Read infzm - China Southern Weekly on your iPad or Kindle in no time. Click download to load the free ebook on your reader.

Check out all the available public recipes or write your own with these quick start guides. ReadBeam is built on calibre, so everything in the docs and the fora applies here as well.

Download for free »

Chinese Weekly Tabloid

Language: zh

Requires Subscription: No, it's available as free ebook

Schedule Every morning

			  from calibre.web.feeds.news import BasicNewsRecipe

class AdvancedUserRecipe1277305250(BasicNewsRecipe):
    title          = u'infzm - China Southern Weekly'
    oldest_article = 14
    max_articles_per_feed = 100

    feeds          = [(u'\u5357\u65b9\u5468\u672b-\u70ed\u70b9\u65b0\u95fb', u'http://www.infzm.com/rss/home/rss2.0.xml'),
	(u'\u5357\u65b9\u5468\u672b-\u7ecf\u6d4e\u65b0\u95fb', u'http://www.infzm.com/rss/economic.xml'),
	(u'\u5357\u65b9\u5468\u672b-\u6587\u5316\u65b0\u95fb', u'http://www.infzm.com/rss/culture.xml'),
	(u'\u5357\u65b9\u5468\u672b-\u751f\u6d3b\u65f6\u5c1a', u'http://www.infzm.com/rss/lifestyle.xml'),
	(u'\u5357\u65b9\u5468\u672b-\u89c2\u70b9', u'http://www.infzm.com/rss/opinion.xml')
	]
    __author__            = 'rty'
    __version__            = '1.0'
    language = 'zh'
    pubisher  = 'http://www.infzm.com'
    description           = 'Chinese Weekly Tabloid'
    category              = 'News, China'
    remove_javascript = True
    use_embedded_content   = False
    no_stylesheets = True
    #encoding               = 'GB2312'
    encoding               = 'UTF-8'
    conversion_options = {'linearize_tables':True}
    masthead_url = 'http://i50.tinypic.com/2qmfb7l.jpg'

    extra_css = '''
             @font-face { font-family: "DroidFont", serif, sans-serif;  src: url(res:///system/fonts/DroidSansFallback.ttf); }\n
             body {
                  margin-right: 8pt;
                  font-family: 'DroidFont', serif;}
             .detailContent {font-family: 'DroidFont', serif, sans-serif}
            '''

    keep_only_tags = [
                              dict(name='div', attrs={'id':'detailContent'}),
                               ]
    remove_tags = [
                    dict(name='div', attrs={'id':['detailTools', 'detailSideL', 'pageNum']}),
                         ]
    remove_tags_after = [
                  dict(name='div', attrs={'id':'pageNum'}),
                         ]
    def preprocess_html(self, soup):
        for item in soup.findAll(color=True):
            del item['font']
        for item in soup.findAll(style=True):
            del item['style']
        return soup