Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-11 09:13:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update London Review of Books (subscription)

Browse Source
This commit is contained in:
Kovid Goyal 2012-09-19 09:16:02 +05:30
parent fabe29c577
commit a7d24e2b64
1 changed files with 18 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
recipes/lrb_payed.recipe
View File

@ -1,15 +1,15 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
lrb.co.uk
'''
import re
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class LondonReviewOfBooksPayed(BasicNewsRecipe):
title = 'London Review of Books'
__author__ = 'Darko Miletic'
__author__ = 'Rich Shang, Darko Miletic'
description = 'Subscription content. 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, UK'
publisher = 'LRB Ltd.'
@ -41,9 +41,12 @@ class LondonReviewOfBooksPayed(BasicNewsRecipe):
articles = []
soup = self.index_to_soup(self.INDEX)
cover_item = soup.find('p',attrs={'class':'cover'})
dates = str(soup.find('span', attrs={'class':'coverdate'}))
newdates = re.sub('\<.*\>','',re.split('<br />',dates)[1])
self.timefmt = ' [%s]'%newdates
lrbtitle = self.title
if cover_item:
self.cover_url = self.INDEX + cover_item.a.img['src']
self.cover_url = re.sub('/m/','/l/',cover_item.a.img['src'])
content = self.INDEX + cover_item.a['href']
soup2 = self.index_to_soup(content)
sitem = soup2.find(attrs={'class':'article-list'})
@ -54,13 +57,20 @@ class LondonReviewOfBooksPayed(BasicNewsRecipe):
feed_link = item
if feed_link.has_key('href'):
url = self.INDEX + feed_link['href']
title = title_prefix + self.tag_to_string(feed_link)
title_link = re.split('<br />',str(feed_link))
if len (title_link) > 1:
title = title_prefix + re.sub('\<.*\>','',title_link[0]) + ' - ' + re.sub('\<.*\>','',title_link[1])
else:
title = title_prefix + self.tag_to_string(feed_link)
desc = item.findNext('li')
if desc is not None and desc.find('cite') is not None and desc.find('ul') is None:
description=self.tag_to_string(desc)
date = strftime(self.timefmt)
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':description
'title' :title
,'date' :date
,'url' :url
,'description':description
})
return [(lrbtitle, articles)]