Fix #930190 (Updated recipe for Pescanik)

This commit is contained in:
Kovid Goyal 2012-02-10 21:39:22 +05:30
parent 21415d0232
commit 047e12391c
2 changed files with 19 additions and 31 deletions

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.1 KiB

After

Width:  |  Height:  |  Size: 289 B

View File

@ -1,18 +1,18 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2012, Darko Miletic <darko.miletic at gmail.com>'
'''
pescanik.net
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Pescanik(BasicNewsRecipe):
title = 'Pescanik'
title = 'Peščanik'
__author__ = 'Darko Miletic'
description = 'Pescanik'
publisher = 'Pescanik'
description = 'Peščanik je udruženje građana osnovano 2006. godine. Glavni proizvod Peščanika je radio emisija koja je emitovana na Radiju B92 od 02.02.2000. do 16.06.2011, a od septembra 2011. se emituje na osam radio stanica u Srbiji, Crnoj Gori i BiH'
publisher = 'Peščanik'
category = 'news, politics, Serbia'
oldest_article = 10
max_articles_per_feed = 100
@ -21,7 +21,12 @@ class Pescanik(BasicNewsRecipe):
encoding = 'utf-8'
language = 'sr'
publication_type = 'newsportal'
extra_css = ' @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} .article_description,body{font-family: Arial,"Lucida Grande",Tahoma,Verdana,sans1,sans-serif} .contentheading{font-size: x-large; font-weight: bold} .small{font-size: small} .createdate{font-size: x-small; font-weight: bold} '
masthead_url = 'http://pescanik.net/wp-content/uploads/2011/10/logo1.png'
extra_css = """
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
body{font-family: Verdana,Arial,Tahoma,sans1,sans-serif}
#BlogTitle{font-size: xx-large; font-weight: bold}
"""
conversion_options = {
'comment' : description
@ -32,29 +37,12 @@ class Pescanik(BasicNewsRecipe):
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
remove_attributes = ['valign','colspan','width','height','align','alt']
remove_tags = [dict(name=['object','link','meta','script'])]
keep_only_tags = [
dict(attrs={'class':['contentheading','small','createdate']})
,dict(name='td', attrs={'valign':'top','colspan':'2'})
]
feeds = [(u'Pescanik Online', u'http://www.pescanik.net/index.php?option=com_rd_rss&id=12')]
remove_tags = [dict(name=['object','link','meta','script','iframe','embed'])]
keep_only_tags = [dict(attrs={'id':['BlogTitle','BlogDate','BlogContent']})]
feeds = [
(u'Autori' , u'http://pescanik.net/category/autori/feed/'),
(u'Prevodi', u'http://pescanik.net/category/prevodi/feed/')
]
def print_version(self, url):
nurl = url.replace('/index.php','/index2.php')
return nurl + '&pop=1&page=0'
def preprocess_html(self, soup):
st = soup.findAll('td')
for it in st:
it.name='p'
for pt in soup.findAll('img'):
brtag = Tag(soup,'br')
brtag2 = Tag(soup,'br')
pt.append(brtag)
pt.append(brtag2)
return soup
return url + 'print/'