Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-11 09:13:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update The Hindu

Browse Source
This commit is contained in:
Kovid Goyal 2013-03-25 15:25:29 +05:30
parent 4e655fa8cc
commit c2bc85a3ad
1 changed files with 28 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
recipes/hindu.recipe
View File

@ -2,7 +2,6 @@ from __future__ import with_statement
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
import time
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class TheHindu(BasicNewsRecipe): class TheHindu(BasicNewsRecipe):
@ -14,44 +13,42 @@ class TheHindu(BasicNewsRecipe):
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
keep_only_tags = [dict(id='content')] auto_cleanup = True
remove_tags = [dict(attrs={'class':['article-links', 'breadcr']}),
dict(id=['email-section', 'right-column', 'printfooter', 'topover',
'slidebox', 'th_footer'])]
extra_css = '.photo-caption { font-size: smaller }' extra_css = '.photo-caption { font-size: smaller }'
def preprocess_raw_html(self, raw, url):
return raw.replace('<body><p>', '<p>').replace('</p></body>', '</p>')
def postprocess_html(self, soup, first_fetch):
for t in soup.findAll(['table', 'tr', 'td','center']):
t.name = 'div'
return soup
def parse_index(self): def parse_index(self):
today = time.strftime('%Y-%m-%d') soup = self.index_to_soup('http://www.thehindu.com/todays-paper/')
soup = self.index_to_soup( div = soup.find('div', attrs={'id':'left-column'})
'http://www.thehindu.com/todays-paper/tp-index/?date=' + today) soup.find(id='subnav-tpbar').extract()
div = soup.find(id='left-column')
feeds = []
current_section = None current_section = None
current_articles = [] current_articles = []
for x in div.findAll(['h3', 'div']): feeds = []
if current_section and x.get('class', '') == 'tpaper': for x in div.findAll(['a', 'span']):
a = x.find('a', href=True) if x.name == 'span' and x['class'] == 's-link':
if a is not None: # Section heading found
title = self.tag_to_string(a) if current_articles and current_section:
self.log('\tFound article:', title)
current_articles.append({'url':a['href']+'?css=print',
'title':title, 'date': '',
'description':''})
if x.name == 'h3':
if current_section and current_articles:
feeds.append((current_section, current_articles)) feeds.append((current_section, current_articles))
current_section = self.tag_to_string(x) current_section = self.tag_to_string(x)
self.log('Found section:', current_section)
current_articles = [] current_articles = []
self.log('\tFound section:', current_section)
elif x.name == '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':''})
if current_articles and current_section:
feeds.append((current_section, current_articles))
return feeds return feeds