calibre/recipes/barrons.recipe
2021-04-25 13:05:42 +05:30

120 lines
4.4 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2019, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
import json
from mechanize import Request
from calibre import random_user_agent
from calibre.web.feeds.news import BasicNewsRecipe
from base64 import standard_b64encode
try:
import urllib.parse as urlparse
except ImportError:
import urlparse
try:
from urllib.parse import quote
except ImportError:
from urllib import quote
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
MAGAZINE_INDEX = 'https://www.barrons.com/magazine'
class BarronsMagazine(BasicNewsRecipe):
title = 'Barron\'s Magazine'
__author__ = 'Kovid Goyal'
description = 'Financial news from the publisher of the WSJ'
language = 'en'
needs_subscription = True
no_stylesheets = True
keep_only_tags = [
classes('article__headline article__body'),
]
def get_browser(self, *a, **kw):
# To understand the login logic read app-min.js from
# https://sso.accounts.dowjones.com/login
kw['user_agent'] = random_user_agent(allow_ie=False)
br = super().get_browser(*a, **kw)
if not self.username or not self.password:
self.barrons_itp_page = br.open(MAGAZINE_INDEX).read()
return br
itp = quote(MAGAZINE_INDEX, safe='')
start_url = 'https://accounts.barrons.com/login?target=' + itp
self.log('Starting login process...')
res = br.open(start_url)
sso_url = res.geturl()
query = urlparse.parse_qs(urlparse.urlparse(sso_url).query)
query = {k:v[0] for k, v in query.items()}
request_query = {
'username': self.username,
'password': self.password,
'client_id': query['client'],
'sso': 'true',
'tenant': 'sso',
'_intstate': 'deprecated',
'connection': 'DJldap',
}
for k in 'scope connection nonce state ui_locales ns protocol redirect_uri'.split():
if k in query:
request_query[k] = query[k]
login_url = 'https://sso.accounts.dowjones.com/usernamepassword/login'
# you can get the version below from lib-min.js
# search for: str: "x.x.x"
# This might need to be updated in the future
auth0_client = json.dumps({"name": "auth0.js", "version": "7.0.3"})
if not isinstance(auth0_client, bytes):
auth0_client = auth0_client.encode('utf-8')
auth0_client = standard_b64encode(auth0_client)
if isinstance(auth0_client, bytes):
auth0_client = auth0_client.decode('ascii')
rq = Request(login_url, headers={
'Accept': 'text/html',
'Accept-Language': 'en-US,en;q=0.8',
'Auth0-Client': auth0_client.rstrip('='),
'X-HTTP-Method-Override': 'POST',
'X-Requested-With': 'XMLHttpRequest',
'X-Remote-User': self.username
}, data=request_query)
self.log('Sending login request...')
try:
res = br.open(rq)
except Exception as err:
if hasattr(err, 'read'):
raise Exception('Login request failed with error: {} and body: {}'.format(err, err.read().decode('utf-8', 'replace')))
raise
if res.code != 200:
raise ValueError('Failed to login, check your username and password')
br.select_form(nr=0)
self.log('Performing login callback...')
res = br.submit()
self.barrons_itp_page = raw = res.read()
if b'/logout' not in raw:
raise ValueError(
'Failed to login (callback URL failed), check username and password')
return br
def parse_index(self):
soup = self.index_to_soup(self.barrons_itp_page)
articles = []
for art in soup.findAll('article'):
h = art.find(['h2', 'h3'])
a = h.find('a')
title = self.tag_to_string(a)
url = a['href']
desc = ''
p = art.find('p', attrs={'class': lambda x: x and ('_summary_' in x or '_byline_' in x)})
if p:
desc += self.tag_to_string(p)
articles.append({'title': title, 'url': url, 'description': desc})
return [('Articles', articles)]