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

New recipe for Jutarnji (thanks to Darko Miletic)

Browse Source
This commit is contained in:
Kovid Goyal 2008-12-04 11:20:13 -08:00
parent b5d167512a
commit b6f9ffbab7
1 changed files with 42 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

67
src/calibre/web/feeds/recipes/jutarnji.py
View File

@ -1,45 +1,42 @@
''' #!/usr/bin/env python
Profile to download Jutarnji.hr by Valloric
'''
import re __license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
jutarnji.hr
'''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Jutarnji(BasicNewsRecipe): class Jutarnji(BasicNewsRecipe):
title = u'Jutarnji'
title = 'Jutarnji' __author__ = u'Darko Miletic'
description = 'News from Croatia' description = u'Hrvatski portal'
__author__ = 'Valloric' oldest_article = 7
use_embedded_content = False max_articles_per_feed = 100
timefmt = ' [%d %b %Y]'
max_articles_per_feed = 80
html_description = True
no_stylesheets = True no_stylesheets = True
use_embedded_content = False
encoding = 'cp1250'
preprocess_regexps = [ remove_tags = [dict(name='embed')]
(re.compile(r'<body.*?<span class="vijestnaslov">', re.IGNORECASE | re.DOTALL), lambda match : '<body><span class="vijestnaslov">'),
(re.compile(r'</div>.*?</td>', re.IGNORECASE | re.DOTALL), lambda match : '</div></td>'),
(re.compile(r'<a name="addComment.*?</body>', re.IGNORECASE | re.DOTALL), lambda match : '</body>'),
(re.compile(r'<br>', re.IGNORECASE | re.DOTALL), lambda match : ''),
]
## Getting the print version
def print_version(self, url):
return 'http://www.jutarnji.hr/ispis_clanka.jl?artid=' + url[len(url)-9:len(url)-3]
## Comment out the feeds you don't want retrieved.
## Or add any new new RSS feed URL's here, sorted alphabetically when converted to LRF
## If you want one of these at the top, append a space in front of the name.
feeds = [ feeds = [
(' Naslovnica', 'http://www.jutarnji.hr/rss'), (u'Naslovnica' , u'http://www.jutarnji.hr/rss' )
('Sport', 'http://www.jutarnji.hr/sport/rss'), ,(u'Sport' , u'http://www.jutarnji.hr/sport/rss' )
('Novac', 'http://www.jutarnji.hr/novac/rss'), ,(u'Jutarnji2' , u'http://www.jutarnji.hr/j2/rss' )
('Kultura i zivot', 'http://www.jutarnji.hr/kultura_i_zivot/rss'), ,(u'Kultura' , u'http://www.jutarnji.hr/kultura/rss' )
('Automoto', 'http://www.jutarnji.hr/auto_moto/rss'), ,(u'Spektakli' , u'http://www.jutarnji.hr/spektakli/rss' )
('Hi-Tech', 'http://www.jutarnji.hr/kultura_i_zivot/hi-tech/rss'), ,(u'Dom i nekretnine', u'http://www.jutarnji.hr/nekretnine/rss')
('Dom i nekretnine', 'http://www.jutarnji.hr/nekretnine/rss'), ,(u'Uhvati ritam' , u'http://www.jutarnji.hr/kalendar/rss' )
] ]
def print_version(self, url):
main = url.partition('.jl')[0]
rrest = main.rpartition(',')[-1]
return 'http://www.jutarnji.hr/ispis_clanka.jl?artid=' + rrest
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8">'
soup.head.insert(0,mtag)
return soup