diff options
Diffstat (limited to 'inc/3rdparty/site_config/standard/politico.com.txt')
-rwxr-xr-x | inc/3rdparty/site_config/standard/politico.com.txt | 26 |
1 files changed, 11 insertions, 15 deletions
diff --git a/inc/3rdparty/site_config/standard/politico.com.txt b/inc/3rdparty/site_config/standard/politico.com.txt index c5302d1b..d8f5e575 100755 --- a/inc/3rdparty/site_config/standard/politico.com.txt +++ b/inc/3rdparty/site_config/standard/politico.com.txt | |||
@@ -1,17 +1,13 @@ | |||
1 | title://div[contains(@class, "article")]/h1 | 1 | title://div[contains(@class, "article")]/h1 |
2 | body://div[contains(@class,"story-text")] | 2 | body://div[contains(@class,"story-text")] |
3 | 3 | ||
4 | # Why doesn't this work? next_page_link://ul[contains(@class,"pagination")]/li/a[@rel="next"] | 4 | # Why doesn't this work? next_page_link://ul[contains(@class,"pagination")]/li/a[@rel="next"] |
5 | 5 | ||
6 | next_page_link://ul[contains(@class,"pagination")]/li[contains(@class, "current")]/following-sibling::node()/a | 6 | next_page_link://ul[contains(@class,"pagination")]/li[contains(@class, "current")]/following-sibling::node()/a |
7 | next_page_link://div[contains(@class,"pagination")]/ol/li[contains(@class, "current")]/following-sibling::node()/a | 7 | date://meta[@name="publish_date"]/@content |
8 | date://meta[@name="publish_date"]/@content | 8 | |
9 | 9 | strip://div[contains(@class, "breadcrumbs")] | |
10 | strip://div[contains(@class, "breadcrumbs")] | 10 | strip://a[contains(@class, "hidden")] |
11 | strip://a[contains(@class, "hidden")] | 11 | strip://div[contains(@class, "story-embed")] |
12 | strip://div[contains(@class, "story-embed")] | ||
13 | strip://div[contains(@class, "story-text")]//p/a[contains(text(), "Also on POLITICO:")]/.. | 12 | strip://div[contains(@class, "story-text")]//p/a[contains(text(), "Also on POLITICO:")]/.. |
14 | strip://div[contains(@class, "story-interrupt")] | ||
15 | strip://footer[contains(@class, "author-bio")] | ||
16 | |||
17 | test_url: http://www.politico.com/news/stories/0712/78105.html \ No newline at end of file | 13 | test_url: http://www.politico.com/news/stories/0712/78105.html \ No newline at end of file |