Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update The Straits Times

Browse Source
This commit is contained in:
Kovid Goyal 2017-01-30 08:56:27 +05:30
parent 2c3ffd8dc3
commit 1543f235f9
1 changed files with 16 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
recipes/straitstimes.recipe
View File

@ -43,19 +43,23 @@ class StraitsTimes(BasicNewsRecipe):
remove_tags_after = dict(name='div', attrs={'class': 'hr_thin'})
feeds = [
(u'Singapore', u'http://www.straitstimes.com/news/singapore/rss.xml'),
(u'Asia', u'http://www.straitstimes.com/news/asia/rss.xml'),
(u'Business', u'http://www.straitstimes.com/news/business/rss.xml'),
(u'Sport', u'http://www.straitstimes.com/news/sport/rss.xml'),
(u'World', u'http://www.straitstimes.com/news/world/rss.xml'),
(u'Lifestyle', u'http://www.straitstimes.com/news/lifestyle/rss.xml'),
(u'Digital Life', u'http://www.straitstimes.com/news/digital-life/rss.xml')
(u'Top of the News' , u'http://www.straitstimes.com/print/top-of-the-news/rss.xml')
,(u'World' , u'http://www.straitstimes.com/print/world/rss.xml')
,(u'Home' , u'http://www.straitstimes.com/print/home/rss.xml')
,(u'Business' , u'http://www.straitstimes.com/print/business/rss.xml')
,(u'Life' , u'http://www.straitstimes.com/print/life/rss.xml')
,(u'Science' , u'http://www.straitstimes.com/print/science/rss.xml')
,(u'Digital' , u'http://www.straitstimes.com/print/digital/rss.xml')
,(u'Insight' , u'http://www.straitstimes.com/print/insight/rss.xml')
,(u'Opinion' , u'http://www.straitstimes.com/print/opinion/rss.xml')
,(u'Forum' , u'http://www.straitstimes.com/print/forum/rss.xml')
,(u'Big Picture' , u'http://www.straitstimes.com/print/big-picture/rss.xml')
,(u'Community' , u'http://www.straitstimes.com/print/community/rss.xml')
,(u'Education' , u'http://www.straitstimes.com/print/education/rss.xml')
]
def preprocess_html(self, soup):
for a in soup.findAll('a', attrs={'class': 'thumb'}):
img = a.find('img')
if img is not None:
img['src'] = a['href']
for img in soup.findAll('img', srcset=True):
img['src'] = img['srcset'].partition(' ')[0]
img['srcset'] = ''
return soup