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

Recipe for German Tom's Hardware by Oliver Niesner

Browse Source
This commit is contained in:
Kovid Goyal 2009-01-15 09:44:34 -08:00
parent d1033aa667
commit 3525827192
4 changed files with 57 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
src/calibre/gui2/images/news/tomshardware_de.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 992 B

3
src/calibre/web/feeds/recipes/__init__.py
View File

@ -21,7 +21,8 @@ recipe_modules = ['recipe_' + r for r in (
'linux_magazine', 'telegraph_uk', 'utne', 'sciencedaily', 'forbes',
'time_magazine', 'endgadget', 'fudzilla', 'nspm_int', 'nspm', 'pescanik',
'spiegel_int', 'themarketticker', 'tomshardware', 'xkcd', 'ftd', 'zdnet',
'joelonsoftware', 'telepolis', 'common_dreams', 'nin',
'joelonsoftware', 'telepolis', 'common_dreams', 'nin', 'tomshardware_de',
)]
import re, imp, inspect, time, os

1
src/calibre/web/feeds/recipes/recipe_tomshardware.py
View File

@ -6,7 +6,6 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
tomshardware.com
'''
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.web.feeds.recipes import BasicNewsRecipe
class Tomshardware(BasicNewsRecipe):

54
src/calibre/web/feeds/recipes/recipe_tomshardware_de.py Normal file
View File

@ -0,0 +1,54 @@
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
Fetch tomshardware.
'''
from calibre.web.feeds.news import BasicNewsRecipe
import re
class TomsHardwareDe(BasicNewsRecipe):
title = 'Tom\'s Hardware German'
description = 'Computer news in german'
__author__ = 'Oliver Niesner'
use_embedded_content = False
timefmt = ' [%d %b %Y]'
max_articles_per_feed = 50
no_stylesheets = True
encoding = 'utf-8'
#preprocess_regexps = \
# [(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
# [
# (r'<84>', lambda match: ''),
# (r'<93>', lambda match: ''),
# ]
# ]
remove_tags = [dict(id='outside-advert'),
dict(id='advertRightWhite'),
dict(id='header-advert'),
dict(id='header-banner'),
dict(id='header-menu'),
dict(id='header-top'),
dict(id='header-tools'),
dict(id='nbComment'),
dict(id='internalSidebar'),
dict(id='header-news-infos'),
dict(id='breadcrumbs'),
dict(id=''),
dict(name='div', attrs={'class':'pyjama'}),
dict(name='href', attrs={'class':'comment'}),
dict(name='div', attrs={'class':'greyBoxR clearfix'}),
dict(name='div', attrs={'class':'greyBoxL clearfix'}),
dict(name='div', attrs={'class':'greyBox clearfix'}),
dict(id='')]
#remove_tags_before = [dict(id='header-news-title')]
remove_tags_after = [dict(name='div', attrs={'class':'news-elm'})]
#remove_tags_after = [dict(name='div', attrs={'class':'intelliTXT'})]
feeds = [ ('tomshardware', 'http://www.tomshardware.com/de/feeds/rss2/tom-s-hardware-de,12-1.xml') ]