From 54122546fa87d4e570e5a90ba0953284763f1d2d Mon Sep 17 00:00:00 2001 From: Mateus Dalto Piveta Date: Mon, 16 Jun 2014 12:12:34 -0300 Subject: Updated businessinsider.com --- businessinsider.com.txt | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'businessinsider.com.txt') diff --git a/businessinsider.com.txt b/businessinsider.com.txt index f847687..e66aeaa 100644 --- a/businessinsider.com.txt +++ b/businessinsider.com.txt @@ -1,12 +1,14 @@ title://div[@class="sl-layout-post"]/h1 -body: //div[contains(@class, 'post-content') or contains(@class, 'KonaBody')] +body: //div[contains(@class, 'post-content') or contains(@class, 'slide-module') or contains(@class, 'KonaBody')] strip: //div[contains(@class, "post-sidebar")] strip: //div[@id='related-links'] author://div[@class="byline"]/a date://div[@class="byline"]/span[@class="date"] prune: no +single_page_link: //a[contains(text(), 'View as one page')] + strip://*[contains(@class,'sponsored-text')] strip: //div[@id='post_footer'] -test_url: http://www.businessinsider.com/microsoft-just-put-one-of-its-hardcore-technical-geniuses-on-xbox-2012-1 \ No newline at end of file +test_url: http://www.businessinsider.com/microsoft-just-put-one-of-its-hardcore-technical-geniuses-on-xbox-2012-1 -- cgit v1.3.1 From cedf20e74ba331a04a0d9c8836f728c408284f73 Mon Sep 17 00:00:00 2001 From: Mateus Dalto Piveta Date: Mon, 16 Jun 2014 12:39:44 -0300 Subject: Updated businessinsider.com --- businessinsider.com.txt | 1 + 1 file changed, 1 insertion(+) (limited to 'businessinsider.com.txt') diff --git a/businessinsider.com.txt b/businessinsider.com.txt index e66aeaa..12ca474 100644 --- a/businessinsider.com.txt +++ b/businessinsider.com.txt @@ -2,6 +2,7 @@ title://div[@class="sl-layout-post"]/h1 body: //div[contains(@class, 'post-content') or contains(@class, 'slide-module') or contains(@class, 'KonaBody')] strip: //div[contains(@class, "post-sidebar")] strip: //div[@id='related-links'] +strip: //p[@class='source'] author://div[@class="byline"]/a date://div[@class="byline"]/span[@class="date"] prune: no -- cgit v1.3.1 From a79ad8147d2fdd50bed73ab0628221b0bf1027fa Mon Sep 17 00:00:00 2001 From: Mateus Dalto Piveta Date: Mon, 16 Jun 2014 22:45:25 -0300 Subject: Updated businessinsider.com --- businessinsider.com.txt | 1 + 1 file changed, 1 insertion(+) (limited to 'businessinsider.com.txt') diff --git a/businessinsider.com.txt b/businessinsider.com.txt index 12ca474..39eb742 100644 --- a/businessinsider.com.txt +++ b/businessinsider.com.txt @@ -2,6 +2,7 @@ title://div[@class="sl-layout-post"]/h1 body: //div[contains(@class, 'post-content') or contains(@class, 'slide-module') or contains(@class, 'KonaBody')] strip: //div[contains(@class, "post-sidebar")] strip: //div[@id='related-links'] +strip: //div[@class='related-links-container'] strip: //p[@class='source'] author://div[@class="byline"]/a date://div[@class="byline"]/span[@class="date"] -- cgit v1.3.1