This is an update to the built-in recipe. I made some aesthetic changes.
Code:
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
lrb.co.uk
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class LondonReviewOfBooksPayed(BasicNewsRecipe):
title = 'London Review of Books'
__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.'
max_articles_per_feed = 100
language = 'en_GB'
no_stylesheets = True
delay = 1
use_embedded_content = False
encoding = 'utf-8'
INDEX = 'http://www.lrb.co.uk'
LOGIN = INDEX + '/login'
masthead_url = INDEX + '/assets/images/lrb_logo_big.gif'
needs_subscription = True
publication_type = 'magazine'
extra_css = ' body{font-family: Georgia,Palatino,"Palatino Linotype",serif} '
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
br.open(self.LOGIN)
br.select_form(nr=1)
br['username'] = self.username
br['password'] = self.password
br.submit()
return br
def parse_index(self):
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 = 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'})
lrbtitle = soup2.head.title.string
for item in sitem.findAll('a',attrs={'class':'title'}):
description = u''
title_prefix = u''
feed_link = item
if feed_link.has_key('href'):
url = self.INDEX + feed_link['href']
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
})
return [(lrbtitle, articles)]
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
keep_only_tags = [dict(name='div' , attrs={'class':['article-body indent','letters']})]
remove_attributes = ['width','height']