Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update antyweb.recipe

Browse Source 
Division to subsections
This commit is contained in:
koliberek 2014-03-28 17:34:19 +01:00
parent 130965ba41
commit 6ff1c2332d
1 changed files with 19 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
recipes/antyweb.recipe
View File

@ -1,4 +1,4 @@
#-*- coding: utf-8 -*-
from calibre.web.feeds.news import BasicNewsRecipe
class AntywebRecipe(BasicNewsRecipe):
@ -15,18 +15,31 @@ class AntywebRecipe(BasicNewsRecipe):
auto_cleanup = False
no_stylesheets=True
use_embedded_content = False
oldest_article = 1
oldest_article = 7
max_articles_per_feed = 100
remove_javascript = True
simultaneous_downloads = 3
ignore_duplicate_articles = {'title', 'url'} # zignoruj zduplikowane artykuły o takich samych tytułach LUB adresach
scale_news_images =True
conversion_options = { 'tags' : u'news, aplikacje mobilne, Android, iOS, Windows Phone ',
'smarten_punctuation' : True,
'publisher' : 'AntyWeb'
} # opcje konwersji.
keep_only_tags=[]
keep_only_tags.append(dict(name = 'h1', attrs = { 'class' : 'entry-title '}))
keep_only_tags.append(dict(name = 'h1'))
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'entry-cover'}))
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'news-content'}))
extra_css = '''body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}'''
feeds = [
(u'Artykuly', u'feed://feeds.feedburner.com/Antyweb?format=xml'),
(u'Felietony', 'http://feeds.feedburner.com/AntywebFelietony'),
(u'Apple', 'http://feeds.feedburner.com/AntywebApple'),
(u'Gry', 'http://feeds.feedburner.com/AntywebGry'),
(u'Mobile', 'http://feeds.feedburner.com/AntywebMobile'),
(u'Startups', 'http://feeds.feedburner.com/AntywebStartups'),
(u'Google', 'http://feeds.feedburner.com/AntywebGoogle'),
(u'Microsoft', 'http://feeds.feedburner.com/AntywebMicrosoft')
]
def preprocess_html(self, soup):
for alink in soup.findAll('a'):