home *** CD-ROM | disk | FTP | other *** search
- __license__ = 'GPL v3'
- __copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
- '''
- techcrunch.com
- '''
-
- from calibre.web.feeds.news import BasicNewsRecipe
-
- class TechCrunch(BasicNewsRecipe):
- title = 'TechCrunch'
- __author__ = 'Darko Miletic'
- description = 'IT News'
- publisher = 'AOL Inc.'
- category = 'news, IT'
- oldest_article = 2
- max_articles_per_feed = 200
- no_stylesheets = True
- encoding = 'utf8'
- use_embedded_content = False
- language = 'en'
- remove_empty_feeds = True
- publication_type = 'newsportal'
- masthead_url = 'http://s2.wp.com/wp-content/themes/vip/tctechcrunch2/images/site-logo.png'
- extra_css = """
- body{font-family: Helvetica,Arial,sans-serif }
- img{margin-bottom: 0.4em; display:block}
- """
-
- conversion_options = {
- 'comment' : description
- , 'tags' : category
- , 'publisher' : publisher
- , 'language' : language
- }
-
- remove_tags = [dict(name=['meta','link'])]
- remove_attributes=['lang']
- keep_only_tags=[
- dict(name='h1', attrs={'class':'headline'})
- ,dict(attrs={'class':['author','post-time','body-copy']})
- ]
-
- feeds = [(u'News', u'http://feeds.feedburner.com/TechCrunch/')]
-
- def preprocess_html(self, soup):
- for item in soup.findAll(style=True):
- del item['style']
- for item in soup.findAll('a'):
- limg = item.find('img')
- if item.string is not None:
- str = item.string
- item.replaceWith(str)
- else:
- if limg:
- item.name = 'div'
- item.attrs = []
- else:
- str = self.tag_to_string(item)
- item.replaceWith(str)
- for item in soup.findAll('img'):
- if not item.has_key('alt'):
- item['alt'] = 'image'
- return soup
-