diff options
| -rw-r--r-- | bbc.co.uk.txt | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/bbc.co.uk.txt b/bbc.co.uk.txt index a6f0b6b..ef1f491 100644 --- a/bbc.co.uk.txt +++ b/bbc.co.uk.txt @@ -3,6 +3,9 @@ body: //div[@class="story-body"] 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'] @@ -24,6 +27,8 @@ 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'] replace_string(<noscript>): <div> replace_string(</noscript>): </div> @@ -31,6 +36,7 @@ replace_string(</noscript>): </div> prune: no dissolve: //h2 +test_url: http://www.bbc.co.uk/sport/0/football/23224017 test_url: http://www.bbc.co.uk/news/business-15060862 # video entry test_url: http://www.bbc.co.uk/news/world-asia-22056933
\ No newline at end of file |