Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update General Knowledge Today

Browse Source 
Fixes #1457724 [Enhancement Request](https://bugs.launchpad.net/calibre/+bug/1457724)
This commit is contained in:
Kovid Goyal 2015-05-27 12:05:06 +05:30
parent f22af669e8
commit cdd376a4b4
1 changed files with 23 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
recipes/gkt.recipe
View File

@ -4,7 +4,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class Politics(BasicNewsRecipe): class Politics(BasicNewsRecipe):
title = u'General Knowledge Today' title = u'General Knowledge Today'
language = 'en_IN' language = 'en_IN'
__author__ = 'Kanika G' __author__ = 'Kovid Goyal'
oldest_article = 7 # days oldest_article = 7 # days
max_articles_per_feed = 20 max_articles_per_feed = 20
use_embedded_content = False use_embedded_content = False
@ -13,21 +13,26 @@ class Politics(BasicNewsRecipe):
no_javascript = True no_javascript = True
auto_cleanup = True auto_cleanup = True
def parse_gkt_section(self, url):
root = self.index_to_soup(url, as_tree=True)
for a in root.xpath('//h1[@class="post-title"]/a[@href]'):
title = self.tag_to_string(a).strip()
url = a.get('href')
if title and url:
self.log('\tFound article:', title, 'at', url)
yield {'title':title, 'url':url}
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('http://www.gktoday.in/') url = 'http://www.gktoday.in/'
root = self.index_to_soup(url, as_tree=True)
# Find TOC ans = []
toc = soup.find('div', attrs={'class':'entry clearfix'}) for h3 in root.xpath('//h3[@class="widget-title" and contains(text(), "Current Affairs Category")]'):
articles = [] for a in h3.getparent().xpath('descendant::li/a[@href]'):
for li in toc.findAll('li'): category = self.tag_to_string(a).strip()
a = li.find('a') url = a.get('href')
info = self.tag_to_string(a) self.log('Found section:', category)
url = a['href'] articles = list(self.parse_gkt_section(url)) + list(self.parse_gkt_section(url + '/page/2'))
desc = '' if articles:
self.log('Found article:', info) ans.append((category, articles))
self.log('\t', url) break
self.log('\t', desc) return ans
articles.append({'title':info, 'url':url, 'date':'',
'description':desc})
return [('Current Issue', articles)]