calibre/recipes/guardian.recipe
2015-11-26 19:18:21 +05:30

78 lines
2.9 KiB
Python

#!/usr/bin/env python2
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
'''
www.guardian.co.uk
'''
from calibre.web.feeds.news import BasicNewsRecipe
from datetime import date
class Guardian(BasicNewsRecipe):
title = u'The Guardian and The Observer'
if date.today().weekday() == 6:
base_url = "http://www.guardian.co.uk/theobserver"
cover_pic = 'Observer digital edition'
masthead_url = 'http://static.guim.co.uk/sys-images/Guardian/Pix/site_furniture/2010/10/19/1287478087992/The-Observer-001.gif'
else:
base_url = "http://www.guardian.co.uk/theguardian"
cover_pic = 'Guardian digital edition'
masthead_url = 'http://static.guim.co.uk/static/f76b43f9dcfd761f0ecf7099a127b603b2922118/common/images/logos/the-guardian/titlepiece.gif'
__author__ = 'Kovid Goyal'
language = 'en_GB'
oldest_article = 7
max_articles_per_feed = 100
remove_javascript = True
encoding = 'utf-8'
remove_empty_feeds = True
no_stylesheets = True
remove_attributes = ['style']
ignore_duplicate_articles = {'title', 'url'}
timefmt = ' [%a, %d %b %Y]'
keep_only_tags = [
dict(attrs={'class': lambda x: x and 'content__main-column' in x.split()}),
]
remove_tags = [
dict(attrs={'class': lambda x:x and '--twitter' in x}),
dict(attrs={'data-component': ['share', 'social']}),
dict(attrs={'data-link-name': 'block share'}),
dict(attrs={'class': lambda x:x and 'inline-expand-image' in x}),
dict(attrs={'class': lambda x:x and 'modern-visible' in x.split()}),
]
remove_tags_after = [
dict(attrs={'class': lambda x: x and 'content__article-body' in x.split()}),
]
def preprocess_html(self, soup):
for img in soup.findAll('img', srcset=True):
img['src'] = img['srcset'].partition(' ')[0]
img['srcset'] = ''
return soup
def parse_section(self, url, title_prefix=''):
feeds = []
soup = self.index_to_soup(url)
for section in soup.findAll('section'):
title = title_prefix + self.tag_to_string(section.find(attrs={'class':'fc-container__header__title'})).strip().capitalize()
self.log('\nFound section:', title)
feeds.append((title, []))
for li in section.findAll('li'):
for a in li.findAll('a', attrs={'data-link-name':'article'}, href=True):
title = self.tag_to_string(a).strip()
url = a['href']
self.log(' ', title, url)
feeds[-1][1].append({'title':title, 'url':url})
break
return feeds
def parse_index(self):
feeds = self.parse_section(self.base_url)
feeds += self.parse_section('http://www.theguardian.com/uk/sport', 'Sport - ')
return feeds