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 Pajamas Media

Browse Source
This commit is contained in:
Kovid Goyal 2012-12-24 16:10:54 +05:30
parent 4892defbec
commit 8b7eda245e
1 changed files with 26 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
recipes/pajama.recipe
View File

@ -1,27 +1,27 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class PajamasMedia(BasicNewsRecipe): class PajamasMedia(BasicNewsRecipe):
title = u'Pajamas Media' title = u'Pajamas Media'
description = u'Provides exclusive news and opinion for forty countries.' description = u'Provides exclusive news and opinion for forty countries.'
language = 'en' language = 'en'
__author__ = 'Krittika Goyal' __author__ = 'Krittika Goyal'
oldest_article = 1 #days oldest_article = 2 #days
max_articles_per_feed = 25 max_articles_per_feed = 25
recursions = 1 recursions = 1
match_regexps = [r'http://pajamasmedia.com/blog/.*/2/$'] match_regexps = [r'http://pajamasmedia.com/blog/.*/2/$']
#encoding = 'latin1' #encoding = 'latin1'
remove_stylesheets = True remove_stylesheets = True
#remove_tags_before = dict(name='h1', attrs={'class':'heading'}) auto_cleanup = True
remove_tags_after = dict(name='div', attrs={'class':'paged-nav'}) ##remove_tags_before = dict(name='h1', attrs={'class':'heading'})
remove_tags = [ #remove_tags_after = dict(name='div', attrs={'class':'paged-nav'})
dict(name='iframe'), #remove_tags = [
dict(name='div', attrs={'class':['pages']}), #dict(name='iframe'),
#dict(name='div', attrs={'id':['bookmark']}), #dict(name='div', attrs={'class':['pages']}),
#dict(name='span', attrs={'class':['related_link', 'slideshowcontrols']}), ##dict(name='div', attrs={'id':['bookmark']}),
#dict(name='ul', attrs={'class':'articleTools'}), ##dict(name='span', attrs={'class':['related_link', 'slideshowcontrols']}),
] ##dict(name='ul', attrs={'class':'articleTools'}),
#]
feeds = [ feeds = [
('pajamas Media', ('pajamas Media',
@ -29,20 +29,20 @@ class PajamasMedia(BasicNewsRecipe):
] ]
def preprocess_html(self, soup): #def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'id':'innerpage-content'}) #story = soup.find(name='div', attrs={'id':'innerpage-content'})
#td = heading.findParent(name='td') ##td = heading.findParent(name='td')
#td.extract() ##td.extract()
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>') #soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
body = soup.find(name='body') #body = soup.find(name='body')
body.insert(0, story) #body.insert(0, story)
return soup #return soup
def postprocess_html(self, soup, first): #def postprocess_html(self, soup, first):
if not first: #if not first:
h = soup.find(attrs={'class':'innerpage-header'}) #h = soup.find(attrs={'class':'innerpage-header'})
if h: h.extract() #if h: h.extract()
auth = soup.find(attrs={'class':'author'}) #auth = soup.find(attrs={'class':'author'})
if auth: auth.extract() #if auth: auth.extract()
return soup #return soup