from __future__ import (unicode_literals, division, absolute_import, print_function) import html5lib import json import re from calibre.web.feeds.news import BasicNewsRecipe def classes(classes): q = frozenset(classes.split(' ')) return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) class Forbes(BasicNewsRecipe): title = u'Forbes' description = 'Business and Financial News' __author__ = 'Kovid Goyal' oldest_article = 30 max_articles_per_feed = 20 language = 'en' encoding = 'utf-8' no_stylesheets = True ignore_duplicate_articles = {'title', 'url'} remove_empty_feeds = True extra_css = ''' div.fb-captioned-img { font-size: smaller; margin-top: 1em; margin-bottom: 1em; } div.fb-captioned-img img { display:block; margin-left: auto; margin-right: auto; } ''' feeds = [ (u'Latest', u'http://www.forbes.com/news/index.xml'), (u'Most Popular', u'http://www.forbes.com/feeds/popstories.xml'), (u'Technology', u'http://www.forbes.com/technology/index.xml'), (u'Business', u'http://www.forbes.com/business/index.xml'), (u'Sports Money', u'http://www.forbes.com/sportsmoney/index.xml'), (u'Leadership', u'http://www.forbes.com/leadership/index.xml'), ] def get_browser(self): br = BasicNewsRecipe.get_browser(self) br.set_cookie('dailyWelcomeCookie', 'true', '.forbes.com') br.set_cookie('welcomeAd', 'true', '.forbes.com') return br def preprocess_raw_html(self, raw, url): root = html5lib.parse( raw, namespaceHTMLElements=False, treebuilder='lxml') for script in root.xpath('//script'): if script.text and script.text.startswith('try {'): idx = script.text.find('fbs_settings.content = {') if idx > -1: text = script.text.partition('=')[2].lstrip() ridx = text.rfind('} catch(err)') text = text[:ridx].rstrip().rstrip(';') data = json.loads(text) # from pprint import pformat # print(pformat(data), file=open('/t/data.py', 'w')) break else: raise ValueError('Failed to find serialized JSON content') title = data['brandVoiceTitle'] body = data['body'] def cap(m): val = m.group() if val.startswith('[/'): return '' return '

' body = re.sub(r'\[/?caption[^\]]*\]', cap, body) return '''{0}

{0}

{1}

'''.format(title, body) # def parse_index(self): # return [('Articles', [{'title':'Test', 'url': # 'http://www.forbes.com/sites/hamdiraini/2016/04/25/bazin-seeks-startups-to-accelerate-accorhotels-transformation/'}])]