calibre/recipes/guardian.recipe

#!/usr/bin/env  python
__license__   = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'

'''
www.guardian.co.uk
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from datetime import date
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag

class Guardian(BasicNewsRecipe):

    title = u'The Guardian and The Observer'
    if date.today().weekday() == 6:
        base_url = "http://www.guardian.co.uk/theobserver"
        cover_pic = 'Observer digital edition'
        masthead_url = 'http://static.guim.co.uk/sys-images/Guardian/Pix/site_furniture/2010/10/19/1287478087992/The-Observer-001.gif'
    else:
        base_url = "http://www.guardian.co.uk/theguardian"
        cover_pic = 'Guardian digital edition'
        masthead_url = 'http://static.guim.co.uk/static/f76b43f9dcfd761f0ecf7099a127b603b2922118/common/images/logos/the-guardian/titlepiece.gif'

    __author__ = 'Seabound and Sujata Raman'
    language = 'en_GB'

    oldest_article              = 7
    max_articles_per_feed       = 100
    remove_javascript           = True
    encoding                    = 'utf-8'

    # List of section titles to ignore
    # For example: ['Sport']
    ignore_sections = []

    timefmt = ' [%a, %d %b %Y]'
    keep_only_tags = [
                      dict(name='div', attrs={'id':["content","article_header","main-article-info",]}),
                           ]
    remove_tags = [
                        dict(name='div', attrs={'class':["video-content","videos-third-column"]}),
                        dict(name='div', attrs={'id':["article-toolbox","subscribe-feeds",]}),
                        dict(name='div', attrs={'class':["guardian-tickets promo-component",]}),
                        dict(name='ul', attrs={'class':["pagination"]}),
                        dict(name='ul', attrs={'id':["content-actions"]}),
                        # article history link
                        dict(name='a', attrs={'class':["rollover history-link"]}),
                        # "a version of this article ..." speil
                        dict(name='div' , attrs = { 'class' : ['section']}),
                        # "about this article" js dialog
                        dict(name='div', attrs={'class':["share-top",]}),
                        # author picture
                        dict(name='img', attrs={'class':["contributor-pic-small"]}),
                        # embedded videos/captions
                        dict(name='span',attrs={'class' : ['inline embed embed-media']}),
                        #dict(name='img'),
                        ]
    use_embedded_content    = False

    no_stylesheets = True
    extra_css = '''
                    .article-attributes{font-size: x-small; font-family:Arial,Helvetica,sans-serif;}
                    .h1{font-size: large ;font-family:georgia,serif; font-weight:bold;}
                    .stand-first-alone{color:#666666; font-size:small; font-family:Arial,Helvetica,sans-serif;}
                    .caption{color:#666666; font-size:x-small; font-family:Arial,Helvetica,sans-serif;}
                    #article-wrapper{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
                    .main-article-info{font-family:Arial,Helvetica,sans-serif;}
                    #full-contents{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
                    #match-stats-summary{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
                '''

    def get_article_url(self, article):
          url = article.get('guid', None)
          if '/video/' in url or '/flyer/' in url or '/quiz/' in url or \
              '/gallery/' in url  or 'ivebeenthere' in url or \
              'pickthescore' in url or 'audioslideshow' in url :
              url = None
          return url

    def populate_article_metadata(self, article, soup, first):
        if first and hasattr(self, 'add_toc_thumbnail'):
            picdiv = soup.find('img')
            if picdiv is not None:
                self.add_toc_thumbnail(article,picdiv['src'])

    def preprocess_html(self, soup):

          # multiple html sections in soup, useful stuff in the first
          html = soup.find('html')
          soup2 = BeautifulSoup()
          soup2.insert(0,html) 
          
          soup = soup2  
          
          for item in soup.findAll(style=True):
              del item['style']

          for item in soup.findAll(face=True):
              del item['face']
          for tag in soup.findAll(name=['ul','li']):
                tag.name = 'div'
         
         # removes number next to rating stars
          items_to_remove = []
          rating_container = soup.find('div', attrs = {'class': ['rating-container']})
          if rating_container:
            for item in rating_container:
                if isinstance(item, Tag) and str(item.name) == 'span':
                    items_to_remove.append(item)
          
          for item in items_to_remove:
            item.extract()
          
          return soup

    def find_sections(self):
        # soup = self.index_to_soup("http://www.guardian.co.uk/theobserver")
        soup = self.index_to_soup(self.base_url)
        # find cover pic
        img = soup.find( 'img',attrs ={'alt':self.cover_pic})
        if img is not None:
            self.cover_url = img['src']
        # end find cover pic

        idx = soup.find('div', id='book-index')
        for s in idx.findAll('strong', attrs={'class':'book'}):
            a = s.find('a', href=True)
            section_title = self.tag_to_string(a)
            if not section_title in self.ignore_sections:
                prefix = ''
                if section_title != 'Main section':
                    prefix = section_title + ': '
                for subsection in s.parent.findAll('a', attrs={'class':'book-section'}):
                    yield (prefix + self.tag_to_string(subsection), subsection['href'])

    def find_articles(self, url):
        soup = self.index_to_soup(url)
        div = soup.find('div', attrs={'class':'book-index'})
        for ul in div.findAll('ul', attrs={'class':'trailblock'}):
            for li in ul.findAll('li'):
                a = li.find(href=True)
                if not a:
                    continue
                title = self.tag_to_string(a)
                url = a['href']
                if not title or not url:
                    continue
                tt = li.find('div', attrs={'class':'trailtext'})
                if tt is not None:
                    for da in tt.findAll('a'): da.extract()
                    desc = self.tag_to_string(tt).strip()
                yield {
                        'title': title, 'url':url, 'description':desc,
                        'date' : strftime('%a, %d %b'),
                        }

    def parse_index(self):
        feeds = []
        for title, href in self.find_sections():
            feeds.append((title, list(self.find_articles(href))))
        return feeds