Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update The Economic Times India

Browse Source 
Merge branch 'master' of https://github.com/kannankarthik/calibre
This commit is contained in:
Kovid Goyal 2014-07-17 18:03:01 +05:30
commit 1ef1bcd9a9
1 changed files with 33 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
recipes/theeconomictimes_india.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2014, Karthik <hashkendistro@gmail.com>, Darko Miletic <darko.miletic at gmail.com>'
''' '''
economictimes.indiatimes.com economictimes.indiatimes.com
''' '''
@ -9,11 +9,11 @@ from calibre.web.feeds.news import BasicNewsRecipe
class TheEconomicTimes(BasicNewsRecipe): class TheEconomicTimes(BasicNewsRecipe):
title = 'The Economic Times India' title = 'The Economic Times India'
__author__ = 'Darko Miletic' __author__ = 'Karthik K, Darko Miletic'
description = 'Financial news from India' description = 'Financial news from India'
publisher = 'economictimes.indiatimes.com' publisher = 'economictimes.indiatimes.com'
category = 'news, finances, politics, India' category = 'news, finances, politics, India'
oldest_article = 2 oldest_article = 1
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
@ -24,31 +24,48 @@ class TheEconomicTimes(BasicNewsRecipe):
masthead_url = 'http://economictimes.indiatimes.com/photo/2676871.cms' masthead_url = 'http://economictimes.indiatimes.com/photo/2676871.cms'
extra_css = """ extra_css = """
body{font-family: Arial,Helvetica,sans-serif} body{font-family: Arial,Helvetica,sans-serif}
.foto_mg{font-size: 60%;
font-weight: 700;}
h1{font-size: 150%;}
div.dateformat{font-size: 60%}
div.storycontent{padding-top: 10px}
""" """
conversion_options = {'comment' : description,
conversion_options = { 'tags' : category,
'comment' : description 'publisher' : publisher,
, 'tags' : category 'language' : language
, 'publisher' : publisher }
, 'language' : language remove_tags_before = dict(name='h1')
} remove_tags_after = dict(name='div', attrs={'class':'spacebw'})
remove_attributes = ['xmlns']
feeds = [(u'Top Stories', u'http://economictimes.indiatimes.com/rssfeedstopstories.cms'),
(u'News', u'http://economictimes.indiatimes.com/News/rssfeeds/1715249553.cms'),
(u'Market', u'http://economictimes.indiatimes.com/Markets/markets/rssfeeds/1977021501.cms'),
(u'Personal Finance', u'http://economictimes.indiatimes.com/rssfeeds/837555174.cms'),
(u'Infotech', u'http://economictimes.indiatimes.com/Infotech/rssfeeds/13357270.cms'),
(u'Job', u'http://economictimes.indiatimes.com/Infotech/rssfeeds/107115.cms'),
(u'Opinion', u'http://economictimes.indiatimes.com/opinion/opinionshome/rssfeeds/897228639.cms'),
(u'Features', u'http://economictimes.indiatimes.com/Features/etfeatures/rssfeeds/1466318837.cms'),
(u'Environment', u'http://economictimes.indiatimes.com/rssfeeds/2647163.cms'),
(u'NRI', u'http://economictimes.indiatimes.com/rssfeeds/7771250.cms')]
remove_tags_before = dict(name='h1')
feeds = [(u'All articles', u'http://economictimes.indiatimes.com/rssfeedsdefault.cms')]
#Uses the mobile print version. For web print version use 'http://economictimes.indiatimes.com/articleshow/<article_id>?prtpage=1'
def print_version(self, url): def print_version(self, url):
rest, sep, art = url.rpartition('/articleshow/') rest, sep, article_id = url.rpartition('/articleshow/')
return 'http://m.economictimes.com/PDAET/articleshow/' + art return 'http://m.economictimes.com/PDAET/articleshow/' + article_id
return 'http://economictimes.indiatimes.com/articleshow/' + art + '?prtpage=1'
def get_article_url(self, article): def get_article_url(self, article):
rurl = article.get('guid', None) rurl = article.get('guid', None)
if (rurl.find('/quickieslist/') > 0) or (rurl.find('/quickiearticleshow/') > 0): if (rurl.find('/quickieslist/') > 0) or (rurl.find('/quickiearticleshow/') > 0):
return None return None
return rurl return rurl
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
return soup
def postprocess_html(self, soup, first_fetch):
return self.adeify_images(soup) return self.adeify_images(soup)