mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
82 lines
2.9 KiB
Plaintext
82 lines
2.9 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
import re
|
|
|
|
class HBR(BasicNewsRecipe):
|
|
|
|
title = 'Harvard Business Review Blogs'
|
|
description = 'To subscribe go to http://hbr.harvardbusiness.org'
|
|
__author__ = 'Kovid Goyal'
|
|
language = 'en'
|
|
no_stylesheets = True
|
|
#recipe_disabled = ('hbr.org has started requiring the use of javascript'
|
|
# ' to log into their website. This is unsupported in calibre, so'
|
|
# ' this recipe has been disabled. If you would like to see '
|
|
# ' HBR supported in calibre, contact hbr.org and ask them'
|
|
# ' to provide a javascript free login method.')
|
|
needs_subscription = False
|
|
|
|
LOGIN_URL = 'http://hbr.org/login?request_url=/'
|
|
LOGOUT_URL = 'http://hbr.org/logout?request_url=/'
|
|
|
|
INDEX = 'http://hbr.org/current'
|
|
|
|
remove_tags_after = dict(id='articleBody')
|
|
remove_tags_before = dict(id='pageFeature')
|
|
feeds = [('Blog','http://feeds.harvardbusiness.org/harvardbusiness')]
|
|
oldest_article = 30
|
|
max_articles_per_feed = 100
|
|
use_embedded_content = False
|
|
|
|
keep_only_tags = [ dict(name='div', id='pageContainer')
|
|
]
|
|
|
|
remove_tags = [dict(id=['mastheadContainer', 'magazineHeadline',
|
|
'articleToolbarTopRD', 'pageRightSubColumn', 'pageRightColumn',
|
|
'todayOnHBRListWidget', 'mostWidget', 'keepUpWithHBR',
|
|
'articleToolbarTop','articleToolbarBottom', 'articleToolbarRD',
|
|
'mailingListTout', 'partnerCenter', 'pageFooter', 'shareWidgetTop']),
|
|
dict(name=['iframe', 'style'])]
|
|
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
self.logout_url = None
|
|
return br
|
|
|
|
#'''
|
|
br.open(self.LOGIN_URL)
|
|
br.select_form(name='signin-form')
|
|
br['signin-form:username'] = self.username
|
|
br['signin-form:password'] = self.password
|
|
raw = br.submit().read()
|
|
if 'My Account' not in raw:
|
|
raise Exception('Failed to login, are you sure your username and password are correct?')
|
|
try:
|
|
link = br.find_link(text='Sign out')
|
|
if link:
|
|
self.logout_url = link.absolute_url
|
|
except:
|
|
self.logout_url = self.LOGOUT_URL
|
|
#'''
|
|
return br
|
|
|
|
#-------------------------------------------------------------------------------------------------
|
|
def cleanup(self):
|
|
if self.logout_url is not None:
|
|
self.browser.open(self.logout_url)
|
|
#-------------------------------------------------------------------------------------------------
|
|
def map_url(self, url):
|
|
if url.endswith('/ar/1'):
|
|
return url[:-1]+'pr'
|
|
|
|
def get_cover_url(self):
|
|
cover_url = None
|
|
index = 'http://hbr.org/current'
|
|
soup = self.index_to_soup(index)
|
|
link_item = soup.find('img', alt=re.compile("Current Issue"), src=True)
|
|
|
|
if link_item:
|
|
cover_url = 'http://hbr.org' + link_item['src']
|
|
|
|
return cover_url
|