home *** CD-ROM | disk | FTP | other *** search
- from calibre.web.feeds.news import BasicNewsRecipe
-
- class ElUniversalImpresaRecipe(BasicNewsRecipe):
- __license__ = 'GPL v3'
- __author__ = 'kwetal'
- language = 'es'
- version = 1
-
- title = u'El Universal (Edici\u00F3n Impresa)'
- publisher = u'El Universal'
- category = u'News, Mexico'
- description = u'News from Mexico'
-
- remove_empty_feeds = True
- remove_javascript = True
-
- INDEX = 'http://www.eluniversal.com.mx'
-
- extra_css = '''
- body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
- '''
-
- conversion_options = {'comments': description, 'tags': category, 'language': 'en',
- 'publisher': publisher, 'linearize_tables': True}
-
- def parse_index(self):
- soup = self.index_to_soup('http://www.eluniversal.com.mx/edicion_impresa.html')
- index = []
-
- table = soup.find('table', attrs = {'width': '500'})
- articles = []
- for td in table.findAll(lambda tag: tag.name == 'td' and tag.has_key('class') and tag['class'] == 'arnegro12'):
- a = td.a
- a.extract()
- title = self.tag_to_string(a)
- url = self.INDEX + a['href']
- description = self.tag_to_string(td)
- articles.append({'title': title, 'date': None, 'url': url, 'description' : description})
-
- index.append(('Primera Plana', articles))
-
- for td in table.findAll(lambda tag: tag.name == 'td' and len(tag.attrs) == 0):
- articles = []
- feedTitle = None
- for a in td.findAll('a'):
- if not feedTitle:
- feedTitle = self.tag_to_string(a)
- continue
-
- title = self.tag_to_string(a)
-
- url = self.INDEX + a['href']
- articles.append({'title': title, 'date': None, 'url': url, 'description': ''})
-
- index.append((feedTitle, articles))
-
- return index
-
- def print_version(self, url):
- if url.find('wcarton') >= 0:
- return None
-
- main, sep, id = url.rpartition('/')
-
- return main + '/vi_' + id
-
- def preprocess_html(self, soup):
- table = soup.find('table')
- table.extract()
-
- for p in soup.findAll('p'):
- if self.tag_to_string(p).strip() == '':
- p.extract()
-
- tag = soup.find('font', attrs = {'color': '#0F046A'})
- if tag:
- for attr in ['color', 'face', 'helvetica,', 'sans-serif', 'size']:
- if tag.has_key(attr):
- del tag[attr]
- tag.name = 'h1'
-
- return soup
-