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 #1817256 [Unable to fetch "General Knowledge today"](https://bugs.launchpad.net/calibre/+bug/1817256)
This commit is contained in:
Kovid Goyal 2019-02-23 08:56:19 +05:30
parent 482b24e888
commit 306959fd4a
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
recipes/gkt.recipe
View File

@ -1,7 +1,7 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Politics(BasicNewsRecipe): class GKT(BasicNewsRecipe):
title = u'General Knowledge Today' title = u'General Knowledge Today'
language = 'en_IN' language = 'en_IN'
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal'
@ -12,8 +12,13 @@ class Politics(BasicNewsRecipe):
no_javascript = True no_javascript = True
auto_cleanup = True auto_cleanup = True
def parse_gkt_section(self, url): def parse_gkt_section(self, url, ignore_error=False):
root = self.index_to_soup(url, as_tree=True) try:
root = self.index_to_soup(url, as_tree=True)
except Exception:
if ignore_error:
return
raise
for a in root.xpath('//div[@class="post-content"]/h1/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')
@ -28,12 +33,12 @@ class Politics(BasicNewsRecipe):
h3 = root.xpath('//h3[@class="widget-title"]')[1] 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()
if 'PDF' in category: if 'PDF' in category or not category:
continue continue
url = a.get('href') url = a.get('href')
self.log('Found section:', category) self.log('Found section:', category)
articles = list(self.parse_gkt_section(url)) + \ articles = list(self.parse_gkt_section(url)) + \
list(self.parse_gkt_section(url + '/page/2')) list(self.parse_gkt_section(url + '/page/2', ignore_error=True))
if articles: if articles:
ans.append((category, articles)) ans.append((category, articles))
return ans return ans