blob: bad77654b02c29981afcbb54079f77d60ab4096e (
plain) (
tree)
|
|
body: //div[@class="story-body"]
# for video entries
body: //div[contains(@class, "videoInStory") or @id="meta-information"]
title: //h1[@class="story-header"]
date: //span[@class="story-date"]/span[@class='date']
# for sport site
date: //meta[@name='DCTERMS.created']/@content
author: //div[@id='headline']//span[@class='byline-name']
# recipes, e.g. http://www.bbc.co.uk/food/recipes/mymincepies_71055
body: //div[contains(@class, 'hrecipe')]//div[@id='subcolumn-1']
#strip: //div[@class="story-feature narrow"]
#strip: //div[@class="story-feature wide"]
#strip: //div[@class="story-feature dslideshow-enclosure"]
strip: //div[contains(@class, "story-feature") and not(contains(@class, 'full-width'))]
strip: //span[@class="story-date"]
#strip: //div[@class="caption body-narrow-width"]
strip: //div[@class="warning"]//p
strip: //div[@id='page-bookmark-links-head']
strip: //object
strip: //div[contains(@class, "bbccom_advert_placeholder")]
strip: //div[contains(@class, "embedded-hyper")]
strip: //div[contains(@class, 'market-data')]
strip: //a[contains(@class, 'hidden')]
strip: //div[contains(@class, 'hypertabs')]
strip: //div[contains(@class, 'related')]
strip: //form[@id='comment-form']
strip: //div[contains(@class, 'comment-introduction')]
strip: //div[contains(@class, 'share-tools')]
strip: //div[@id='also-related-links']
strip_id_or_class: share-help
strip_id_or_class: comments_module
replace_string(<noscript>): <div>
replace_string(</noscript>): </div>
tidy: no
prune: no
dissolve: //h2
test_url: http://www.bbc.co.uk/sport/0/football/23224017
test_contains: Swansea City have completed the club-record signing
test_url: http://www.bbc.co.uk/news/business-15060862
test_contains: Europe's leaders are meeting again to try to solve
# news feed
test_url: http://feeds.bbci.co.uk/news/rss.xml
# sports feed
test_url: http://feeds.bbci.co.uk/sport/0/football/rss.xml?edition=int
# video entry
test_url: http://www.bbc.co.uk/news/world-asia-22056933
|
