mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
49 lines
2.5 KiB
Plaintext
49 lines
2.5 KiB
Plaintext
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class AdvancedUserRecipe1283848012(BasicNewsRecipe):
|
|
description = 'TheMarker Financial News in Hebrew'
|
|
__author__ = 'Marbs'
|
|
cover_url = 'http://static.ispot.co.il/wp-content/upload/2009/09/themarker.jpg'
|
|
title = u'TheMarker'
|
|
language = 'he'
|
|
simultaneous_downloads = 5
|
|
remove_javascript = True
|
|
timefmt = '[%a, %d %b, %Y]'
|
|
oldest_article = 1
|
|
keep_only_tags =dict(name='div', attrs={'id':'content'})
|
|
remove_attributes = ['width','float','margin-left']
|
|
no_stylesheets = True
|
|
remove_tags = [dict(name='div', attrs={'class':['social-nav article-social-nav','prsnlArticleEnvelope','cb']}) ,
|
|
dict(name='a', attrs={'href':['/misc/mobile']}) ,
|
|
dict(name='span', attrs={'class':['post-summ']}) ]
|
|
max_articles_per_feed = 100
|
|
extra_css='body{direction: rtl;} .article_description{direction: rtl; } a.article{direction: rtl; } .calibre_feed_description{direction: rtl; }'
|
|
feeds = [(u'Head Lines', u'http://www.themarker.com/cmlink/1.144'),
|
|
(u'TA Market', u'http://www.themarker.com/cmlink/1.243'),
|
|
(u'Real Estate', u'http://www.themarker.com/cmlink/1.605656'),
|
|
(u'Global', u'http://www.themarker.com/cmlink/1.605658'),
|
|
(u'Wall Street', u'http://www.themarker.com/cmlink/1.613713'),
|
|
(u'SmartPhone', u'http://www.themarker.com/cmlink/1.605661'),
|
|
(u'Law', u'http://www.themarker.com/cmlink/1.605664'),
|
|
(u'Media', u'http://www.themarker.com/cmlink/1.605660'),
|
|
(u'Consumer', u'http://www.themarker.com/cmlink/1.605662'),
|
|
(u'Career', u'http://www.themarker.com/cmlink/1.605665'),
|
|
(u'Car', u'http://www.themarker.com/cmlink/1.605663'),
|
|
(u'High Tech', u'http://www.themarker.com/cmlink/1.605659'),
|
|
(u'Small Business', u'http://www.themarker.com/cmlink/1.605666')]
|
|
|
|
def print_version(self, url):
|
|
#split1 = url.split("/")
|
|
#print_url='http://www.themarker.com/misc/article-print-page/'+split1[-1]
|
|
txt=url
|
|
|
|
re1='.*?' # Non-greedy match on filler
|
|
re2='(tv)' # Word 1
|
|
|
|
rg = re.compile(re1+re2,re.IGNORECASE|re.DOTALL)
|
|
m = rg.search(txt)
|
|
if m:
|
|
#print 'bad link'
|
|
return 1
|