View Single Post
Old 01-09-2014, 09:59 AM   #4
oneillpt
Connoisseur
oneillpt began at the beginning.
 
Posts: 63
Karma: 46
Join Date: Feb 2011
Device: Kindle 3 (cracked screen!); PW1; Oasis
This is working for me

I see I have been using a customised copy, although I think it was probably only the timefmt statement which I added or changed. I do not remember making any change which would effect content extraction.

Code:
__license__   = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'

'''
english.aljazeera.net
'''
from calibre.web.feeds.news import BasicNewsRecipe

class AlJazeera(BasicNewsRecipe):
    title                  = 'Al Jazeera in English'
    __author__             = 'Darko Miletic oneillpt update'
    description            = 'News from Middle East'
    language               = 'en'
    timefmt = ' [%a, %d %b, %Y  %H:%M]'
    publisher              = 'Al Jazeera'
    category               = 'news, politics, middle east'
    delay                  = 1
    oldest_article         = 2
    max_articles_per_feed  = 100
    no_stylesheets         = True
    encoding               = 'iso-8859-1'
    use_embedded_content   = False
    #ignore_duplicate_articles = {'url'}
    ignore_duplicate_articles = {'title', 'url'}
    cover_url = u'http://www.aljazeera.com/Media/ver2/Images/1pximage.png'
    extra_css              = """
                                body{font-family: Arial,sans-serif}
                                #ctl00_cphBody_dvSummary{font-weight: bold}
                                #dvArticleDate{font-size: small; color: #999999}
                             """
    conversion_options = {
                          'comment'   : description
                        , 'tags'      : category
                        , 'publisher' : publisher
                        , 'language'  : language
                        }

    keep_only_tags = [
                         dict(attrs={'id':['DetailedTitle','ctl00_cphBody_dvSummary','dvArticleDate']})
                        ,dict(name='td',attrs={'class':'DetailedSummary'})
                     ]

    remove_tags = [
                     dict(name=['object','link','table','meta','base','iframe','embed'])
                    ,dict(name='td', attrs={'class':['MostActiveDescHeader','MostActiveDescBody']})
                  ]

    feeds = [(u'AL JAZEERA ENGLISH (AJE)', u'http://english.aljazeera.net/Services/Rss/?PostingId=2007731105943979989' )]

    def get_article_url(self, article):
        artlurl =  article.get('link',  None)
        return artlurl.replace('http://english.aljazeera.net//','http://english.aljazeera.net/')

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        for item in soup.findAll(face=True):
            del item['face']
        td = soup.find('td',attrs={'class':'DetailedSummary'})
        if td:
           td.name = 'div'
        spn = soup.find('span',attrs={'id':'DetailedTitle'})
        if spn:
           spn.name='h1'
        for itm in soup.findAll('span', attrs={'id':['dvArticleDate','ctl00_cphBody_lblDate']}):
            itm.name = 'div'
        for alink in soup.findAll('a'):
            if alink.string is not None:
               tstr = alink.string
               alink.replaceWith(tstr)
        return soup
oneillpt is offline   Reply With Quote