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
This commit is contained in:
Kovid Goyal 2018-10-20 10:19:39 +05:30
parent 5f8eb3ce73
commit 550a633a3e
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
recipes/gkt.recipe
View File

@ -7,7 +7,6 @@ class Politics(BasicNewsRecipe):
__author__ = 'Kovid Goyal' __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
no_stylesheets = True no_stylesheets = True
no_javascript = True no_javascript = True
@ -15,7 +14,7 @@ class Politics(BasicNewsRecipe):
def parse_gkt_section(self, url): def parse_gkt_section(self, url):
root = self.index_to_soup(url, as_tree=True) root = self.index_to_soup(url, as_tree=True)
for a in root.xpath('//h1[@class="post-title"]/a[@href]'): for a in root.xpath('//div[@class="post-content"]/h1/a[@href]'):
title = self.tag_to_string(a).strip() title = self.tag_to_string(a).strip()
url = a.get('href') url = a.get('href')
if title and url: if title and url:
@ -26,14 +25,15 @@ class Politics(BasicNewsRecipe):
url = 'http://www.gktoday.in/' url = 'http://www.gktoday.in/'
root = self.index_to_soup(url, as_tree=True) root = self.index_to_soup(url, as_tree=True)
ans = [] ans = []
for h3 in root.xpath('//h3[@class="widget-title" and contains(text(), "Current Affairs Category")]'): h3 = root.xpath('//h3[@class="widget-title"]')[1]
for a in h3.getparent().xpath('descendant::li/a[@href]'): for a in h3.getparent().xpath('descendant::li/a[@href]'):
category = self.tag_to_string(a).strip() category = self.tag_to_string(a).strip()
url = a.get('href') if 'PDF' in category:
self.log('Found section:', category) continue
articles = list(self.parse_gkt_section(url)) + \ url = a.get('href')
list(self.parse_gkt_section(url + '/page/2')) self.log('Found section:', category)
if articles: articles = list(self.parse_gkt_section(url)) + \
ans.append((category, articles)) list(self.parse_gkt_section(url + '/page/2'))
break if articles:
ans.append((category, articles))
return ans return ans