Register Guidelines E-Books Search Today's Posts Mark Forums Read

Go Back   MobileRead Forums > E-Book Software > Calibre > Recipes


Thread Tools Search this Thread
Old 05-18-2011, 03:39 PM   #1
schuster doesn't litterschuster doesn't litter
Posts: 116
Karma: 100
Join Date: Jan 2011
Location: Germany / NRW /Köln
Device: prs-650 / prs-350 /kindle 3
recipe for - german

from import BasicNewsRecipe
class AdvancedUserRecipe1305470859(BasicNewsRecipe):
    title                 = u''
    language              = 'de'
    __author__            = 'schuster'
    oldest_article        =7
    max_articles_per_feed = 35
    no_stylesheets        = True
    remove_javascript     = True
    use_embedded_content  = False
    masthead_url = ''
    cover_url = ''

    def preprocess_html(self, soup):
        for alink in soup.findAll('a'):
            if alink.string is not None:
               tstr = alink.string
        return soup                      

    extra_css = '''
                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
                    h4{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
                    img {min-width:300px; max-width:600px; min-height:300px; max-height:800px}
    def print_version(self, url):
        return url.replace ('nv=rss#utm_source=rss2&utm_medium=rss_feed&utm_campaign=/', 'mode=print')
    remove_tags_bevor = [dict(name='td', attrs={'class':'textcell'})]
    remove_tags_after = [dict(name='div', attrs={'class':'artikelsplit'})]

    feeds = [   (u'Wirtschaftsmagazin', u''),
	(u'Unternehmen', u''),
	(u'Finanz & Geldanlage', u'')]

    def append_page(self, soup, appendtag, position):
        pager = soup.find('div',attrs={'class':'artikelsplit'})
        if pager:
           nexturl = self.INDEX + pager.a['href']
           soup2 = self.index_to_soup(nexturl)
           texttag = soup2.find('div', attrs={'class':'printable'})
           for it in texttag.findAll(style=True):
               del it['style']
           newpos = len(texttag.contents)

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        for item in soup.findAll('div', attrs={'class':'artikelsplit'}):
        self.append_page(soup, soup.body, 3)
        pager = soup.find('div',attrs={'class':'artikelsplit'})
        if pager:
        return self.adeify_images(soup)

    remove_tags = [dict(attrs={'class':['navSeitenAlle', 'kommentieren', 'teaserheader', 'teasercontent', 'info', 'zwischenhead', 'artikelsplit']}),
                dict(id=['topNav', 'mainNav', 'subNav', 'socialmedia', 'footerRahmen', 'gatrixx_marktinformationen', 'pager', 'weitere']),
                dict(span=['ratingtext', 'Gesamtranking', 'h3','']),

Last edited by schuster; 05-18-2011 at 03:48 PM.
schuster is offline   Reply With Quote
Old 05-01-2016, 04:45 AM   #2
Aimylios began at the beginning.
Posts: 14
Karma: 10
Join Date: Apr 2016
Device: Tolino Vision 3HD
Hi, changed its feed address and also the structure of the articles. I modified and cleaned up the original capital_de.recipe to make it work again.

#!/usr/bin/env python2
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function


import re
from import BasicNewsRecipe

class AdvancedUserRecipe1305470859(BasicNewsRecipe):
    title       = ''
    __author__  = 'schuster'
    description = 'RSS-Feed von'
    publisher   = 'Gruner+Jahr GmbH & Co KG'
    language    = 'de'

    oldest_article        = 14
    max_articles_per_feed = 35
    no_stylesheets        = True
    remove_javascript     = True
    use_embedded_content  = False

    conversion_options = {'smarten_punctuation' : True,
                          'publisher'           : publisher}

    cover_source = ''
    masthead_url = ''

    feeds = [
        ('', '')

    keep_only_tags = [
        dict(name='div', attrs={'class':'grid_8 alpha omega layout_full block'})

    remove_tags = [
        dict(name='div', attrs={'class':'article_header'}),
        dict(name='br', attrs={'class':'clear'})

    remove_attributes = ['height', 'width']

    extra_css = 'h1 {font-size: 1.6em; text-align: left} \
                 h2 {font-size: 1em; text-align: left} \
                 .copyright {font-size: 0.6em} \
                 .caption {font-size: 0.6em}'

    def get_cover_url(self):
        soup = self.index_to_soup(self.cover_source)
        img_span = soup.find('span', {'class':re.compile('coverimage')})
        self.cover_url = img_span.find('img', src=True)['src']
        return self.cover_url

    def preprocess_html(self, soup):
        # remove all articles without relevant content
        tags = soup.findAll('li', {'class':'tag-chain-item'})
        for li in tags:
            if 'BILDERSTRECKE' in self.tag_to_string(li).upper():
        # remove list of tags
        tags = soup.find('ul', {'class':'tag-chain'})
        if tags:
        # remove all style attributes
        for item in soup.findAll(style=True):
            del item['style']
        # remove all local hyperlinks
        for a in soup.findAll('a', {'href':True}):
            if a['href'] and not 'http' in a['href']:
                del a['href']
        # remove picture(s) of author(s)
        for div in soup.findAll('div', {'class':'ce_text block'}):
            if div.find('hr'):
                for hr in div.findAll('hr'):
                for img in div.findAll('img'):
        return soup
Aimylios is offline   Reply With Quote

Thread Tools Search this Thread
Search this Thread:

Advanced Search

Forum Jump

Similar Threads
Thread Thread Starter Forum Replies Last Post
recipe for - German schuster Recipes 2 05-22-2016 05:00 AM
recipe for - german schuster Recipes 1 06-05-2011 09:58 AM
recipe for - German schuster Recipes 3 05-15-2011 11:33 AM
recipe for Astronomie heute - german schuster Recipes 0 05-14-2011 12:42 PM
Hi from the ex capital of culture snickp Introduce Yourself 14 01-30-2009 02:27 PM

All times are GMT -4. The time now is 10:32 AM. is a privately owned, operated and funded community.