aboutsummaryrefslogtreecommitdiffhomepage
path: root/inc/3rdparty/site_config/standard/bbc.co.uk.txt
diff options
context:
space:
mode:
Diffstat (limited to 'inc/3rdparty/site_config/standard/bbc.co.uk.txt')
-rwxr-xr-x[-rw-r--r--]inc/3rdparty/site_config/standard/bbc.co.uk.txt74
1 files changed, 42 insertions, 32 deletions
diff --git a/inc/3rdparty/site_config/standard/bbc.co.uk.txt b/inc/3rdparty/site_config/standard/bbc.co.uk.txt
index 9c5c3419..ef1f491a 100644..100755
--- a/inc/3rdparty/site_config/standard/bbc.co.uk.txt
+++ b/inc/3rdparty/site_config/standard/bbc.co.uk.txt
@@ -1,32 +1,42 @@
1body: //div[@class="story-body"] 1body: //div[@class="story-body"]
2title: //h1[@class="story-header"] 2# for video entries
3date: //span[@class="story-date"]/span[@class='date'] 3body: //div[contains(@class, "videoInStory") or @id="meta-information"]
4 4title: //h1[@class="story-header"]
5# recipes, e.g. http://www.bbc.co.uk/food/recipes/mymincepies_71055 5date: //span[@class="story-date"]/span[@class='date']
6body: //div[contains(@class, 'hrecipe')]//div[@id='subcolumn-1'] 6# for sport site
7 7date: //meta[@name='DCTERMS.created']/@content
8#strip: //div[@class="story-feature narrow"] 8author: //div[@id='headline']//span[@class='byline-name']
9#strip: //div[@class="story-feature wide"] 9
10#strip: //div[@class="story-feature dslideshow-enclosure"] 10# recipes, e.g. http://www.bbc.co.uk/food/recipes/mymincepies_71055
11strip: //div[contains(@class, "story-feature")] 11body: //div[contains(@class, 'hrecipe')]//div[@id='subcolumn-1']
12strip: //span[@class="story-date"] 12
13#strip: //div[@class="caption body-narrow-width"] 13#strip: //div[@class="story-feature narrow"]
14strip: //div[@class="warning"]//p 14#strip: //div[@class="story-feature wide"]
15strip: //div[@id='page-bookmark-links-head'] 15#strip: //div[@class="story-feature dslideshow-enclosure"]
16strip: //object 16strip: //div[contains(@class, "story-feature")]
17strip: //div[contains(@class, "bbccom_advert_placeholder")] 17strip: //span[@class="story-date"]
18strip: //div[contains(@class, "embedded-hyper")] 18#strip: //div[@class="caption body-narrow-width"]
19strip: //div[contains(@class, 'market-data')] 19strip: //div[@class="warning"]//p
20strip: //a[contains(@class, 'hidden')] 20strip: //div[@id='page-bookmark-links-head']
21strip: //div[contains(@class, 'hypertabs')] 21strip: //object
22strip: //div[contains(@class, 'related')] 22strip: //div[contains(@class, "bbccom_advert_placeholder")]
23strip: //form[@id='comment-form'] 23strip: //div[contains(@class, "embedded-hyper")]
24strip: //div[contains(@class, 'comment-introduction')] 24strip: //div[contains(@class, 'market-data')]
25 25strip: //a[contains(@class, 'hidden')]
26replace_string(<noscript>): <div> 26strip: //div[contains(@class, 'hypertabs')]
27replace_string(</noscript>): </div> 27strip: //div[contains(@class, 'related')]
28 28strip: //form[@id='comment-form']
29prune: no 29strip: //div[contains(@class, 'comment-introduction')]
30 30strip: //div[contains(@class, 'share-tools')]
31dissolve: //h2 31strip: //div[@id='also-related-links']
32test_url: http://www.bbc.co.uk/news/business-15060862 \ No newline at end of file 32
33replace_string(<noscript>): <div>
34replace_string(</noscript>): </div>
35
36prune: no
37
38dissolve: //h2
39test_url: http://www.bbc.co.uk/sport/0/football/23224017
40test_url: http://www.bbc.co.uk/news/business-15060862
41# video entry
42test_url: http://www.bbc.co.uk/news/world-asia-22056933 \ No newline at end of file