View Single Post
Old 09-20-2010, 10:22 AM   #2777
marbs
Zealot
marbs began at the beginning.
 
Posts: 122
Karma: 10
Join Date: Jul 2010
Device: nook
new recipe TheMarker to be builtin

this is good enough to get in to calibre.
and thanks to TonyTheBookworm. I couldn't do this with out you.
Now its time for my next recipe.

Spoiler:
Code:
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, re

class AdvancedUserRecipe1283848012(BasicNewsRecipe):
    description   = 'TheMarker Financial News in Hebrew'
    __author__            = 'TonyTheBookworm, Marbs'
    cover_url      = 'http://static.ispot.co.il/wp-content/upload/2009/09/themarker.jpg'
    title          = u'TheMarker'
    language              = _('Hebrew')
    simultaneous_downloads = 5
    remove_javascript     = True
    timefmt        = '[%a, %d %b, %Y]'
    oldest_article = 1
    remove_tags = [dict(name='tr', attrs={'bgcolor':['#738A94']})          ]
    max_articles_per_feed = 10
    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/tmc/content/xml/rss/hpfeed.xml'), 
                      (u'TA Market', u'http://www.themarker.com/tmc/content/xml/rss/sections/marketfeed.xml'),
                      (u'Real Estate', u'http://www.themarker.com/tmc/content/xml/rss/sections/realEstaterfeed.xml'),
                      (u'Wall Street & Global', u'http://www.themarker.com/tmc/content/xml/rss/sections/wallsfeed.xml'), 
                      (u'Law', u'http://www.themarker.com/tmc/content/xml/rss/sections/lawfeed.xml'), 
                      (u'Media', u'http://www.themarker.com/tmc/content/xml/rss/sections/mediafeed.xml'), 
                      (u'Consumer', u'http://www.themarker.com/tmc/content/xml/rss/sections/consumerfeed.xml'), 
                      (u'Career', u'http://www.themarker.com/tmc/content/xml/rss/sections/careerfeed.xml'), 
                      (u'Car', u'http://www.themarker.com/tmc/content/xml/rss/sections/carfeed.xml'), 
                      (u'High Tech', u'http://www.themarker.com/tmc/content/xml/rss/sections/hightechfeed.xml'), 
                      (u'Investor Guide', u'http://www.themarker.com/tmc/content/xml/rss/sections/investorGuidefeed.xml')]

    def print_version(self, url):
        print 'ORG URL IS: ', url
        split1 = url.split("=")
        print 'THE SPLIT IS: ', split1 
        weblinks = url
      
        if weblinks is not None:
            for link in weblinks:
                re1='.*?'	
                re2='(it\\.themarker\\.com)'	# Fully Qualified Domain Name 1
                rg = re.compile(re1+re2,re.IGNORECASE|re.DOTALL)
                m = rg.search(url)
                
                
                if m:
                 split2 = url.split("article/")
                 print 'FOUND IT.THEMARKER.COM: ', url
                 print_url = 'http://it.themarker.com/tmit/PrintArticle/' + split2[1]
                
                else:
                    print_url = 'http://www.themarker.com/ibo/misc/printFriendly.jhtml?ElementId=%2Fibo%2Frepositories%2Fstories%2Fm1_2000%2F' + split1[1]+'.xml'
                 
        print 'THIS URL WILL PRINT: ', print_url # this is a test string to see what the url is it will return
        return print_url

Last edited by marbs; 09-20-2010 at 11:33 AM.
marbs is offline