[schuster]

after a fresh cup of coffee the building of url is O.K.

you are right there are many way's to solve a probleme.
this one IS solved right now.

here the way:

import string, re
from calibre import strftime
class AdvancedUserRecipe(BasicNewsRecipe):

    title = '007_National Geo_run'
    description = 'Magazin des NG '
    __author__ = 'schuster'
    publisher = 'Aus dem Online-Archiv des NG'
    language = 'de'
    cover_url = 'http://www.nationalgeographic.de/images/national-geographic-logo.jpg'
    masthead_url = 'http://www.nationalgeographic.de/images/national-geographic-logo.jpg'
    INDEX = 'http://www.nationalgeographic.de/archive/'

    def parse_index(self):
##--------------------------------------------------------------------------------------
        year_norm = strftime('%Y')                      ## get the year as string
        month_norm = strftime('%m')                     ## get the month as string
        year_min = unicode(int(strftime('%Y')) - 1)     ## string to unicode
        month_min = unicode(int(strftime('%m')[1]) - 1) ## string to unicode
        if (strftime('%m')) <= 1:                       ## if it is january
           year = year_min                              ## get year_min that is minus one year. so i get the last year
           month = 12                                   ## and set month to december
        else:                                           ## otherway
              year = year_norm                          ## get the year today
              month = month_min                         ## and the month minus one month. to get the last month, that had the hole content
##--------------------------------------------------------------------------------------
        articles = []
        soup = self.index_to_soup(self.INDEX+ year + '-' + month)
        feeds = []
        for section in soup.findAll('div', attrs={'class':'searchresult_text'}):
              section_title = self.tag_to_string(section.find('headline-middle_no_margin black'))
              articles = []
              for post in section.findAll('a', href=True):
                  url = post['href']
                  split_url = url.split("/")
                  section_title = split_url[1]
                  if url.startswith('/'):
                   url = 'http://www.nationalgeographic.de'+url
                   title = self.tag_to_string(post)
                   if str(post).find('class=') > 0:
                      klass = post['class']
                      if klass != "":
                        self.log()
                        self.log('--> post:  ', post)
                        self.log('--> url:   ', url)
                        self.log('--> title: ', title)
                        self.log('--> class: ', klass)
                        articles.append({'title':title, 'url':url})
              if articles:
                  feeds.append((section_title, articles))
        return feeds


    keep_only_tags = [dict(attrs={'class':['contentbox_no_top_border']})]
    remove_tags = [dict(name='div', attrs={'class':'gallery'})]

great feeling

- - - - - - - - - - - - - - - - - -

next prob is the right output of the toc, let me see...........