Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Jakarta Post

Browse Source
This commit is contained in:
Kovid Goyal 2015-07-09 15:30:12 +05:30
parent 35f2cc5048
commit ce7c2fae68
1 changed files with 30 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
recipes/jakarta_post.recipe
View File

@ -13,10 +13,8 @@ from calibre.web.feeds.news import BasicNewsRecipe
class JakartaPost(BasicNewsRecipe): class JakartaPost(BasicNewsRecipe):
title = u'Jakarta Post' title = u'Jakarta Post'
masthead_url = 'http://www.thejakartapost.com/images/jakartapost_logo.jpg'
cover_url = 'http://www.thejakartapost.com/images/jakartapost_logo.jpg'
__author__ = u'Adrian Gunawan' __author__ = u'Kovid Goyal'
description = u'Indonesian Newspaper in English from Jakarta Post Online Edition' description = u'Indonesian Newspaper in English from Jakarta Post Online Edition'
category = 'breaking news, national, business, international, Indonesia' category = 'breaking news, national, business, international, Indonesia'
language = 'en_ID' language = 'en_ID'
@ -24,39 +22,40 @@ class JakartaPost(BasicNewsRecipe):
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False
no_javascript = True no_javascript = True
remove_empty_feeds = True remove_empty_feeds = True
auto_cleanup = True
timefmt = ' [%A, %d %B, %Y]' timefmt = ' [%A, %d %B, %Y]'
encoding = 'utf-8' encoding = 'utf-8'
ignore_duplicate_articles = {'title', 'url'}
extra_css = ''' keep_only_tags = [
h1{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:large;} dict(name='h1'),
.cT-storyDetails{font-family:Arial,Helvetica,sans-serif; color:#666666;font-size:x-small;} dict(attrs={'class':lambda x: x and 'byline' in x.split()}),
.articleBody{font-family:Arial,Helvetica,sans-serif; color:black;font-size:small;} dict(attrs={'class':lambda x: x and 'span-13' in x.split()}),
.cT-imageLandscape{font-family:Arial,Helvetica,sans-serif; color:#333333 ;font-size:x-small;} ]
.source{font-family:Arial,Helvetica,sans-serif; color:#333333 ;font-size:xx-small;} remove_tags_after = dict(attrs={'class':lambda x: x and 'span-12' in x.split()})
#content{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
.pageprint{font-family:Arial,Helvetica,sans-serif;font-size:small;}
#bylineDetails{font-family:Arial,Helvetica,sans-serif; color:#666666;font-size:x-small;}
.featurePic-wide{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
#idfeaturepic{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
h3{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
h2{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
h4{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
h5{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
body{font-family:Arial,Helvetica,sans-serif; font-size:x-small;}
'''
feeds = [ def parse_jp_section(self, url):
soup = self.index_to_soup(url)
for div in soup.findAll('div', attrs={'class':'story'}):
a = div.find('a', href=True)
url = a.get('href')
title = self.tag_to_string(a)
p = div.find('p')
desc = self.tag_to_string(p)
self.log('\t', title, ' at ', url)
yield {'title':title, 'url':url, 'description':desc}
(u'Breaking News', u'http://www.thejakartapost.com/breaking/feed'), def parse_index(self):
(u'National', u'http://www.thejakartapost.com/channel/national/feed'), ans = []
(u'Archipelago', u'http://www.thejakartapost.com/channel/archipelago/feed'), for sec in ('editors_choice channel/headlines channel/business channel/national channel/archipelago'
(u'Business', u'http://www.thejakartapost.com/channel/business/feed'), ' channel/jakarta channel/world channel/sports').split():
(u'Jakarta', u'http://www.thejakartapost.com/channel/jakarta/feed'), title = (sec.partition('/')[2] or sec).replace('_', ' ').capitalize()
(u'World', u'http://www.thejakartapost.com/channel/world/feed'), articles = list(self.parse_jp_section('http://www.thejakartapost.com/' + sec))
(u'Sports', u'http://www.thejakartapost.com/channel/sports/feed'), self.log('Found section:', title)
] if articles:
ans.append((title, articles))
if self.test and len(ans) >= self.test[0]:
break
return ans