[aerodynamik]

Here we go, a first recipe for the printed edition of Der Spiegel. You need a subscription to access it.

I tested it on my Kindle 3, looks very good. Would be great to get some more tests on other devices.

When you copy the script, replace the character ◆ with "& # 9670 ;" (remove spaces in quotes). My Kindle wasn't able to display this correctly so I just replaced with a horizontal rule.

Spoiler:

#!/usr/bin/env  python

__license__   = 'GPL v3'
__copyright__ = '2011, Nikolas Mangold <nmangold at gmail.com>'
'''
spiegel.de
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre import strftime
from calibre import re

class DerSpiegel(BasicNewsRecipe):
    title                  = 'Der Spiegel'
    __author__             = 'Nikolas Mangold'
    description            = 'Der Spiegel, Printed Edition. Access to paid content.'
    publisher              = 'SPIEGEL-VERLAG RUDOLF AUGSTEIN GMBH & CO. KG'
    category               = 'news, politics, Germany'
    no_stylesheets         = True
    encoding               = 'cp1252'
    needs_subscription     = True
    remove_empty_feeds     = True
    delay                  = 1
    PREFIX                 = 'http://m.spiegel.de'
    INDEX                  = PREFIX + '/spiegel/print/epaper/index-heftaktuell.html'
    use_embedded_content   = False
    masthead_url = 'http://upload.wikimedia.org/wikipedia/en/thumb/1/17/Der_Spiegel_logo.svg/200px-Der_Spiegel_logo.svg.png'
    language               = 'de'
    publication_type       = 'magazine'
    extra_css              = ' body{font-family: Arial,Helvetica,sans-serif} '
    timefmt = '[%W/%Y]'
    empty_articles = ['Titelbild']
    preprocess_regexps = [
        (re.compile(r'<p>◆</p>', re.DOTALL|re.IGNORECASE), lambda match: '<hr>'),
        ]

    def get_browser(self):
        def has_login_name(form):
            try:
                form.find_control(name="f.loginName")
            except:
                return False
            else:
                return True

        br = BasicNewsRecipe.get_browser()
        if self.username is not None and self.password is not None:
            br.open(self.PREFIX + '/meinspiegel/login.html')
            br.select_form(predicate=has_login_name)
            br['f.loginName'    ] = self.username
            br['f.password'] = self.password
            br.submit()
        return br

    remove_tags_before =  dict(attrs={'class':'spArticleContent'})
    remove_tags_after  =  dict(attrs={'class':'spArticleCredit'})
        
    def parse_index(self):
        soup = self.index_to_soup(self.INDEX)

        cover = soup.find('img', width=248)
        if cover is not None:
            self.cover_url = cover['src']

        index = soup.find('dl')

        feeds = []
        for section in index.findAll('dt'):
            section_title = self.tag_to_string(section).strip()
            self.log('Found section ', section_title)

            articles = []
            for article in section.findNextSiblings(['dd','dt']):
                if article.name == 'dt':
                    break
                link = article.find('a')
                title = self.tag_to_string(link).strip()
                if title in self.empty_articles:
                    continue
                self.log('Found article ', title)
                url = self.PREFIX + link['href']
                articles.append({'title' : title, 'date' : strftime(self.timefmt), 'url' : url})
            feeds.append((section_title,articles))
        return feeds;

I am unhappy with this code

            
for article in section.findNextSiblings(['dd','dt']):
    if article.name == 'dt':
         break

with which I am trying to get all articles ('dd') underneath a section ('dt')

<dt>section 1</dt>
 <dd class="spFirst">article 1</dd>
 <dd>article 2</dd>
<dt>section 2</dt>
 <dd>article 3</dd>

findNextSiblings would give me all 'dd's over all sections, but I am sure there is some smarter and better way to resolve this

Is it okay to use a wikipedia image for the masthead image?