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

merge from my lp branch

Browse Source
This commit is contained in:
Tom Scholl 2011-04-18 15:59:20 +00:00
commit 0744534b2d
2 changed files with 63 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
recipes/daily_mail_fast.recipe Normal file
View File

@ -0,0 +1,52 @@
from calibre.web.feeds.news import BasicNewsRecipe
class TheDailyMail(BasicNewsRecipe):
title = u'The Daily Mail (fast)'
oldest_article = 2
language = 'en_GB'
author = 'RufusA and Sujata Raman'
description = 'Faster and smaller version of the Daily Mail that does not download pictures'
simultaneous_downloads= 1
max_articles_per_feed = 50
extra_css = '''#js-article-text{font-family:Arial,Helvetica,sans-serif;}
h1{font-size:x-large; font-weight:bold;}
a.author{color:#003580;}
.js-article-text{font-size:50%;}
.imageCaption{font-size:x-small; font-weight:bold}
'''
remove_tags = [ dict(name='div', attrs={'class':['article-icon-links-container','print-or-mail-links cleared',
'social-links cleared','explore-links','relatedItems','intellicrumbs box','travel','moduleHalf']}),
dict(name='div', attrs={'id':['link-unit-wrapper','pushdown-ad','reader-comments','googleAds',]}),
dict(name='h3', attrs={'class':['social-links-title']}),
dict(name='span', attrs={'class':['clickToEnlargeTop']}),
dict(name=['img']),
]
#remove_tags_before = dict(name='div', attrs={'id':'content'})
keep_only_tags = [dict(name='div', attrs={'id':'js-article-text'})]
no_stylesheets = True
feeds = [
(u'Home', u'http://www.dailymail.co.uk/home/index.rss'),
(u'News', u'http://www.dailymail.co.uk/news/index.rss'),
(u'Sport', u'http://www.dailymail.co.uk/sport/index.rss'),
(u'TV and Showbiz', u'http://www.dailymail.co.uk/tvshowbiz/index.rss'),
(u'Femail', u'http://www.dailymail.co.uk/femail/index.rss'),
(u'Health', u'http://www.dailymail.co.uk/health/index.rss'),
(u'Science and Technology', u'http://www.dailymail.co.uk/sciencetech/index.rss'),
(u'Money', u'http://www.dailymail.co.uk/money/index.rss'),
(u'Property', u'http://www.dailymail.co.uk/property/index.rss'),
(u'Motoring', u'http://www.dailymail.co.uk/motoring/index.rss'),
(u'Travel', u'http://www.dailymail.co.uk/travel/index.rss')
]
#def print_version(self, url):
# main = url.partition('?')[0]
# return main + '?printingPage=true'

13
recipes/guardian.recipe
View File

@ -87,7 +87,13 @@ class Guardian(BasicNewsRecipe):
idx = soup.find('div', id='book-index')
for s in idx.findAll('strong', attrs={'class':'book'}):
a = s.find('a', href=True)
yield (self.tag_to_string(a), a['href'])
section_title = self.tag_to_string(a)
if not section_title in self.ignore_sections:
prefix = ''
if section_title != 'Main section':
prefix = section_title + ': '
for subsection in s.parent.findAll('a', attrs={'class':'book-section'}):
yield (prefix + self.tag_to_string(subsection), subsection['href'])
def find_articles(self, url):
soup = self.index_to_soup(url)
@ -114,10 +120,7 @@ class Guardian(BasicNewsRecipe):
try:
feeds = []
for title, href in self.find_sections():
if not title in self.ignore_sections:
feeds.append((title, list(self.find_articles(href))))
feeds.append((title, list(self.find_articles(href))))
return feeds
except:
raise NotImplementedError