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 Business Week Magazine

Browse Source
This commit is contained in:
Kovid Goyal 2014-01-19 08:23:15 +05:30
parent 766fb9c400
commit 4c9c7aad6f
1 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
recipes/bwmagazine2.recipe
View File

@ -5,31 +5,34 @@ from collections import OrderedDict
class BusinessWeekMagazine(BasicNewsRecipe):
title = 'Business Week Magazine'
__author__ = 'Rick Shang'
__author__ = 'Rick Shang, Armin Geller' # AGE Upd 2014-01-18
description = 'A renowned business publication. Business news, trends and profiles of successful businesspeople.'
language = 'en'
category = 'news'
encoding = 'UTF-8'
keep_only_tags = [
dict(name='div', attrs={'id':['article_body_container','story_body']}),
dict(name='div', attrs={'id':['content']}), # AGE 2014-01-18
]
remove_tags = [dict(name='ui'),dict(name='li'),dict(name='div', attrs={'id':['share-email']})]
remove_tags = [dict(name='hr'),
dict(name='a', attrs={'class':'sub_sales'}),
dict(name='div', attrs={'class':'fieldset'}),
dict(name='div', attrs={'id':'taboola_wrapper'})] # AGE 2014-01-18
no_javascript = True
no_stylesheets = True
cover_url = 'http://images.businessweek.com/mz/covers/current_120x160.jpg'
def parse_index(self):
#Go to the issue
# Go to the issue
soup = self.index_to_soup('http://www.businessweek.com/magazine/news/articles/business_news.htm')
#Find date
# Find date
mag=soup.find('h2',text='Magazine')
dates=self.tag_to_string(mag.findNext('h3'))
self.timefmt = u' [%s]'%dates
#Go to the main body
# Go to the main body
div0 = soup.find('div', attrs={'class':'column left'})
section_title = ''
feeds = OrderedDict()