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

Update Baltimore Sun

Browse Source
This commit is contained in:
Kovid Goyal 2012-10-16 18:19:29 +05:30
parent b7e058518d
commit 1c153d4100
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
recipes/baltimore_sun.recipe
View File

@ -11,10 +11,9 @@ class BaltimoreSun(BasicNewsRecipe):
title = 'The Baltimore Sun' title = 'The Baltimore Sun'
__author__ = 'Josh Hall' __author__ = 'Josh Hall'
description = 'Complete local news and blogs from Baltimore' description = 'Complete local news and blogs from Baltimore'
language = 'en' language = 'en'
version = 2 version = 2.1
oldest_article = 1 oldest_article = 1
max_articles_per_feed = 100 max_articles_per_feed = 100
use_embedded_content = False use_embedded_content = False
@ -22,6 +21,7 @@ class BaltimoreSun(BasicNewsRecipe):
remove_javascript = True remove_javascript = True
recursions = 1 recursions = 1
ignore_duplicate_articles = {'title'}
keep_only_tags = [dict(name='div', attrs={'class':["story","entry-asset asset hentry"]}), keep_only_tags = [dict(name='div', attrs={'class':["story","entry-asset asset hentry"]}),
dict(name='div', attrs={'id':["pagebody","story","maincontentcontainer"]}), dict(name='div', attrs={'id':["pagebody","story","maincontentcontainer"]}),
] ]
@ -201,3 +201,5 @@ class BaltimoreSun(BasicNewsRecipe):
tag.extract() tag.extract()
for tag in soup.findAll('font', dict(attrs={'id':["cr-other-headlines"]})): for tag in soup.findAll('font', dict(attrs={'id':["cr-other-headlines"]})):
tag.extract() tag.extract()
return soup