calibre/recipes/india_today.recipe

77 lines
2.7 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
class IndiaToday(BasicNewsRecipe):
title = 'India Today'
__author__ = 'Kovid Goyal'
language = 'en_IN'
timefmt = ' [%d %m, %Y]'
oldest_article = 700
max_articles_per_feed = 10
no_stylesheets = True
remove_tags_before = dict(id='content_story_title')
remove_tags_after = dict(id='rightblockdiv')
remove_tags = [dict(id=['rightblockdiv', 'share_links'])]
extra_css = '#content_story_title { font-size: 170%; font-weight: bold;}'
conversion_options = { 'linearize_tables': True }
def it_get_index(self):
soup = self.index_to_soup('http://indiatoday.intoday.in/site/archive')
a = soup.find('a', href=lambda x: x and 'issueId=' in x)
url = 'http://indiatoday.intoday.in/site/'+a.get('href')
img = a.find('img')
self.cover_url = img.get('src')
return self.index_to_soup(url)
def parse_index(self):
soup = self.it_get_index()
feeds, current_section, current_articles = [], None, []
for x in soup.findAll(name=['h1', 'a']):
if x.name == 'h1':
if current_section and current_articles:
feeds.append((current_section, current_articles))
current_section = self.tag_to_string(x)
current_articles = []
self.log('\tFound section:', current_section)
elif x.name == 'a' and 'Story' in x.get('href', ''):
title = self.tag_to_string(x)
url = x.get('href')
url = url.replace(' ', '%20')
if not url.startswith('/'):
url = 'http://indiatoday.intoday.in/site/' + url
if title and url:
url += '?complete=1'
self.log('\tFound article:', title)
self.log('\t\t', url)
desc = ''
h3 = x.parent.findNextSibling('h3')
if h3 is not None:
desc = 'By ' + self.tag_to_string(h3)
h4 = h3.findNextSibling('h4')
if h4 is not None:
desc = self.tag_to_string(h4) + ' ' + desc
if desc:
self.log('\t\t', desc)
current_articles.append({'title':title, 'description':desc,
'url':url, 'date':''})
if current_section and current_articles:
feeds.append((current_section, current_articles))
return feeds
def postprocess_html(self, soup, first):
a = soup.find(text='Print')
if a is not None:
tr = a.findParent('tr')
if tr is not None:
tr.extract()
return soup