]>
Commit | Line | Data |
---|---|---|
1 | body: //div[@class="story-body"]\r | |
2 | title: //h1[@class="story-header"]\r | |
3 | date: //span[@class="story-date"]/span[@class='date']\r | |
4 | \r | |
5 | # recipes, e.g. http://www.bbc.co.uk/food/recipes/mymincepies_71055\r | |
6 | body: //div[contains(@class, 'hrecipe')]//div[@id='subcolumn-1']\r | |
7 | \r | |
8 | #strip: //div[@class="story-feature narrow"]\r | |
9 | #strip: //div[@class="story-feature wide"]\r | |
10 | #strip: //div[@class="story-feature dslideshow-enclosure"]\r | |
11 | strip: //div[contains(@class, "story-feature")]\r | |
12 | strip: //span[@class="story-date"]\r | |
13 | #strip: //div[@class="caption body-narrow-width"]\r | |
14 | strip: //div[@class="warning"]//p\r | |
15 | strip: //div[@id='page-bookmark-links-head']\r | |
16 | strip: //object\r | |
17 | strip: //div[contains(@class, "bbccom_advert_placeholder")]\r | |
18 | strip: //div[contains(@class, "embedded-hyper")]\r | |
19 | strip: //div[contains(@class, 'market-data')]\r | |
20 | strip: //a[contains(@class, 'hidden')]\r | |
21 | strip: //div[contains(@class, 'hypertabs')]\r | |
22 | strip: //div[contains(@class, 'related')]\r | |
23 | strip: //form[@id='comment-form']\r | |
24 | strip: //div[contains(@class, 'comment-introduction')]\r | |
25 | \r | |
26 | replace_string(<noscript>): <div>\r | |
27 | replace_string(</noscript>): </div>\r | |
28 | \r | |
29 | prune: no\r | |
30 | \r | |
31 | dissolve: //h2\r | |
32 | test_url: http://www.bbc.co.uk/news/business-15060862 |