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

Fix #790945 (Updated recipe for BBC News (fast))

Browse Source
This commit is contained in:
Kovid Goyal 2011-05-31 17:46:12 -06:00
parent db0c246240
commit 7fe53cd96b
1 changed files with 52 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

72
recipes/bbc_fast.recipe
View File

@ -1,27 +1,30 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2010 - 2011, Darko Miletic <darko.miletic at gmail.com>'
'''
news.bbc.co.uk
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class BBC(BasicNewsRecipe):
title = 'BBC News (fast)'
__author__ = 'Darko Miletic, Starson17'
description = 'News from UK. A much faster version that does not download pictures'
description = 'Visit BBC News for up-to-the-minute news, breaking news, video, audio and feature stories. BBC News provides trusted World and UK news as well as local and regional perspectives. Also entertainment, business, science, technology and health news.'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
#delay = 1
use_embedded_content = False
encoding = 'utf8'
publisher = 'BBC'
category = 'news, UK, world'
language = 'en_GB'
publication_type = 'newsportal'
extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif } .introduction{font-weight: bold} .story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small} .story-feature h2{text-align: center; text-transform: uppercase} '
preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
masthead_url = 'http://news.bbcimg.co.uk/img/1_0_1/cream/hi/news/news-blocks.gif'
extra_css = """
body{ font-family: Verdana,Helvetica,Arial,sans-serif }
.introduction{font-weight: bold}
.story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small}
.story-feature h2{text-align: center; text-transform: uppercase}
"""
conversion_options = {
'comments' : description
,'tags' : category
@ -33,29 +36,52 @@ class BBC(BasicNewsRecipe):
keep_only_tags = [
dict(name='div', attrs={'class':['layout-block-a layout-block']})
,dict(attrs={'class':['story-body','storybody']})
,dict(attrs={'id':['meta-information','story-body']})
]
remove_tags = [
dict(name='div', attrs={'class':['story-feature related narrow', 'share-help', 'embedded-hyper', \
'story-feature wide ', 'story-feature narrow']})
, dict(name=['img'])
dict(name='div', attrs={'class':['story-feature related narrow', \
'share-help', 'embedded-hyper', \
'story-feature wide ', \
'story-feature narrow', \
'hidden','story-actions', \
'embedded-hyper']})
,dict(name=['img','meta','link','object','embed','iframe','base'])
,dict(attrs={'class':['hidden','videoInStoryC']})
,dict(attrs={'id':['bbccom_sponsor_section','toggle-controls', \
'toggle-images','toggle-title']})
]
remove_attributes = ['width','height']
remove_attributes = ['width','height','xmlns:og','lang','clear']
feeds = [
('News Front Page', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/front_page/rss.xml'),
('Science/Nature', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/science/nature/rss.xml'),
('Technology', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/technology/rss.xml'),
('Entertainment', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/entertainment/rss.xml'),
('Magazine', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/uk_news/magazine/rss.xml'),
('Business', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/business/rss.xml'),
('Health', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/health/rss.xml'),
('Americas', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/americas/rss.xml'),
('Europe', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/europe/rss.xml'),
('South Asia', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/south_asia/rss.xml'),
('UK', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/uk_news/rss.xml'),
('Asia-Pacific', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/asia-pacific/rss.xml'),
('Africa', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/africa/rss.xml'),
('Top Stories' , 'http://feeds.bbci.co.uk/news/rss.xml' ),
('Science/Environment', 'http://feeds.bbci.co.uk/news/science_and_environment/rss.xml'),
('Technology' , 'http://feeds.bbci.co.uk/news/technology/rss.xml' ),
('Entertainment/Arts' , 'http://feeds.bbci.co.uk/news/entertainment_and_arts/rss.xml' ),
('Magazine' , 'http://feeds.bbci.co.uk/news/magazine/rss.xml' ),
('Business' , 'http://feeds.bbci.co.uk/news/business/rss.xml' ),
('Politics' , 'http://feeds.bbci.co.uk/news/politics/rss.xml' ),
('Health' , 'http://feeds.bbci.co.uk/news/health/rss.xml' ),
('US&Canada' , 'http://feeds.bbci.co.uk/news/world/us_and_canada/rss.xml' ),
('Latin America' , 'http://feeds.bbci.co.uk/news/world/latin_america/rss.xml' ),
('Europe' , 'http://feeds.bbci.co.uk/news/world/europe/rss.xml' ),
('South Asia' , 'http://feeds.bbci.co.uk/news/world/south_asia/rss.xml' ),
('England' , 'http://feeds.bbci.co.uk/news/england/rss.xml' ),
('Asia-Pacific' , 'http://feeds.bbci.co.uk/news/world/asia_pacific/rss.xml' ),
('Africa' , 'http://feeds.bbci.co.uk/news/world/africa/rss.xml' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('left'):
item.name='span'
for item in soup.findAll('a'):
if item.string is not None:
str = item.string
item.replaceWith(str)
else:
str = self.tag_to_string(item)
item.replaceWith(str)
return soup