Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Frontline

Browse Source
This commit is contained in:
Kovid Goyal 2013-06-22 07:59:40 +05:30
parent bf1055abd9
commit 6a134427c8
1 changed files with 25 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
recipes/frontlineonnet.recipe
View File

@ -46,35 +46,34 @@ class Frontlineonnet(BasicNewsRecipe):
keep_only_tags= [ keep_only_tags= [
dict(name='div', attrs={'id':'content'}) 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 parse_index(self): def parse_index(self):
articles = [] articles = []
current_section = None
feeds = []
soup = self.index_to_soup(self.INDEX) soup = self.index_to_soup(self.INDEX)
for feed_link in soup.findAll('div', id='headseccol'): for h3 in soup.findAll('h3'):
a = feed_link.find('a', href=True) if h3.get('class', None) == 'artListSec':
title = self.tag_to_string(a) if articles:
url = a['href'] feeds.append((current_section, articles))
articles.append({ articles = []
'title' :title current_section = self.tag_to_string(h3).strip()
,'date' :'' self.log(current_section)
,'url' :url elif h3.get('id', None) in {'headseccol', 'headsec'}:
,'description':'' a = h3.find('a', href=True)
}) if a is not None:
return [('Frontline', articles)] title = self.tag_to_string(a)
url = a['href']
articles.append({
'title' :title
,'date' :''
,'url' :url
,'description':''
})
self.log('\t', title, url)
if articles:
feeds.append((current_section, articles))
return feeds
#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()