From 87c091f668c7fb574eec5337fd1c6613ea7bffaa Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Sun, 7 Apr 2013 14:04:32 +0200 Subject: extract image and text for BBC video entries --- bbc.co.uk.txt | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/bbc.co.uk.txt b/bbc.co.uk.txt index a855ceb..a6f0b6b 100644 --- a/bbc.co.uk.txt +++ b/bbc.co.uk.txt @@ -1,4 +1,6 @@ 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'] @@ -29,4 +31,6 @@ replace_string(): prune: no dissolve: //h2 -test_url: http://www.bbc.co.uk/news/business-15060862 \ No newline at end of file +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 -- cgit v1.3.1