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 Popular Science

Browse Source
This commit is contained in:
Kovid Goyal 2015-05-27 12:43:37 +05:30
parent f01a490730
commit 9f0578b4bd
1 changed files with 9 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
recipes/popscience.recipe
View File

@ -1,21 +1,16 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
import re
class AdvancedUserRecipe1282101454(BasicNewsRecipe): class AdvancedUserRecipe1282101454(BasicNewsRecipe):
title = 'Popular Science' title = 'Popular Science'
language = 'en' language = 'en'
__author__ = 'TonytheBookworm' __author__ = 'Kovid Goyal'
description = 'Popular Science' description = 'Popular Science'
publisher = 'Popular Science' publisher = 'Popular Science'
category = 'gadgets,science'
oldest_article = 7 # change this if you want more current articles. I like to go a week in oldest_article = 7 # change this if you want more current articles. I like to go a week in
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
use_embedded_content = True use_embedded_content = False
masthead_url = 'http://www.raytheon.com/newsroom/rtnwcm/groups/Public/documents/masthead/rtn08_popscidec_masthead.jpg'
feeds = [ feeds = [
@ -26,31 +21,11 @@ class AdvancedUserRecipe1282101454(BasicNewsRecipe):
('DIY', 'http://www.popsci.com/full-feed/diy'), ('DIY', 'http://www.popsci.com/full-feed/diy'),
] ]
keep_only_tags = [
dict(attrs={'class':lambda x: x and {'pane-node-header', 'pane-node-body'} & set(x.split())}),
]
def preprocess_html(self, soup):
#The following will get read of the Gallery: links when found for img in soup.findAll('img', attrs={'data-medsrc':True}):
img['src'] = img['data-medsrc']
def preprocess_html(self, soup) :
weblinks = soup.findAll(['head','h2'])
if weblinks is not None:
for link in weblinks:
if re.search('(Gallery)(:)',str(link)):
link.parent.extract()
return soup return soup
#-----------------------------------------------------------------