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

Richmond Times-Dispatch by jde

Browse Source
This commit is contained in:
Kovid Goyal 2012-04-27 07:36:53 +05:30
parent 332f40bbd1
commit e8fc70a2f2
1 changed files with 58 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
recipes/richmond_times_dispatch.recipe Normal file
View File

@ -0,0 +1,58 @@
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1308591763(BasicNewsRecipe):
title = u'Richmond Times-Dispatch'
description = 'News from Richmond, Virginia'
language = 'en'
__author__ = 'jde'
oldest_article = 3 #days
max_articles_per_feed = 25
summary_length = 150
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
encoding = 'utf8'
publisher = 'Richmond Times-Dispatch'
category = 'news, Virginia, world'
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: '')]
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
,'linearize_tables': True
}
remove_attributes = ['width','height']
remove_tags_before = dict(name='h1', attrs={'id':'story_headline'})
remove_tags_after = dict(name='class', attrs={'id':'content_fbrecommend'})
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'id':['topslider', 'top_links', 'top_links_center', 'top_links_right', 'mast', 'mainnav', 'search', 'searchbar_box', 'dateline', 'breadcrumb']}),
dict(name='div', attrs={'id':['sectionheader', 'comments_list', 'comment_form', 'sr_b', 'mg_ft', 'bottomad', 'mgproperties', 'copyright', 'bottomnow']}),
dict(name='div', attrs={'id':['comments_left']}),
dict(name='div', attrs={'class':['related_content', 'article_comments', 'article_foot', 'content_fbrecommend']}),
dict(name='div', attrs={'class':['bottom_social addthis_toolbox', 'featurebox', 'article_bottom']}),
dict(name='ul', attrs={'class':['jd_menu']})
]
feeds = [
(u'News', u'http://www2.timesdispatch.com/list/feed/rss/news-archive/'),
(u'Breaking News', u'http://www2.timesdispatch.com/list/feed/rss/breaking-news/'),
(u'National News', u'http://www2.timesdispatch.com/list/feed/rss/national-news/'),
(u'Local News', u'http://www2.timesdispatch.com/list/feed/rss/local-news/'),
(u'Business', u'http://www2.timesdispatch.com/list/feed/rss/business/'),
(u'Local Business', u'http://www2.timesdispatch.com/list/feed/rss/local-business/'),
(u'Politics', u'http://www2.timesdispatch.com/list/feed/rss/politics/'),
(u'Virginia Politics', u'http://www2.timesdispatch.com/list/feed/rss/virginia-politics/'),
(u'Editorials', u'http://www2.timesdispatch.com/list/feed/rss/editorial-desk/'),
(u'Columnists and Blogs', u'http://www2.timesdispatch.com/list/feed/rss/news-columnists-blogs//'),
(u'Opinion Columnists', u'http://www2.timesdispatch.com/list/feed/rss/opinion-editorial-columnists/'),
(u'Letters to the Editor', u'http://www2.timesdispatch.com/list/feed/rss/opinion-letters/'),
(u'Traffic', u'http://www2.timesdispatch.com/list/feed/rss/traffic/'),
]