calibre/recipes/irish_times.recipe
2021-04-15 08:49:48 +05:30

104 lines
3.9 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = "2008, Derry FitzGerald. 2009 Modified by Ray Kinsella and David O'Callaghan, 2011 Modified by Phil Burns, 2013 Tom Scholl, 2016 by leo738"
'''
irishtimes.com
'''
import re
import json
from uuid import uuid4
from mechanize import Request
try:
from urllib.parse import urlencode, urljoin
except ImportError:
from urllib import urlencode
from urlparse import urljoin
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ptempfile import PersistentTemporaryFile
class IrishTimes(BasicNewsRecipe):
title = u'The Irish Times'
__author__ = "Derry FitzGerald, Ray Kinsella, David O'Callaghan and Phil Burns, Tom Scholl"
description = 'Daily news from The Irish Times'
needs_subscription = True
language = 'en_IE'
masthead_url = 'http://www.irishtimes.com/assets/images/generic/website/logo_theirishtimes.png'
encoding = 'utf-8'
oldest_article = 1.0
max_articles_per_feed = 100
simultaneous_downloads = 5
remove_empty_feeds = True
no_stylesheets = True
temp_files = []
articles_are_obfuscated = True
feeds = [
('News', 'https://www.irishtimes.com/cmlink/the-irish-times-news-1.1319192'),
('World', 'https://www.irishtimes.com/cmlink/irishtimesworldfeed-1.1321046'),
('Politics', 'https://www.irishtimes.com/cmlink/irish-times-politics-rss-1.1315953'),
('Business', 'https://www.irishtimes.com/cmlink/the-irish-times-business-1.1319195'),
('Culture', 'https://www.irishtimes.com/cmlink/the-irish-times-culture-1.1319213'),
('Sport', 'https://www.irishtimes.com/cmlink/the-irish-times-sport-1.1319194'),
('Debate', 'https://www.irishtimes.com/cmlink/debate-1.1319211'),
('Life & Style', 'https://www.irishtimes.com/cmlink/the-irish-times-life-style-1.1319214'),
]
def get_browser(self):
# To understand the signin logic read signin javascript from submit button from
# https://www.irishtimes.com/signin
br = BasicNewsRecipe.get_browser(self)
url = 'https://www.irishtimes.com/signin'
deviceid = str(uuid4()).replace('-', '')
# Enable debug stuff?
# br.set_debug_http(True)
br.open(url).read()
rurl = 'https://www.irishtimes.com/auth-rest-api/v1/paywall/login'
rq = Request(rurl, headers={
'Accept': '*/*',
'Accept-Language': 'en-US,en;q=0.5',
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Referer': url,
'X-Requested-With': 'XMLHttpRequest',
}, data=urlencode({'username': self.username, 'password': self.password,'deviceid':deviceid, 'persistent':'on'}))
r = br.open(rq)
raw = r.read()
data = json.loads(raw)
# print(data)
if r.code != 200 or b'user_id' not in raw:
raise ValueError('Failed to log in check username/password')
# Set cookie
br.set_cookie('IT_PW_AUTH', data['varnish_id'], '.irishtimes.com')
# br.set_debug_http(False)
return br
def get_obfuscated_article(self, url):
# Insert a pic from the original url, but use content from the print url
pic = None
pics = self.index_to_soup(url)
div = pics.find('div', {'class' : re.compile('image-carousel')})
if div:
pic = div.img
if pic:
try:
pic['src'] = urljoin(url, pic['src'])
pic.extract()
except:
pic = None
content = self.index_to_soup(url + '?mode=print&ot=example.AjaxPageLayout.ot')
if pic:
content.p.insert(0, pic)
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(content.prettify().encode('utf-8'))
self.temp_files[-1].close()
return self.temp_files[-1].name