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 The Hindu

Browse Source 
Fixes #1643752 [not able to fetch news from "the Hindu"](https://bugs.launchpad.net/calibre/+bug/1643752)
This commit is contained in:
Kovid Goyal 2016-11-22 21:18:41 +05:30
parent fcc685661d
commit 9a8447961e
1 changed files with 26 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
recipes/hindu.recipe
View File

@ -16,12 +16,31 @@ class TheHindu(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
auto_cleanup = True auto_cleanup = True
ignore_duplicate_articles = {'title', 'url'}
extra_css = '.photo-caption { font-size: smaller }' extra_css = '.photo-caption { font-size: smaller }'
def articles_from_soup(self, soup):
ans = []
div = soup.find('section', attrs={'id': 'section_1'})
if div is None:
return ans
ul = div.find('ul', attrs={'class': 'archive-list'})
if ul is not None:
for x in ul.findAll(['a']):
title = self.tag_to_string(x)
url = x.get('href', False)
if not url or not title:
continue
self.log('\t\tFound article:', title)
self.log('\t\t\t', url)
ans.append({'title': title, 'url': url,
'description': '', 'date': ''})
return ans
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('http://www.thehindu.com/todays-paper/') soup = self.index_to_soup('http://www.thehindu.com/todays-paper/')
nav_div = soup.find(id='tpnav-bar') nav_div = soup.find(id='subnav-tpbar-latest')
section_list = [] section_list = []
# Finding all the section titles that are acceptable # Finding all the section titles that are acceptable
@ -29,34 +48,18 @@ class TheHindu(BasicNewsRecipe):
if self.is_accepted_entry(x): if self.is_accepted_entry(x):
section_list.append( section_list.append(
(string.capwords(self.tag_to_string(x)), x['href'])) (string.capwords(self.tag_to_string(x)), x['href']))
self.log('Found section:', 'Front page')
feeds = [('Front Page', self.articles_from_soup(soup))]
# For each section title, fetch the article urls # For each section title, fetch the article urls
feeds = []
for section in section_list: for section in section_list:
section_title = section[0] section_title = section[0]
section_url = section[1] section_url = section[1]
self.log('Found section:', section_title, section_url)
soup = self.index_to_soup(section_url) soup = self.index_to_soup(section_url)
current_articles = [] articles = self.articles_from_soup(soup)
if articles:
div = soup.find('div', attrs={'id': 'left-column'}) feeds.append((section_title, articles))
try:
soup.find('span', attrs={
'class': 'newsection-title'}).extract()
except AttributeError:
continue # empty section
soup.find('div', attrs={'id': 'tpnav-bar'}).extract()
for x in div.findAll(['a']):
title = self.tag_to_string(x)
url = x.get('href', False)
if not url or not title:
continue
self.log('\t\tFound article:', title)
self.log('\t\t\t', url)
current_articles.append({'title': title, 'url': url,
'description': '', 'date': ''})
feeds.append((section_title, current_articles))
return feeds return feeds