Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Forbes

Browse Source
This commit is contained in:
Kovid Goyal 2020-03-15 18:57:40 +05:30
parent a15acae96d
commit 7933c43e7a
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 23 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
recipes/forbes.recipe
View File

@ -1,7 +1,4 @@
from __future__ import absolute_import, division, print_function, unicode_literals
import html5lib
import json
import re
from calibre.web.feeds.news import BasicNewsRecipe
@ -33,47 +30,37 @@ class Forbes(BasicNewsRecipe):
}
'''
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'),
(u'Latest', u'https://www.forbes.com/news/index.xml'),
(u'Most Popular', u'https://www.forbes.com/feeds/popstories.xml'),
(u'Technology', u'https://www.forbes.com/technology/index.xml'),
(u'Business', u'https://www.forbes.com/business/index.xml'),
(u'Sports Money', u'https://www.forbes.com/sportsmoney/index.xml'),
(u'Leadership', u'https://www.forbes.com/leadership/index.xml'),
]
keep_only_tags = [
classes('article-headline-container hero-image-block article-body bottom-contrib-block')
]
remove_tags = [
classes('article-sharing'),
dict(name='button'),
]
def preprocess_html(self, soup):
h = soup.find(**classes('hero-image-block'))
if h is not None:
h1 = soup.find(**classes('article-headline-container'))
h.extract()
h1.append(h)
return soup
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 '</div>'
return '<div class="fb-captioned-img">'
body = re.sub(r'\[/?caption[^\]]*\]', cap, body)
return '''<html><head><title>{0}</title></head><body><h1>{0}</h1><div>{1}</div></body></html>'''.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/'}])]