home *** CD-ROM | disk | FTP | other *** search
- #!/usr/bin/env python
-
- __license__ = 'GPL v3'
- __copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
- '''
- timesonline.co.uk
- '''
- import re
-
- from calibre.web.feeds.news import BasicNewsRecipe
- from calibre.ebooks.BeautifulSoup import Tag
-
- class Timesonline(BasicNewsRecipe):
- title = 'The Times Online'
- __author__ = 'Darko Miletic and Sujata Raman'
- description = 'UK news'
- publisher = 'timesonline.co.uk'
- category = 'news, politics, UK'
- oldest_article = 2
- max_articles_per_feed = 100
- no_stylesheets = True
- use_embedded_content = False
- simultaneous_downloads = 1
- encoding = 'ISO-8859-1'
- remove_javascript = True
- language = 'en_GB'
- recursions = 9
- match_regexps = [r'http://www.timesonline.co.uk/.*page=[2-9]']
-
- preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
-
- keep_only_tags = [
- dict(name='div', attrs= {'id':['region-column1and2-layout2']}),
- {'class' : ['subheading']},
- dict(name='div', attrs= {'id':['dynamic-image-holder']}),
- dict(name='div', attrs= {'class':['article-author']}),
- dict(name='div', attrs= {'id':['related-article-links']}),
- ]
-
- remove_tags = [
- dict(name=['embed','object','form','iframe']),
- dict(name='span', attrs = {'class':'float-left padding-left-8 padding-top-2'}),
- dict(name='div', attrs= {'id':['region-footer','region-column2-layout2','grid-column4','login-status','comment-sort-order']}),
- dict(name='div', attrs= {'class': ['debate-quote-container','clear','your-comment','float-left related-attachements-container','float-left padding-bottom-5 padding-top-8','puff-top']}),
- dict(name='span', attrs = {'id': ['comment-count']}),
- dict(name='ul',attrs = {'id': 'read-all-comments'}),
- dict(name='a', attrs = {'class':'reg-bold'}),
- ]
-
-
- extra_css = '''
- .small{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
- .byline{font-family :Arial,Helvetica,sans-serif; font-size:x-small; background:#F8F1D8;}
- .color-666{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#666666; }
- h1{font-family:Georgia,Times New Roman,Times,serif;font-size:large; }
- .color-999 {color:#999999;}
- .x-small {font-size:x-small;}
- #related-article-links{font-family :Arial,Helvetica,sans-serif; font-size:small;}
- h2{color:#333333;font-family :Georgia,Times New Roman,Times,serif; font-size:small;}
- p{font-family :Arial,Helvetica,sans-serif; font-size:small;}
- '''
-
- feeds = [
- (u'Top stories from Times Online', u'http://www.timesonline.co.uk/tol/feeds/rss/topstories.xml' ),
- ('Latest Business News', 'http://www.timesonline.co.uk/tol/feeds/rss/business.xml'),
- ('Economics', 'http://www.timesonline.co.uk/tol/feeds/rss/economics.xml'),
- ('World News', 'http://www.timesonline.co.uk/tol/feeds/rss/worldnews.xml'),
- ('UK News', 'http://www.timesonline.co.uk/tol/feeds/rss/uknews.xml'),
- ('Travel News', 'http://www.timesonline.co.uk/tol/feeds/rss/travel.xml'),
- ('Sports News', 'http://www.timesonline.co.uk/tol/feeds/rss/sport.xml'),
- ('Film News', 'http://www.timesonline.co.uk/tol/feeds/rss/film.xml'),
- ('Tech news', 'http://www.timesonline.co.uk/tol/feeds/rss/tech.xml'),
- ('Literary Supplement', 'http://www.timesonline.co.uk/tol/feeds/rss/thetls.xml'),
- ]
-
- def get_cover_url(self):
- cover_url = None
- index = 'http://www.timesonline.co.uk/tol/newspapers/'
- soup = self.index_to_soup(index)
- link_item = soup.find(name = 'div',attrs ={'class': "float-left margin-right-15"})
- if link_item:
- cover_url = link_item.img['src']
- return cover_url
-
- def get_article_url(self, article):
- return article.get('guid', None)
-
-
- def preprocess_html(self, soup):
- soup.html['xml:lang'] = self.language
- soup.html['lang'] = self.language
- mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.language)])
- mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=ISO-8859-1")])
- soup.head.insert(0,mlang)
- soup.head.insert(1,mcharset)
- return self.adeify_images(soup)
-
- def postprocess_html(self,soup,first):
- for tag in soup.findAll(text = ['Previous Page','Next Page']):
- tag.extract()
- return soup
-
-
-