Debian Codegraph @

recipes/toi.recipe

raw
1 __license__ = 'GPL v3'
2 __copyright__ = '2008-2014, Karthik <[email protected]>'
3 '''
4 timesofindia.indiatimes.com
5 '''
6
7
8 from calibre.web.feeds.news import BasicNewsRecipe
9
10
11 def classes(classes):
12 q = frozenset(classes.split(' '))
13 return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
14
15
16 class TheEconomicTimes(BasicNewsRecipe):
17 title = 'The Times of India'
18 __author__ = 'Karthik'
19 description = 'News from the Indian daily Times of India'
20 publisher = 'timesofindia.indiatimes.com'
21 category = 'news, finances, politics, sports, business, entertainment, India'
22 oldest_article = 1
23 max_articles_per_feed = 100
24 no_stylesheets = True
25 use_embedded_content = False
26 simultaneous_downloads = 1
27 encoding = 'utf-8'
28 language = 'en_IN'
29 publication_type = 'newspaper'
30 masthead_url = 'http://timesofindia.indiatimes.com/photo.cms?msid=2419189'
31 extra_css = '''
32 body{font-family: Arial,Helvetica,sans-serif}
33 .foto_mg{font-size: 60%;
34 font-weight: 700;}
35 h1{font-size: 150%;}
36 artdate{font-size: 60%}
37 artag{font-size: 60%}
38 div.storycontent{padding-top: 10px}
39 '''
40 conversion_options = {'comment': description, 'tags': category, 'publisher': publisher, 'language': language}
41 remove_tags_before = dict(name='h1')
42 remove_tags_after = dict(name='div', attrs={'class': 'storycontent'})
43 remove_attributes = ['xmlns', 'style']
44 remove_tags = [classes('readalso success_screen poll_withoutLogin hide')]
45
46 feeds = [
47 ('Recent Stories', 'http://timesofindia.indiatimes.com/rssfeeds/1221656.cms'),
48 ('India', 'http://timesofindia.indiatimes.com/rssfeeds/-2128936835.cms'),
49 ('World', 'http://timesofindia.indiatimes.com/rssfeeds/296589292.cms'),
50 ('Business', 'http://timesofindia.indiatimes.com/rssfeeds/1898055.cms'),
51 ('Cricket', 'http://timesofindia.indiatimes.com/rssfeeds/4719161.cms'),
52 ('Sports', 'http://timesofindia.indiatimes.com/rssfeeds/4719148.cms'),
53 ('Tech', 'http://timesofindia.indiatimes.com/rssfeeds/5880659.cms'),
54 ('Education', 'http://timesofindia.indiatimes.com/rssfeeds/913168846.cms'),
55 ('Science', 'http://timesofindia.indiatimes.com/rssfeeds/-2128672765.cms'),
56 ('Opinion', 'http://timesofindia.indiatimes.com/rssfeeds/784865811.cms'),
57 ('Entertainment', 'http://timesofindia.indiatimes.com/rssfeeds/1081479906.cms'),
58 ]
59
60 def print_version(self, url):
61 return url.replace('/articleshow/', '/articleshowprint/')
62 # For mobile version
63 # return 'http://m.timesofindia.com/PDAET/articleshow/' + article_id
64
65 def get_cover_url(self):
66 soup = self.index_to_soup('https://www.magzter.com/IN/Bennett-Coleman-and-Company-Limited/The-Times-of-India-Delhi/Newspaper/')
67 return soup.find('img', id=lambda s: s and 'mgd__lhd__cover' in s.split())['src']
68
69 def get_article_url(self, article):
70 rurl = article.get('guid', None)
71 if '/articleshow/' in rurl:
72 return rurl
73
74 def postprocess_html(self, soup, first_fetch):
75 return self.adeify_images(soup)