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

align to kalibrator - focus_pl.recipe

Browse Source
This commit is contained in:
Tomasz Długosz 2012-10-25 23:47:19 +02:00
parent a114202648
commit ace07d1cc6
1 changed files with 33 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

65
recipes/focus_pl.recipe
View File

@ -2,7 +2,9 @@ import re
from calibre.web.feeds.news import BasicNewsRecipe
class FocusRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = u'intromatyk <intromatyk@gmail.com>'
language = 'pl'
@ -12,10 +14,10 @@ class FocusRecipe(BasicNewsRecipe):
publisher = u'Gruner + Jahr Polska'
category = u'News'
description = u'Newspaper'
category='magazine'
cover_url=''
remove_empty_feeds= True
no_stylesheets=True
category = 'magazine'
cover_url = ''
remove_empty_feeds = True
no_stylesheets = True
oldest_article = 7
max_articles_per_feed = 100000
recursions = 0
@ -27,15 +29,15 @@ class FocusRecipe(BasicNewsRecipe):
simultaneous_downloads = 5
r = re.compile('.*(?P<url>http:\/\/(www.focus.pl)|(rss.feedsportal.com\/c)\/.*\.html?).*')
keep_only_tags =[]
keep_only_tags.append(dict(name = 'div', attrs = {'id' : 'cll'}))
remove_tags =[]
remove_tags.append(dict(name = 'div', attrs = {'class' : 'ulm noprint'}))
remove_tags.append(dict(name = 'div', attrs = {'class' : 'txb'}))
remove_tags.append(dict(name = 'div', attrs = {'class' : 'h2'}))
remove_tags.append(dict(name = 'ul', attrs = {'class' : 'txu'}))
remove_tags.append(dict(name = 'div', attrs = {'class' : 'ulc'}))
keep_only_tags = []
keep_only_tags.append(dict(name='div', attrs={'id': 'cll'}))
remove_tags = []
remove_tags.append(dict(name='div', attrs={'class': 'ulm noprint'}))
remove_tags.append(dict(name='div', attrs={'class': 'txb'}))
remove_tags.append(dict(name='div', attrs={'class': 'h2'}))
remove_tags.append(dict(name='ul', attrs={'class': 'txu'}))
remove_tags.append(dict(name='div', attrs={'class': 'ulc'}))
extra_css = '''
body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
@ -44,18 +46,17 @@ class FocusRecipe(BasicNewsRecipe):
p.lead {font-weight: bold; text-align: left;}
.authordate {font-size: small; color: #696969;}
.fot{font-size: x-small; color: #666666;}
'''
'''
feeds = [
('Nauka', 'http://focus.pl.feedsportal.com/c/32992/f/532693/index.rss'),
('Historia', 'http://focus.pl.feedsportal.com/c/32992/f/532694/index.rss'),
('Cywilizacja', 'http://focus.pl.feedsportal.com/c/32992/f/532695/index.rss'),
('Sport', 'http://focus.pl.feedsportal.com/c/32992/f/532696/index.rss'),
('Technika', 'http://focus.pl.feedsportal.com/c/32992/f/532697/index.rss'),
('Przyroda', 'http://focus.pl.feedsportal.com/c/32992/f/532698/index.rss'),
('Technologie', 'http://focus.pl.feedsportal.com/c/32992/f/532699/index.rss'),
]
feeds = [
('Nauka', 'http://www.focus.pl/nauka/rss/'),
('Historia', 'http://www.focus.pl/historia/rss/'),
('Cywilizacja', 'http://www.focus.pl/cywilizacja/rss/'),
('Sport', 'http://www.focus.pl/sport/rss/'),
('Technika', 'http://www.focus.pl/technika/rss/'),
('Przyroda', 'http://www.focus.pl/przyroda/rss/'),
('Technologie', 'http://www.focus.pl/gadzety/rss/')
]
def skip_ad_pages(self, soup):
if ('advertisement' in soup.find('title').string.lower()):
@ -65,20 +66,20 @@ class FocusRecipe(BasicNewsRecipe):
return None
def get_cover_url(self):
soup=self.index_to_soup('http://www.focus.pl/magazyn/')
tag=soup.find(name='div', attrs={'class':'clr fl'})
soup = self.index_to_soup('http://www.focus.pl/magazyn/')
tag = soup.find(name='div', attrs={'class': 'clr fl'})
if tag:
self.cover_url='http://www.focus.pl/' + tag.a['href']
self.cover_url = 'http://www.focus.pl/' + tag.a['href']
return getattr(self, 'cover_url', self.cover_url)
def print_version(self, url):
if url.count ('focus.pl.feedsportal.com'):
if url.count('focus.pl.feedsportal.com'):
u = url.find('focus0Bpl')
u = 'http://www.focus.pl/' + url[u + 11:]
u = u.replace('0C', '/')
u = u.replace('A', '')
u = u.replace ('0E','-')
u = u.replace('0E', '-')
u = u.replace('/nc/1//story01.htm', '/do-druku/1')
else:
u = url.replace('/nc/1','/do-druku/1')
return u
else:
u = url.replace('/nc/1', '/do-druku/1')
return u