tags = [
dict(name='div', attrs={'class':["cnnInlineRailSelectList","cnn_strycntntrgt","cnn_strybtntools","cnn_strylctcntr cnn_strylctcqrelt","cnn_strylceclbtn","cnn_stryftsbttm","cnn_strybtmmorebx","storyLink","article-tools clearfix","widget video related-video vList","cnnFooterBox","scrollArrows","boxHeading","cnnInlineMailbag","mainCol_lastBlock","cnn_bookmarks","cnnFooterBox","cnnEndOfStory","cnnInlineSL","cnnStoryHighlights","cnnFooterClick","cnnSnapShotHeader","cnnStoryToolsFooter","cnnWsnr","cnnUGCBox","cnnTopNewsModule","cnnStoryElementBox","cnnStoryPhotoBoxNavigation"]}),
dict(name='span', attrs={'class':["cnnEmbeddedMosLnk"]}),
dict(name='div', attrs={'id':["cnnIncldHlder","articleCommentsContainer","featuredContent","superstarsWidget","shareMenuContainer","rssMenuContainer","storyBrandingBanner","cnnRightCol","siteFeatures","quigo628","rightColumn","clickIncludeBox","cnnHeaderRightCol","cnnSCFontLabel","cnnSnapShotBottomRight","cnnSCFontButtons","rightColumn"]}),
dict(name='p', attrs={'class':["cnnTopics"]}),
dict(name='td', attrs={'class':["cnnRightRail"]}),
dict(name='table', attrs={'class':["cnnTMbox"]}),
dict(name='ul', attrs={'id':["cnnTopNav","cnnBotNav","cnnSBNav"]}),
dict(name='div', attrs={'id':["cnn_ftrcntnt"]})
]
# def print_version(self, url): #remove_tags_before = dict(name='h1', attrs={'class':'heading'})
# return 'http://www.printthis.clickability.com/pt/printThis?clickMap=printThis&fb=Y&url=' + url #remove_tags_after = dict(name='td', attrs={'class':'newptool1'})
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':['cnnEndOfStory', 'cnnShareThisItem', 'cnn_strylctcntr cnn_strylctcqrelt', 'cnnShareBoxContent', 'cnn_strybtmcntnt', 'cnn_strycntntrgt']}),
dict(name='div', attrs={'id':['IEContainer', 'clickIncludeBox']}),
#dict(name='ul', attrs={'class':'article-tools'}),
#dict(name='ul', attrs={'class':'articleTools'}),
]
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'),
@ -91,10 +84,15 @@ class CNN(BasicNewsRecipe):
('Offbeat', 'http://rss.cnn.com/rss/cnn_offbeat.rss'), ('Offbeat', 'http://rss.cnn.com/rss/cnn_offbeat.rss'),
('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): def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'class':'cnnBody_Left'})
for tag in soup.findAll(name=['ul','li']): if story is None:
tag.name = 'div' story = soup.find(name='div', attrs={'id':'cnnContentContainer'})
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
return soup body = soup.find(name='body')
body.insert(0, story)
else:
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
body = soup.find(name='body')
body.insert(0, story)
return soup

View File

@ -529,15 +529,16 @@ class Application(QApplication):
self.load_translations() self.load_translations()
qt_app = self qt_app = self
self.setStyleSheet(''' if islinux:
QToolTip { self.setStyleSheet('''
border: 2px solid black; QToolTip {
padding: 5px; border: 2px solid black;
border-radius: 10px; padding: 5px;
opacity: 200; border-radius: 10px;
background-color: white; opacity: 200;
} background-color: #e1e1ff;
''') }
''')
def load_translations(self): def load_translations(self):