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

...

Browse Source
This commit is contained in:
Kovid Goyal 2014-01-15 08:11:31 +05:30
parent 3743fb1f2c
commit 71b70ea9f1
1 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
recipes/faznet.recipe
View File

@ -8,7 +8,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class FazNet(BasicNewsRecipe): class FazNet(BasicNewsRecipe):
title = 'FAZ.NET' title = 'FAZ.NET'
__author__ = 'Kovid Goyal, Darko Miletic, Armin Geller' # AGe upd. V4 2014-01-10 __author__ = 'Kovid Goyal, Darko Miletic, Armin Geller' # AGe upd. V4 2014-01-14
description = 'Frankfurter Allgemeine Zeitung' description = 'Frankfurter Allgemeine Zeitung'
publisher = 'Frankfurter Allgemeine Zeitung GmbH' publisher = 'Frankfurter Allgemeine Zeitung GmbH'
category = 'news, politics, Germany' category = 'news, politics, Germany'
@ -47,7 +47,7 @@ class FazNet(BasicNewsRecipe):
# AGe 2014-01-10 New for multipages # AGe 2014-01-10 New for multipages
INDEX = '' INDEX = ''
def append_page(self, soup, appendtag, position): def append_page(self, soup, appendtag, position): # AGe upd 2014-01-14
pager = soup.find('a',attrs={'title':'Nächste Seite'}) pager = soup.find('a',attrs={'title':'Nächste Seite'})
if pager: if pager:
nexturl = self.INDEX + pager['href'] nexturl = self.INDEX + pager['href']
@ -57,16 +57,17 @@ class FazNet(BasicNewsRecipe):
texttag.find('div', attrs={'class':'ArtikelAbbinder'}).extract() texttag.find('div', attrs={'class':'ArtikelAbbinder'}).extract()
texttag.find('div', attrs={'class':'ArtikelKommentieren Artikelfuss GETS;tk;boxen.top-lesermeinungen;tp;content'}).extract() texttag.find('div', attrs={'class':'ArtikelKommentieren Artikelfuss GETS;tk;boxen.top-lesermeinungen;tp;content'}).extract()
texttag.find('div', attrs={'class':'Anzeige GoogleAdsBuehne'}).extract() texttag.find('div', attrs={'class':'Anzeige GoogleAdsBuehne'}).extract()
texttag.find('div', attrs={'id':'ArticlePagerBottom'}).extract()
newpos = len(texttag.contents) newpos = len(texttag.contents)
self.append_page(soup2,texttag,newpos) self.append_page(soup2,texttag,newpos)
texttag.extract() texttag.extract()
pager.extract() pager.extract()
appendtag.insert(position,texttag) appendtag.insert(position,texttag)
def preprocess_html(self, soup): def preprocess_html(self, soup): # AGe upd 2014-01-14
self.append_page(soup, soup.body, 3) self.append_page(soup, soup.body, 3)
pager = soup.find('div',attrs={'id':'ArticlePagerBottom'})
if pager:
pager.extract()
return self.adeify_images(soup) return self.adeify_images(soup)
def postprocess_html(self, soup, first_fetch): # AGe add 2014-01-14
for div in soup.findAll(id='ArticlePagerBottom'):
div.extract()
return soup