calibre/resources/recipes/hbr_blogs.recipe

198 lines
8.0 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
import re
# Needed for BLOGs
from calibre.web.feeds import Feed
class HBR(BasicNewsRecipe):
title = 'Harvard Business Review Blogs'
description = 'To subscribe go to http://hbr.harvardbusiness.org'
needs_subscription = True
__author__ = 'Kovid Goyal and Sujata Raman, enhanced by BrianG'
language = 'en'
no_stylesheets = True
LOGIN_URL = 'http://hbr.org/login?request_url=/'
INDEX = 'http://hbr.org/current'
#
# Blog Stuff
#
INCLUDE_BLOGS = True
INCLUDE_ARTICLES = False
# option-specific settings.
if INCLUDE_BLOGS == True:
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
else:
timefmt = ' [%B %Y]'
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']),
dict(name='iframe')]
extra_css = '''
a {font-family:Georgia,"Times New Roman",Times,serif; font-style:italic; color:#000000; }
.article{font-family:Georgia,"Times New Roman",Times,serif; font-size: xx-small;}
h2{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:large; }
h4{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:small; }
#articleBody{font-family:Georgia,"Times New Roman",Times,serif; font-style:italic; color:#000000;font-size:x-small;}
#summaryText{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:x-small;}
'''
#-------------------------------------------------------------------------------------------------
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open(self.LOGIN_URL)
br.select_form(name='signInForm')
br['signInForm:username'] = self.username
br['signInForm: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?')
self.logout_url = None
link = br.find_link(text='Sign out')
if link:
self.logout_url = link.absolute_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 hbr_get_toc(self):
soup = self.index_to_soup(self.INDEX)
url = soup.find('a', text=lambda t:'Full Table of Contents' in t).parent.get('href')
return self.index_to_soup('http://hbr.org'+url)
#-------------------------------------------------------------------------------------------------
def hbr_parse_section(self, container, feeds):
current_section = None
current_articles = []
for x in container.findAll(name=['li', 'h3', 'h4']):
if x.name in ['h3', 'h4'] and not x.findAll(True):
if current_section and current_articles:
feeds.append((current_section, current_articles))
current_section = self.tag_to_string(x)
current_articles = []
self.log('\tFound section:', current_section)
if x.name == 'li':
a = x.find('a', href=True)
if a is not None:
title = self.tag_to_string(a)
url = a.get('href')
if '/ar/' not in url:
continue
if url.startswith('/'):
url = 'http://hbr.org'+url
url = self.map_url(url)
p = x.find('p')
desc = ''
if p is not None:
desc = self.tag_to_string(p)
if not title or not url:
continue
self.log('\t\tFound article:', title)
self.log('\t\t\t', url)
self.log('\t\t\t', desc)
current_articles.append({'title':title, 'url':url,
'description':desc, 'date':''})
if current_section and current_articles:
feeds.append((current_section, current_articles))
#-------------------------------------------------------------------------------------------------
def hbr_parse_toc(self, soup):
feeds = []
features = soup.find(id='issueFeaturesContent')
self.hbr_parse_section(features, feeds)
departments = soup.find(id='issueDepartments')
self.hbr_parse_section(departments, feeds)
return feeds
#-------------------------------------------------------------------------------------------------
def feed_to_index_append(self, feedObject, masterFeed):
# Loop thru the feed object and build the correct type of article list
for feed in feedObject:
# build the correct structure from the feed object
newArticles = []
for article in feed.articles:
newArt = {
'title' : article.title,
'url' : article.url,
'date' : article.date,
'description' : article.text_summary
}
newArticles.append(newArt)
# Append the earliest/latest dates of the feed to the feed title
startDate, endDate = self.get_feed_dates(feed, '%d-%b')
newFeedTitle = feed.title + ' (' + startDate + ' thru ' + endDate + ')'
# append the newly-built list object to the index object passed in
# as masterFeed.
masterFeed.append( (newFeedTitle,newArticles) )
#-------------------------------------------------------------------------------------------------
def get_feed_dates(self, feedObject, dateMask):
startDate = feedObject.articles[len(feedObject.articles)-1].localtime.strftime(dateMask)
endDate = feedObject.articles[0].localtime.strftime(dateMask)
return startDate, endDate
#-------------------------------------------------------------------------------------------------
def hbr_parse_blogs(self, feeds):
# Do the "official" parse_feeds first
rssFeeds = Feed()
# Use the PARSE_FEEDS method to get a Feeds object of the articles
rssFeeds = BasicNewsRecipe.parse_feeds(self)
# Create a new feed of the right configuration and append to existing afeeds
self.feed_to_index_append(rssFeeds[:], feeds)
#-------------------------------------------------------------------------------------------------
def parse_index(self):
if self.INCLUDE_ARTICLES == True:
soup = self.hbr_get_toc()
feeds = self.hbr_parse_toc(soup)
else:
feeds = []
# blog stuff
if self.INCLUDE_BLOGS == True:
self.hbr_parse_blogs(feeds)
return feeds
#-------------------------------------------------------------------------------------------------
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