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 Frontline

Browse Source
This commit is contained in:
Kovid Goyal 2013-06-12 17:58:48 +05:30
parent c07db5e194
commit 2f8a25654b
1 changed files with 26 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
recipes/frontlineonnet.recipe
View File

@ -1,3 +1,4 @@
__license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
'''
@ -5,7 +6,6 @@ frontlineonnet.com
'''
import re
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Frontlineonnet(BasicNewsRecipe):
@ -18,7 +18,7 @@ class Frontlineonnet(BasicNewsRecipe):
delay = 1
INDEX = 'http://frontlineonnet.com/'
use_embedded_content = False
encoding = 'cp1252'
encoding = 'utf-8'
language = 'en_IN'
publication_type = 'magazine'
masthead_url = 'http://frontlineonnet.com/images/newfline.jpg'
@ -45,37 +45,36 @@ class Frontlineonnet(BasicNewsRecipe):
]
keep_only_tags= [
dict(name='font', attrs={'class':'storyhead'})
,dict(attrs={'class':'byline'})
dict(name='div', attrs={'id':'content'})
#,dict(attrs={'class':'byline'})
]
remove_attributes=['size','noshade','border']
#remove_attributes=['size','noshade','border']
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
return soup
#def preprocess_html(self, soup):
#for item in soup.findAll(style=True):
#del item['style']
#for item in soup.findAll('img'):
#if not item.has_key('alt'):
#item['alt'] = 'image'
#return soup
def parse_index(self):
articles = []
soup = self.index_to_soup(self.INDEX)
for feed_link in soup.findAll('a',href=True):
if feed_link['href'].startswith('stories/'):
url = self.INDEX + feed_link['href']
title = self.tag_to_string(feed_link)
date = strftime(self.timefmt)
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':''
})
for feed_link in soup.findAll('div', id='headseccol'):
a = feed_link.find('a', href=True)
title = self.tag_to_string(a)
url = a['href']
articles.append({
'title' :title
,'date' :''
,'url' :url
,'description':''
})
return [('Frontline', articles)]
def print_version(self, url):
return "http://www.hinduonnet.com/thehindu/thscrip/print.pl?prd=fline&file=" + url.rpartition('/')[2]
#def print_version(self, url):
#return "http://www.hinduonnet.com/thehindu/thscrip/print.pl?prd=fline&file=" + url.rpartition('/')[2]
def image_url_processor(self, baseurl, url):
return url.replace('../images/', self.INDEX + 'images/').strip()
#def image_url_processor(self, baseurl, url):
#return url.replace('../images/', self.INDEX + 'images/').strip()