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 NZZ Webpaper

Browse Source
This commit is contained in:
Kovid Goyal 2015-04-16 08:37:12 +05:30
parent 54d2effa5a
commit 530876cc47
1 changed files with 15 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
recipes/nzz_webpaper.recipe
View File

@ -1,8 +1,9 @@
import re import re
from calibre import strftime from calibre import strftime
from calibre.ebooks.BeautifulSoup import Tag
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2012-14, Bernd Leinfelder <skoll1975 at gmail.com> ' __copyright__ = '2012-15, Bernd Leinfelder <skoll1975 at gmail.com> '
''' '''
webpaper.nzz.ch webpaper.nzz.ch
@ -14,7 +15,7 @@ from calibre.web.feeds.recipes import BasicNewsRecipe
class Nzz(BasicNewsRecipe): class Nzz(BasicNewsRecipe):
title = 'NZZ Webpaper' title = 'NZZ Webpaper'
__author__ = 'Bernd Leinfelder' __author__ = 'Bernd Leinfelder'
description = 'Neue Zuercher Zeitung Webpaper - Erfordert NZZ Digital Abonnement' description = 'Neue Zuercher Zeitung Webpaper - Erfordert NZZ Digital Abonnement. v20140425'
timefmt = ' [%a, %d %b, %Y]' timefmt = ' [%a, %d %b, %Y]'
publisher = 'NZZ AG' publisher = 'NZZ AG'
needs_subscription = True needs_subscription = True
@ -52,7 +53,15 @@ class Nzz(BasicNewsRecipe):
issue = soup.find("link",rel="prefetch") issue = soup.find("link",rel="prefetch")
soup = self.index_to_soup(baseref+issue['href']) soup = self.index_to_soup(baseref+issue['href'])
for span in soup.findAll('span', attrs={'data-src-640':True}):
imgSrc=span['data-src-640']
# print "image source: "+ imgSrc
imgTag = Tag(soup,"img",[("src",imgSrc)])
span.replaceWith(imgTag)
# print soup.prettify() # print soup.prettify()
section = "" section = ""
lastsection = "" lastsection = ""
pubdate = strftime('%a, %d %b') pubdate = strftime('%a, %d %b')
@ -78,7 +87,7 @@ class Nzz(BasicNewsRecipe):
articles[section].append( articles[section].append(
dict(title=caption.string,url='file://'+filename, date=pubdate, description='', content='')) dict(title=caption.string,url='file://'+filename, date=pubdate, description='', content=''))
ans = [(key, articles[key]) for key in sections if articles.has_key(key)] ans = [(key, articles[key]) for key in sections if key in articles]
# pprint.pprint(ans) # pprint.pprint(ans)