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 Associated Press

Browse Source
This commit is contained in:
Kovid Goyal 2014-02-13 19:00:49 +05:30
parent 9a80329141
commit f2634f5065
1 changed files with 25 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
recipes/ap.recipe
View File

@ -1,4 +1,3 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
@ -6,45 +5,37 @@ class AssociatedPress(BasicNewsRecipe):
title = u'Associated Press'
description = 'Global news'
__author__ = 'Kovid Goyal and Sujata Raman'
__author__ = 'Krittika Goyal'
use_embedded_content = False
language = 'en'
no_stylesheets = True
auto_cleanup = True
# auto_cleanup_keep = '//td[@class="ap-smallphoto-td-image"]'
max_articles_per_feed = 15
auto_cleanup_keep = '//tr[@class="ap-story-td"]'
def parse_index(self):
feeds = []
fronts = ('HOME', 'US', 'WORLD', 'BUSINESS', 'TECHNOLOGY', 'SPORTS', 'ENTERTAINMENT', 'HEALTH', 'SCIENCE', 'POLITICS')
for front in fronts:
feeds.append([front.capitalize(), self.parse_section(front)])
feeds[0][0] = 'Top Stories'
return feeds
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
[
(r'<span class="entry-content">', lambda match : '<div class="entry-content">'),
]
]
def parse_section(self, front):
self.log('Processing section:', front)
soup = self.index_to_soup('http://hosted.ap.org/dynamic/fronts/%s?SITE=AP' % front)
articles = []
for x in soup.findAll('p', attrs={'class':['ap-newsbriefitem-p', 'ap-topheadlineitem-p']}):
a = x.find('a', href=True)
title = self.tag_to_string(a)
url = "http://hosted.ap.org" + a['href']
p = x.find(attrs={'class':'topheadlinebody'})
desc = ''
if p is not None:
desc = self.tag_to_string(p)
self.log('\tFound article:', title, '\n\t\t', desc)
articles.append({'title':title, 'url':url})
#keep_only_tags = [ dict(name='table', attrs={'class':['ap-story-table hnews hentry item']}),
##dict(name='div', attrs={'class':['entry-content']}),
#]
#remove_tags = [dict(name='td', attrs={'class':['ap-mediabox-td']}),
#dict(name='table', attrs={'class':['ap-htmltable-table', 'ap-htmltable-table', 'ap-mediabox-table']}),
##dict(name='td', attrs={'bgcolor':['#333333']}),
#]
extra_css = '''
.headline{font-family:Verdana,Arial,Helvetica,sans-serif;font-weight:bold;}
.bline{color:#003366;}
body{font-family:Arial,Helvetica,sans-serif;}
'''
feeds = [
('AP Headlines', 'http://hosted.ap.org/lineups/TOPHEADS-rss_2.0.xml?SITE=ORAST&SECTION=HOME'),
('AP US News', 'http://hosted.ap.org/lineups/USHEADS-rss_2.0.xml?SITE=CAVIC&SECTION=HOME'),
('AP World News', 'http://hosted.ap.org/lineups/WORLDHEADS-rss_2.0.xml?SITE=SCAND&SECTION=HOME'),
('AP Political News', 'http://hosted.ap.org/lineups/POLITICSHEADS-rss_2.0.xml?SITE=ORMED&SECTION=HOME'),
('AP Washington State News', 'http://hosted.ap.org/lineups/WASHINGTONHEADS-rss_2.0.xml?SITE=NYPLA&SECTION=HOME'),
('AP Technology News', 'http://hosted.ap.org/lineups/TECHHEADS-rss_2.0.xml?SITE=CTNHR&SECTION=HOME'),
('AP Health News', 'http://hosted.ap.org/lineups/HEALTHHEADS-rss_2.0.xml?SITE=FLDAY&SECTION=HOME'),
('AP Science News', 'http://hosted.ap.org/lineups/SCIENCEHEADS-rss_2.0.xml?SITE=OHCIN&SECTION=HOME'),
('AP Strange News', 'http://hosted.ap.org/lineups/STRANGEHEADS-rss_2.0.xml?SITE=WCNC&SECTION=HOME'),
]
self.log('\n\n')
return articles