mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
88 lines
3.2 KiB
Python
88 lines
3.2 KiB
Python
#!/usr/bin/env python2
|
|
# vim:fileencoding=utf-8
|
|
# License: GPLv3 Copyright: 2016, Kovid Goyal <kovid at kovidgoyal.net>
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from css_selectors import Select
|
|
from mechanize import Request
|
|
import json
|
|
try:
|
|
from urllib.parse import urlencode
|
|
except ImportError:
|
|
from urllib import urlencode
|
|
|
|
|
|
class HBR(BasicNewsRecipe):
|
|
|
|
title = 'Harvard Business Review'
|
|
description = 'To subscribe go to http://hbr.harvardbusiness.org'
|
|
needs_subscription = True
|
|
__author__ = 'Kovid Goyal'
|
|
timefmt = ' [%B %Y]'
|
|
language = 'en'
|
|
no_stylesheets = True
|
|
|
|
keep_only_tags = [
|
|
dict(attrs={'class': ['article-hed', 'byline']}),
|
|
dict(attrs={'class': lambda x: x and 'article' in x.split()}),
|
|
]
|
|
remove_tags = [
|
|
dict(name='personalization-placement'),
|
|
]
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
# br.set_debug_http(True)
|
|
br.open('https://hbr.org/sign-in')
|
|
rq = Request('https://hbr.org/authenticate', headers={
|
|
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
|
|
'Referer': 'https://hbr.org/sign-in',
|
|
'Origin': 'https://hbr.org',
|
|
'X-Requested-With': 'XMLHttpRequest',
|
|
'Accept': 'application/json, text/javascript, */*; q=0.01',
|
|
}, data=urlencode({'username': self.username, 'password': self.password}))
|
|
r = br.open(rq)
|
|
raw = r.read()
|
|
data = json.loads(raw)
|
|
if data['code'] != 200 or data["message"] != "Authentication Successful.":
|
|
raise ValueError('Failed to log in check username/password')
|
|
return br
|
|
|
|
def hbr_parse_toc(self, url):
|
|
root = self.index_to_soup(url, as_tree=True)
|
|
select = Select(root)
|
|
section = 'Unknown'
|
|
articles = []
|
|
feeds = []
|
|
toc = next(
|
|
select('stream-content[data-stream-name="table-of-contents"] ul'))
|
|
for x in toc.xpath('descendant::*[local-name()="h4" or local-name()="stream-item"]'):
|
|
if 'h4' in x.tag:
|
|
if articles:
|
|
feeds.append((section, articles))
|
|
section = self.tag_to_string(x)
|
|
articles = []
|
|
self.log('Found section:', section)
|
|
else:
|
|
title, url = x.get('data-title'), x.get('data-url')
|
|
desc = ''.join(c.tail or '' for c in x).strip()
|
|
authors = x.get('data-authors')
|
|
if authors:
|
|
desc = 'by ' + authors + ': ' + desc
|
|
self.log('\tFound article:', title, url, desc)
|
|
articles.append(
|
|
{'title': title, 'url': 'https://hbr.org' + url, 'description': desc})
|
|
if articles:
|
|
feeds.append((section, articles))
|
|
return feeds
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup('http://hbr.org/magazine')
|
|
fig = soup.find('figure', attrs={
|
|
'class': lambda x: x and 'current-issue' in x.split()})
|
|
url = 'https://hbr.org' + fig.find('a', href=True)['href']
|
|
img = fig.find('img')
|
|
self.cover_url = 'https://hbr.org' + img['src']
|
|
self.timefmt = img['alt']
|
|
return self.hbr_parse_toc(url)
|