Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Improve IHT and Guardian. Fixes #749362 (Recipe fixes for International Herald Tribune, Guardian)

Browse Source
This commit is contained in:
Kovid Goyal 2011-04-03 09:13:02 -06:00
commit f083e2e21c
2 changed files with 12 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
recipes/guardian.recipe
View File

@ -36,6 +36,7 @@ class Guardian(BasicNewsRecipe):
remove_tags = [
dict(name='div', attrs={'class':["video-content","videos-third-column"]}),
dict(name='div', attrs={'id':["article-toolbox","subscribe-feeds",]}),
dict(name='div', attrs={'class':["guardian-tickets promo-component",]}),
dict(name='ul', attrs={'class':["pagination"]}),
dict(name='ul', attrs={'id':["content-actions"]}),
#dict(name='img'),

18
recipes/iht.recipe
View File

@ -15,10 +15,10 @@ class InternationalHeraldTribune(BasicNewsRecipe):
language = 'en'
oldest_article = 1
max_articles_per_feed = 10
max_articles_per_feed = 30
no_stylesheets = True
remove_tags = [dict(name='div', attrs={'class':'footer'}),
remove_tags = [dict(name='div', attrs={'class':['footer','header']}),
dict(name=['form'])]
preprocess_regexps = [
(re.compile(r'<!-- webtrends.*', re.DOTALL),
@ -26,6 +26,8 @@ class InternationalHeraldTribune(BasicNewsRecipe):
]
extra_css = '.headline {font-size: x-large;} \n .fact { padding-top: 10pt }'
remove_empty_feeds = True
feeds = [
(u'Frontpage', u'http://www.iht.com/rss/frontpage.xml'),
(u'Business', u'http://www.iht.com/rss/business.xml'),
@ -46,13 +48,15 @@ class InternationalHeraldTribune(BasicNewsRecipe):
]
temp_files = []
articles_are_obfuscated = True
def get_obfuscated_article(self, url, logger):
masthead_url = 'http://graphics8.nytimes.com/images/misc/iht-masthead-logo.gif'
def get_obfuscated_article(self, url):
br = self.get_browser()
br.open(url)
br.select_form(name='printFriendly')
res = br.submit()
html = res.read()
response1 = br.follow_link(url_regex=re.compile(r'.*pagewanted=print.*'))
html = response1.read()
self.temp_files.append(PersistentTemporaryFile('_iht.html'))
self.temp_files[-1].write(html)
self.temp_files[-1].close()