mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-02-24 12:10:06 -05:00
86 lines
3.7 KiB
Python
86 lines
3.7 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
spiegel.de
|
|
'''
|
|
|
|
import time, re
|
|
from contextlib import closing
|
|
from calibre import as_unicode
|
|
from calibre.web.feeds import feed_from_xml, Feed
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class Spiegel_ger(BasicNewsRecipe):
|
|
title = 'Spiegel Online - German'
|
|
__author__ = 'Darko Miletic'
|
|
description = "Immer die neueste Meldung auf dem Schirm, sekundenaktuell und uebersichtlich: Mit dem RSS-Angebot von SPIEGEL ONLINE entgeht Ihnen keine wichtige Meldung mehr, selbst wenn Sie keinen Internet-Browser geoeffnet haben. Sie koennen unsere Nachrichten-Feeds ganz einfach abonnieren - unkompliziert, kostenlos und nach Ihren persoenlichen Themen-Vorlieben." # noqa
|
|
publisher = 'SPIEGEL ONLINE Gmbh'
|
|
category = 'SPIEGEL ONLINE, DER SPIEGEL, 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'
|
|
keep_only_tags = [
|
|
dict(name='h2', attrs={'class':'article-title'}),
|
|
dict(id=['js-article-top-wide-asset', 'js-article-column']),
|
|
]
|
|
remove_tags = [
|
|
dict(attrs={'class':lambda x: x and 'asset-html-box' in x.split()}),
|
|
dict(attrs={'class':lambda x: x and 'article-social-bookmark' in x.split()}),
|
|
dict(attrs={'class':lambda x: x and 'article-newsfeed-box' in x.split()}),
|
|
dict(attrs={'class':lambda x: x and 'article-comments-box' in x.split()}),
|
|
dict(attrs={'class':lambda x: x and 'article-functions-bottom' in x.split()}),
|
|
]
|
|
|
|
conversion_options = {
|
|
'comment' : description
|
|
, 'tags' : category
|
|
, 'publisher' : publisher
|
|
, 'language' : lang
|
|
}
|
|
|
|
feeds = [(u'Spiegel Online', u'http://www.spiegel.de/schlagzeilen/index.rss')]
|
|
|
|
def get_article_url(self, *args):
|
|
url = BasicNewsRecipe.get_article_url(self, *args).replace('#', '/#')
|
|
ai = re.search(r'ai=(\d+)', url).group(1)
|
|
soup = self.index_to_soup(url)
|
|
a = soup.find('a', href=lambda x: x and ai in x)
|
|
return 'http://www.spiegel.de' + a['href']
|
|
|
|
def parse_feeds(self):
|
|
title, url = self.feeds[0]
|
|
self.report_progress(0, _('Fetching feed')+' %s...'%(title if title else url))
|
|
parsed_feeds = []
|
|
try:
|
|
with closing(self.browser.open(url)) as s:
|
|
raw = s.read()
|
|
raw = raw.replace(b'<guid>http://www.spiegel.de</guid>', b'')
|
|
|
|
parsed_feeds.append(feed_from_xml(raw, title=title, log=self.log, oldest_article=self.oldest_article,
|
|
max_articles_per_feed=self.max_articles_per_feed,
|
|
get_article_url=self.get_article_url))
|
|
if (self.delay > 0):
|
|
time.sleep(self.delay)
|
|
except Exception as err:
|
|
feed = Feed()
|
|
msg = 'Failed feed: %s'%(title if title else url)
|
|
feed.populate_from_preparsed_feed(msg, [])
|
|
feed.description = as_unicode(err)
|
|
parsed_feeds.append(feed)
|
|
self.log.exception(msg)
|
|
|
|
remove = [f for f in parsed_feeds if len(f) == 0 and
|
|
self.remove_empty_feeds]
|
|
for f in remove:
|
|
parsed_feeds.remove(f)
|
|
|
|
return parsed_feeds
|
|
|
|
|