Improve bild.de

This commit is contained in:
Kovid Goyal 2011-06-03 09:03:56 -06:00
parent 85bc21b4f7
commit 2cc1ed2ac9

View File

@ -1,10 +1,11 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe): class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'Bild.de' title = u'Bild.de'
__author__ = 'schuster' __author__ = 'schuster'
oldest_article = 1 oldest_article = 1
max_articles_per_feed = 50 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
language = 'de' language = 'de'
@ -12,11 +13,25 @@ class AdvancedUserRecipe1303841067(BasicNewsRecipe):
# get cover from myspace # get cover from myspace
cover_url = 'http://a3.l3-images.myspacecdn.com/images02/56/0232f842170b4d349779f8379c27e073/l.jpg' cover_url = 'http://a3.l3-images.myspacecdn.com/images02/56/0232f842170b4d349779f8379c27e073/l.jpg'
masthead_url = 'http://a3.l3-images.myspacecdn.com/images02/56/0232f842170b4d349779f8379c27e073/l.jpg'
# set what to fetch on the site # set what to fetch on the site
remove_tags_before = dict(name = 'h2', attrs={'id':'cover'}) remove_tags_before = dict(name = 'h2', attrs={'id':'cover'})
remove_tags_after = dict(name ='div', attrs={'class':'back'}) remove_tags_after = dict(name ='div', attrs={'class':'back'})
# remove things on the site that we don't want
remove_tags = [dict(name='div', attrs={'class':'credit'}),
dict(name='div', attrs={'class':'index'}),
dict(name='div', attrs={'id':'zstart31'}),
dict(name='div', attrs={'class':'hentry'}),
dict(name='div', attrs={'class':'back'}),
dict(name='div', attrs={'class':'pagination'}),
dict(name='div', attrs={'class':'header'}),
dict(name='div', attrs={'class':'element floatL'}),
dict(name='div', attrs={'class':'stWrap'})
]
# thanx to kiklop74 for code (see sticky thread -> Recipes - Re-usable code) # thanx to kiklop74 for code (see sticky thread -> Recipes - Re-usable code)
# this one removes a lot of direct-link's # this one removes a lot of direct-link's
def preprocess_html(self, soup): def preprocess_html(self, soup):
@ -42,5 +57,18 @@ class AdvancedUserRecipe1303841067(BasicNewsRecipe):
(u'Unterhaltung', u'http://rss.bild.de/bild-unterhaltung.xml'), (u'Unterhaltung', u'http://rss.bild.de/bild-unterhaltung.xml'),
(u'Sport', u'http://rss.bild.de/bild-sport.xml'), (u'Sport', u'http://rss.bild.de/bild-sport.xml'),
(u'Lifestyle', u'http://rss.bild.de/bild-lifestyle.xml'), (u'Lifestyle', u'http://rss.bild.de/bild-lifestyle.xml'),
(u'Ratgeber', u'http://rss.bild.de/bild-ratgeber.xml') (u'Ratgeber', u'http://rss.bild.de/bild-ratgeber.xml'),
(u'Reg. - Berlin', u'http://rss.bild.de/bild-berlin.xml'),
(u'Reg. - Bremen', u'http://rss.bild.de/bild-bremen.xml'),
(u'Reg. - Dresden', u'http://rss.bild.de/bild-dresden.xml'),
(u'Reg. - Düsseldorf', u'http://rss.bild.de/bild-duesseldorf.xml'),
(u'Reg. - Frankfurt-Main', u'http://rss.bild.de/bild-frankfurt-main.xml'),
(u'Reg. - Hamburg', u'http://rss.bild.de/bild-hamburg.xml'),
(u'Reg. - Hannover', u'http://rss.bild.de/bild-hannover.xml'),
(u'Reg. - Köln', u'http://rss.bild.de/bild-koeln.xml'),
(u'Reg. - Leipzig', u'http://rss.bild.de/bild-leipzig.xml'),
(u'Reg. - München', u'http://rss.bild.de/bild-muenchen.xml'),
(u'Reg. - Ruhrgebiet', u'http://rss.bild.de/bild-ruhrgebiet.xml'),
(u'Reg. - Stuttgart', u'http://rss.bild.de/bild-stuttgart.xml')
] ]