calibre/recipes/chicago_tribune.recipe

from __future__ import with_statement
__license__ = 'GPL 3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'

import urllib, re
from calibre.web.feeds.news import BasicNewsRecipe

class ChicagoTribune(BasicNewsRecipe):

    title       = 'Chicago Tribune'
    __author__  = 'Kovid Goyal and Sujata Raman, a.peter'
    description = 'Politics, local and business news from Chicago'
    language    = 'en'
    version     = 2

    use_embedded_content = False
    no_stylesheets       = True
    remove_javascript    = True
    recursions           = 1

    keep_only_tags = [dict(name='div', attrs={'class':["story","entry-asset asset hentry"]}),
                      dict(name='div', attrs={'id':["pagebody","story","maincontentcontainer"]}),
                           ]
    remove_tags_after = [{'class':['photo_article',]}]

    match_regexps = [r'page=[0-9]+']

    remove_tags = [{'id':["moduleArticleTools","content-bottom","rail","articleRelates module","toolSet","relatedrailcontent","div-wrapper","beta","atp-comments","footer",'gallery-subcontent','subFooter']},
                   {'class':["clearfix","relatedTitle","articleRelates module","asset-footer","tools","comments","featurePromo","featurePromo fp-topjobs brownBackground","clearfix fullSpan brownBackground","curvedContent",'nextgen-share-tools','outbrainTools', 'google-ad-story-bottom']},
                   dict(name='font',attrs={'id':["cr-other-headlines"]})]
    extra_css = '''
                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
                    .byline {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
                    .date {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                    .copyright {font-family:Arial,Helvetica,sans-serif;font-size:xx-small;text-align:center}
                    .story{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                    .entry-asset asset hentry{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                    .pagebody{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                    .maincontentcontainer{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                    .story-body{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
                '''
    feeds = [
             ('Latest news', 'http://feeds.chicagotribune.com/chicagotribune/news/'),
             ('Local news', 'http://feeds.chicagotribune.com/chicagotribune/news/local/'),
             ('Nation/world', 'http://feeds.chicagotribune.com/chicagotribune/news/nationworld/'),
             ('Hot topics', 'http://feeds.chicagotribune.com/chicagotribune/hottopics/'),
             ('Most E-mailed stories', 'http://feeds.chicagotribune.com/chicagotribune/email/'),
             ('Opinion', 'http://feeds.chicagotribune.com/chicagotribune/opinion/'),
             ('Off Topic', 'http://feeds.chicagotribune.com/chicagotribune/offtopic/'),
             #('Politics', 'http://feeds.chicagotribune.com/chicagotribune/politics/'),
             #('Special Reports', 'http://feeds.chicagotribune.com/chicagotribune/special/'),
             #('Religion News', 'http://feeds.chicagotribune.com/chicagotribune/religion/'),
             ('Business news', 'http://feeds.chicagotribune.com/chicagotribune/business/'),
             ('Jobs and Careers', 'http://feeds.chicagotribune.com/chicagotribune/career/'),
             ('Local scene', 'http://feeds.chicagotribune.com/chicagohomes/localscene/'),
             ('Phil Rosenthal', 'http://feeds.chicagotribune.com/chicagotribune/rosenthal/'),
             #('Tech Buzz', 'http://feeds.chicagotribune.com/chicagotribune/techbuzz/'),
             ('Your Money', 'http://feeds.chicagotribune.com/chicagotribune/yourmoney/'),
             ('Jon Hilkevitch - Getting around', 'http://feeds.chicagotribune.com/chicagotribune/gettingaround/'),
             ('Jon Yates - What\'s your problem?', 'http://feeds.chicagotribune.com/chicagotribune/problem/'),
             ('Garisson Keillor', 'http://feeds.chicagotribune.com/chicagotribune/keillor/'),
             ('Marks Jarvis - On Money', 'http://feeds.chicagotribune.com/chicagotribune/marksjarvisonmoney/'),
             ('Sports', 'http://feeds.chicagotribune.com/chicagotribune/sports/'),
             ('Arts and Architecture', 'http://feeds.chicagotribune.com/chicagotribune/arts/'),
             ('Books', 'http://feeds.chicagotribune.com/chicagotribune/books/'),
             #('Magazine', 'http://feeds.chicagotribune.com/chicagotribune/magazine/'),
             ('Movies', 'http://feeds.chicagotribune.com/chicagotribune/movies/'),
             ('Music', 'http://feeds.chicagotribune.com/chicagotribune/music/'),
             ('TV', 'http://feeds.chicagotribune.com/chicagotribune/tv/'),
             ('Hypertext', 'http://feeds.chicagotribune.com/chicagotribune/hypertext/'),
             ('iPhone Blog', 'http://feeds.feedburner.com/redeye/iphoneblog'),
             ('Julie\'s Health Club', 'http://feeds.chicagotribune.com/chicagotribune_julieshealthclub/'),
             ]


    def get_article_url(self, article):
        ans = None
        try:
            s = article.summary
            ans = urllib.unquote(
                re.search(r'href=".+?bookmark.cfm.+?link=(.+?)"', s).group(1))
        except:
            pass
        if ans is None:
            ans = article.get('feedburner_origlink', article.get('guid', article.get('link')))
        if ans is not None:
            return ans.replace('?track=rss', '')

    def skip_ad_pages(self, soup):
        text = soup.find(text='click here to continue to article')
        if text:
            a = text.parent
            url = a.get('href')
            if url:
                return self.index_to_soup(url, raw=True)

    def postprocess_html(self, soup, first_fetch):
        # Remove the navigation bar. It was kept until now to be able to follow
        # the links to further pages. But now we don't need them anymore.
        for nav in soup.findAll(attrs={'class':['toppaginate','article-nav clearfix']}):
            nav.extract()

        for t in soup.findAll(['table', 'tr', 'td']):
            t.name = 'div'

        for tag in soup.findAll('form', dict(attrs={'name':["comments_form"]})):
            tag.extract()
        for tag in soup.findAll('font', dict(attrs={'id':["cr-other-headlines"]})):
            tag.extract()

        return soup