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

Fix #4226 (London Review of Books fails to load completely. An index and table of contents is the only pages in the feed.)

Browse Source
This commit is contained in:
Kovid Goyal 2009-12-16 12:23:39 -07:00
parent abedc5be42
commit c70adff6bf
1 changed files with 17 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
resources/recipes/lrb.recipe
View File

@ -1,4 +1,3 @@
#!/usr/bin/env python
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
@ -12,30 +11,29 @@ class LondonReviewOfBooks(BasicNewsRecipe):
title = u'London Review of Books' title = u'London Review of Books'
__author__ = u'Darko Miletic' __author__ = u'Darko Miletic'
description = u'Literary review publishing essay-length book reviews and topical articles on politics, literature, history, philosophy, science and the arts by leading writers and thinkers' description = u'Literary review publishing essay-length book reviews and topical articles on politics, literature, history, philosophy, science and the arts by leading writers and thinkers'
category = 'news, literature, England'
publisher = 'London Review of Books'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
language = 'en_GB' language = 'en_GB'
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
encoding = 'cp1252' encoding = 'utf-8'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [dict(name='div' , attrs={'id' :'main'})]
remove_tags = [ remove_tags = [
dict(name='div' , attrs={'id' :'otherarticles'}) dict(name='div' , attrs={'class':['pagetools','issue-nav-controls','nocss']})
,dict(name='div' , attrs={'class':'pagetools' }) ,dict(name='div' , attrs={'id' :['mainmenu','precontent','otherarticles'] })
,dict(name='div' , attrs={'id' :'mainmenu' }) ,dict(name='span', attrs={'class':['inlineright','article-icons']})
,dict(name='div' , attrs={'id' :'precontent' }) ,dict(name='ul' , attrs={'class':'article-controls'})
,dict(name='div' , attrs={'class':'nocss' }) ,dict(name='p' , attrs={'class':'meta-info' })
,dict(name='span', attrs={'class':'inlineright' })
] ]
feeds = [(u'London Review of Books', u'http://www.lrb.co.uk/lrbrss.xml')] feeds = [(u'London Review of Books', u'http://www.lrb.co.uk/lrbrss.xml')]
def print_version(self, url):
main, split, rest = url.rpartition('/')
return main + '/print/' + rest
def postprocess_html(self, soup, first_fetch):
for t in soup.findAll(['table', 'tr', 'td']):
t.name = 'div'
return soup