calibre/recipes/telegraph_uk.recipe
2019-12-15 18:56:36 +05:30

122 lines
4.5 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
telegraph.co.uk
'''
from calibre.web.feeds.news import BasicNewsRecipe
import json
def classes(classes):
q = frozenset(classes.split(' '))
return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
)
def absolutize(url):
if url.startswith('/'):
url = 'http://www.telegraph.co.uk' + url
return url
class TelegraphUK(BasicNewsRecipe):
title = 'The Telegraph (UK)'
__author__ = 'A10KiloHam, based on work by Darko Miletic and Sujata Raman'
description = 'News from United Kingdom'
oldest_article = 2
category = 'news, politics, UK'
publisher = 'Telegraph Media Group ltd.'
max_articles_per_feed = 100
no_stylesheets = True
language = 'en_GB'
encoding = 'utf-8'
needs_subscription = True
ignore_duplicate_articles = {'title', 'url'}
remove_empty_feeds = True
use_embedded_content = False
INDEX = 'https://www.telegraph.co.uk/'
LOGIN = 'https://secure.telegraph.co.uk/customer/secure/login/?redirectTo=https%3A%2F%2Fwww.telegraph.co.uk%2F'
PREFIX = u'https://www.telegraph.co.uk'
feeds = [(u'News', u'http://www.telegraph.co.uk/news/rss.xml'),
(u'Politics', u'https://www.telegraph.co.uk/politics/rss.xml'),
(u'Business', u'http://www.telegraph.co.uk/business/rss.xml'),
(u'Money', u'http://www.telegraph.co.uk/money/rss.xml'),
(u'Technology', u'http://www.telegraph.co.uk/technology/rss.xml'),
(u'Science', u'http://www.telegraph.co.uk/science/rss.xml'),
(u'Opinion', u'http://www.telegraph.co.uk/opinion/rss.xml'),
(u'Travel', u'http://www.telegraph.co.uk/travel/rss.xml'),
(u'Culture', u'http://www.telegraph.co.uk/culture/rss.xml'),
(u'Lifestyle', u'http://www.telegraph.co.uk/lifestyle/rss.xml'),
(u'Money', u'http://www.telegraph.co.uk/opinion/rss.xml'),
(u'Opinion', u'http://www.telegraph.co.uk/money/rss.xml'),
(u'Fashion', u'http://www.telegraph.co.uk/fashion/rss.xml')]
keep_only_tags = [
classes(
'lead-asset-image-container headline__heading footer-author article-author__meta'
),
dict(itemprop='articleBody'),
]
remove_tags = [
dict(name=['link', 'meta', 'style']),
classes('videoPlayer'),
]
remove_attributes = 'width height'.split()
def get_cover_url(self):
from datetime import date
cover = 'http://img.kiosko.net/' + str(
date.today().year
) + '/' + date.today().strftime('%m') + '/' + date.today(
).strftime('%d') + '/uk/daily_telegraph.750.jpg'
br = BasicNewsRecipe.get_browser(self)
try:
br.open(cover)
except:
index = 'http://en.kiosko.net/uk/np/daily_telegraph.html'
soup = self.index_to_soup(index)
for image in soup.findAll('img', src=True):
if image['src'].endswith('750.jpg'):
return image['src']
self.log("\nCover unavailable")
cover = None
return cover
def get_browser(self, *a, **kw):
USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0'
br = BasicNewsRecipe.get_browser(self, user_agent=USER_AGENT)
self.log('Forming login request...')
if self.username is not None and self.password is not None:
self.log('Starting login process...')
br.open(self.LOGIN)
br.select_form(nr=0)
br['email'] = self.username
br['password'] = self.password
self.log('Sending login request...')
br.submit()
return br
def get_article_url(self, article):
url = article.get('link', None)
if 'picture-galleries' in url or 'pictures' in url or 'picturegalleries' in url:
url = None
return url
def preprocess_html(self, soup):
for img in soup.findAll(attrs={'data-frz-src-array': True}):
img['style'] = ''
img.name = 'img'
d = json.loads(img['data-frz-src-array'].replace("'", '"'))
for item in d:
if int(item.get('width', 0)) > 700:
img['src'] = absolutize(item['src'])
break
for img in soup.findAll('div', attrs={'data-js': 'LazyImage'}):
img['style'] = ''
img.name = 'img'
img['src'] = img['data-srcset'].split()[0]
return soup