Hi,
I wrote a recipe for fr-online.de which is from the German "Frankfurter Rundschau"
Code:
import re
from calibre.web.feeds.news import BasicNewsRecipe
__license__ = 'GPL v3'
__copyright__ = '2009, Justus Bisser <justus.bisser at gmail.com>'
'''
fr-online.de
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Spiegel_ger(BasicNewsRecipe):
title = 'Frankfurter Rundschau'
__author__ = 'Justus Bisser'
description = "Dies ist die Online-Ausgabe der Frankfurter Rundschau. Um die abgerufenen individuell einzustellen bearbeiten sie die Liste im erweiterten Modus. Die Feeds findet man auf http://www.fr-online.de/verlagsservice/fr_newsreader/?em_cnt=574255"
publisher = 'Druck- und Verlagshaus Frankfurt am Main GmbH'
category = 'FR Online, Frankfurter Rundschau, Nachrichten, News,Dienste, RSS, RSS, Feedreader, Newsfeed, iGoogle, Netvibes, Widget'
oldest_article = 7
max_articles_per_feed = 100
language = 'de'
lang = 'de-DE'
no_stylesheets = True
use_embedded_content = False
#encoding = 'cp1252'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : lang
}
recursions = 0
max_articles_per_feed = 100
#keep_only_tags = [dict(name='div', attrs={'class':'text'})]
#tags_remove = [dict(name='div', attrs={'style':'text-align: left; margin: 4px 0px 0px 4px; width: 200px; float: right;'})]
remove_attributes = ['style']
feeds = []
#remove_tags_before = [dict(name='div', attrs={'style':'padding-left: 0px;'})]
#remove_tags_after = [dict(name='div', attrs={'class':'box_head_text'})]
# enable for all news
allNews = 0
if allNews:
feeds = [(u'Frankfurter Rundschau', u'http://www.fr-online.de/rss/sport/index.xml')]
else:
#select the feeds you like
feeds = [(u'Nachrichten', u'http://www.fr-online.de/rss/politik/index.xml')]
feeds.append((u'Kommentare und Analysen', u'http://www.fr-online.de/rss/meinung/index.xml'))
feeds.append((u'Dokumentationen', u'http://www.fr-online.de/rss/dokumentation/index.xml'))
feeds.append((u'Deutschlandtrend', u'http://www.fr-online.de/rss/deutschlandtrend/index.xml'))
feeds.append((u'Wirtschaft', u'http://www.fr-online.de/rss/wirtschaft/index.xml'))
feeds.append((u'Sport', u'http://www.fr-online.de/rss/sport/index.xml'))
feeds.append((u'Feuilleton', u'http://www.fr-online.de/rss/feuilleton/index.xml'))
feeds.append((u'Panorama', u'http://www.fr-online.de/rss/panorama/index.xml'))
feeds.append((u'Rhein Main und Hessen', u'http://www.fr-online.de/rss/hessen/index.xml'))
feeds.append((u'Fitness und Gesundheit', u'http://www.fr-online.de/rss/fit/index.xml'))
feeds.append((u'Multimedia', u'http://www.fr-online.de/rss/multimedia/index.xml'))
feeds.append((u'Wissen und Bildung', u'http://www.fr-online.de/rss/wissen/index.xml'))
def get_article_url(self, article):
#string = article.link
#string = string.replace('0C', '/')
#string = string.replace('0I', '_')
#string = string.replace('0E', '-')
#string = string.replace('0B', '.')
#string = string[string.find("fr-online.de"):]
#string = "http://www." + string
#return string
url = article.link
#url = url.replace('0A', '0')
#url = url.replace('0I', '_')
regex = re.compile("0C[0-9]{6,8}0A?")
liste = regex.findall(url)
string = liste.pop(0)
string = string[2:len(string)-1]
return "http://www.fr-online.de/_em_cms/_globals/print.php?em_cnt=" + string