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 #5429 (The Jerusalem Post feed doesn't work)

Browse Source
This commit is contained in:
Kovid Goyal 2010-05-02 10:22:08 -06:00
parent dc17c13cb2
commit ee411e3187
1 changed files with 20 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
resources/recipes/jpost.recipe
View File

@ -1,3 +1,4 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class JerusalemPost(BasicNewsRecipe): class JerusalemPost(BasicNewsRecipe):
@ -10,8 +11,6 @@ class JerusalemPost(BasicNewsRecipe):
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal'
max_articles_per_feed = 10 max_articles_per_feed = 10
no_stylesheets = True no_stylesheets = True
remove_tags_before = {'class':'jp-grid-content'}
remove_tags_after = {'id':'body_val'}
feeds = [ ('Front Page', 'http://www.jpost.com/servlet/Satellite?pagename=JPost/Page/RSS&cid=1123495333346'), feeds = [ ('Front Page', 'http://www.jpost.com/servlet/Satellite?pagename=JPost/Page/RSS&cid=1123495333346'),
('Israel News', 'http://www.jpost.com/servlet/Satellite?pagename=JPost/Page/RSS&cid=1178443463156'), ('Israel News', 'http://www.jpost.com/servlet/Satellite?pagename=JPost/Page/RSS&cid=1178443463156'),
@ -20,9 +19,24 @@ class JerusalemPost(BasicNewsRecipe):
('Editorials', 'http://www.jpost.com/servlet/Satellite?pagename=JPost/Page/RSS&cid=1123495333211'), ('Editorials', 'http://www.jpost.com/servlet/Satellite?pagename=JPost/Page/RSS&cid=1123495333211'),
] ]
remove_tags = [
dict(id=lambda x: x and 'ads.' in x),
dict(attrs={'class':['printinfo', 'tt1']}),
dict(onclick='DoPrint()'),
dict(name='input'),
]
conversion_options = {'linearize_tables':True}
def preprocess_html(self, soup): def preprocess_html(self, soup):
for x in soup.findAll(name=['form', 'input']): for tag in soup.findAll('form'):
x.name = 'div' tag.name = 'div'
for x in soup.findAll('body', style=True):
del x['style']
return soup return soup
def print_version(self, url):
m = re.search(r'(ID|id)=(\d+)', url)
if m is not None:
id_ = m.group(2)
return 'http://www.jpost.com/LandedPages/PrintArticle.aspx?id=%s'%id_
return url