Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update The Hindu

Browse Source
This commit is contained in:
Kovid Goyal 2014-10-01 14:22:59 +05:30
parent bcba3d7e8d
commit 01847b8983
1 changed files with 11 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
recipes/hindu.recipe
View File

@ -5,12 +5,13 @@ __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
import string import string
class TheHindu(BasicNewsRecipe): class TheHindu(BasicNewsRecipe):
title = u'The Hindu' title = u'The Hindu'
language = 'en_IN' language = 'en_IN'
oldest_article = 1 oldest_article = 1
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal'
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
@ -26,7 +27,8 @@ class TheHindu(BasicNewsRecipe):
# Finding all the section titles that are acceptable # Finding all the section titles that are acceptable
for x in nav_div.findAll(['a']): for x in nav_div.findAll(['a']):
if self.is_accepted_entry(x): if self.is_accepted_entry(x):
section_list.append((string.capwords(self.tag_to_string(x)), x['href'])) section_list.append(
(string.capwords(self.tag_to_string(x)), x['href']))
# For each section title, fetch the article urls # For each section title, fetch the article urls
feeds = [] feeds = []
@ -36,9 +38,9 @@ class TheHindu(BasicNewsRecipe):
soup = self.index_to_soup(section_url) soup = self.index_to_soup(section_url)
current_articles = [] current_articles = []
div = soup.find('div', attrs={'id':'left-column'}) div = soup.find('div', attrs={'id': 'left-column'})
soup.find('div', attrs={'class':'newsection-title'}).extract() soup.find('span', attrs={'class': 'newsection-title'}).extract()
soup.find('div', attrs={'id':'tpnav-bar'}).extract() soup.find('div', attrs={'id': 'tpnav-bar'}).extract()
for x in div.findAll(['a']): for x in div.findAll(['a']):
title = self.tag_to_string(x) title = self.tag_to_string(x)
@ -47,8 +49,8 @@ class TheHindu(BasicNewsRecipe):
continue continue
self.log('\t\tFound article:', title) self.log('\t\tFound article:', title)
self.log('\t\t\t', url) self.log('\t\t\t', url)
current_articles.append({'title': title, 'url':url, current_articles.append({'title': title, 'url': url,
'description':'', 'date':''}) 'description': '', 'date': ''})
feeds.append((section_title, current_articles)) feeds.append((section_title, current_articles))