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

Various German news sources by schuster

Browse Source
This commit is contained in:
Kovid Goyal 2011-05-18 14:16:41 -06:00
parent d882c28144
commit 5317f8bb9c
3 changed files with 126 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
recipes/borse_online.recipe Normal file
View File

@ -0,0 +1,33 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'Börse-online'
__author__ = 'schuster'
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'de'
remove_javascript = True
cover_url = 'http://www.dpv.de/images/1995/source.gif'
masthead_url = 'http://www.zeitschriften-cover.de/cover/boerse-online-cover-januar-2010-x1387.jpg'
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h4{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
img {min-width:300px; max-width:600px; min-height:300px; max-height:800px}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
remove_tags_bevor = [dict(name='h3')]
remove_tags_after = [dict(name='div', attrs={'class':'artikelfuss'})]
remove_tags = [dict(attrs={'class':['moduleTopNav', 'moduleHeaderNav', 'text', 'blau', 'poll1150']}),
dict(id=['newsletterlayer', 'newsletterlayerClose', 'newsletterlayer_body', 'newsletterarray_error', 'newsletterlayer_emailadress', 'newsletterlayer_submit', 'kommentar']),
dict(name=['h2', 'Gesamtranking', 'h3',''])]
def print_version(self, url):
return url.replace('.html#nv=rss', '.html?mode=print')
feeds = [(u'Börsennachrichten', u'http://www.boerse-online.de/rss/')]

61
recipes/capital_de.recipe Normal file
View File

@ -0,0 +1,61 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1305470859(BasicNewsRecipe):
title = u'Capital.de'
language = 'de'
__author__ = 'schuster'
oldest_article =7
max_articles_per_feed = 35
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
masthead_url = 'http://www.wirtschaftsmedien-shop.de/media/stores/wirtschaftsmedien/capital/teaser_large_abo.jpg'
cover_url = 'http://d1kb9jvg6ylufe.cloudfront.net/WebsiteCMS/de/unternehmen/linktipps/mainColumn/08/image/DE_Capital_bis20mm_SW.jpg'
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h4{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
img {min-width:300px; max-width:600px; min-height:300px; max-height:800px}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
def print_version(self, url):
return url.replace ('nv=rss#utm_source=rss2&utm_medium=rss_feed&utm_campaign=/', 'mode=print')
remove_tags_bevor = [dict(name='td', attrs={'class':'textcell'})]
remove_tags_after = [dict(name='div', attrs={'class':'artikelsplit'})]
feeds = [ (u'Wirtschaftsmagazin', u'http://www.capital.de/rss/'),
(u'Unternehmen', u'http://www.capital.de/rss/unternehmen'),
(u'Finanz & Geldanlage', u'http://www.capital.de/rss/finanzen/geldanlage')]
def append_page(self, soup, appendtag, position):
pager = soup.find('div',attrs={'class':'artikelsplit'})
if pager:
nexturl = self.INDEX + pager.a['href']
soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'class':'printable'})
for it in texttag.findAll(style=True):
del it['style']
newpos = len(texttag.contents)
self.append_page(soup2,texttag,newpos)
texttag.extract()
appendtag.insert(position,texttag)
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('div', attrs={'class':'artikelsplit'}):
item.extract()
self.append_page(soup, soup.body, 3)
pager = soup.find('div',attrs={'class':'artikelsplit'})
if pager:
pager.extract()
return self.adeify_images(soup)
remove_tags = [dict(attrs={'class':['navSeitenAlle', 'kommentieren', 'teaserheader', 'teasercontent', 'info', 'zwischenhead', 'artikelsplit']}),
dict(id=['topNav', 'mainNav', 'subNav', 'socialmedia', 'footerRahmen', 'gatrixx_marktinformationen', 'pager', 'weitere']),
dict(span=['ratingtext', 'Gesamtranking', 'h3','']),
dict(rel=['canonical'])]

32
recipes/impulse_de.recipe Normal file
View File

@ -0,0 +1,32 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1305470859(BasicNewsRecipe):
title = u'Impulse.de'
language = 'de'
__author__ = 'schuster'
oldest_article =14
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
cover_url = 'http://www.bvk.de/files/image/bilder/Logo%20Impulse.jpg'
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h4{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
img {min-width:300px; max-width:600px; min-height:300px; max-height:800px}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
def print_version(self, url):
return url.replace ('#utm_source=rss2&utm_medium=rss_feed&utm_campaign=/', '?mode=print')
remove_tags_bevor = [dict(name='h1', attrs={'class':'h2'})]
remove_tags_after = [dict(name='div', attrs={'class':'artikelfuss'})]
feeds = [ (u'impulstest', u'http://www.impulse.de/rss/')]
remove_tags = [dict(attrs={'class':['navSeitenAlle', 'kommentieren', 'teaserheader', 'teasercontent', 'info', 'zwischenhead', 'kasten_artikel']}),
dict(id=['metaNav', 'impKopf', 'impTopNav', 'impSubNav', 'footerRahmen', 'gatrixx_marktinformationen', 'pager', 'weitere', 'socialmedia', 'rating_open']),
dict(span=['ratingtext', 'Gesamtranking', 'h3','']),
dict(rel=['canonical'])]