diff options
| -rw-r--r-- | cnn.com.txt | 27 |
1 files changed, 4 insertions, 23 deletions
diff --git a/cnn.com.txt b/cnn.com.txt index 95101e0..3c04827 100644 --- a/cnn.com.txt +++ b/cnn.com.txt @@ -1,28 +1,9 @@ -body: //div[@id='cnnContentContainer']//div[contains(@class, 'cnn_strycntntlft')] -title: //div[@class="cnn_storyarea"]/h1 -author: //div[@class="cnnByline"]/strong -date: substring-after(//div[@class="cnn_strytmstmp"], 'Sun') -date: substring-after(//div[@class="cnn_strytmstmp"], 'Mon') -date: substring-after(//div[@class="cnn_strytmstmp"], 'Tue') -date: substring-after(//div[@class="cnn_strytmstmp"], 'Wed') -date: substring-after(//div[@class="cnn_strytmstmp"], 'Thu') -date: substring-after(//div[@class="cnn_strytmstmp"], 'Fri') -date: substring-after(//div[@class="cnn_strytmstmp"], 'Sat') -strip: //div[@class="cnn_storyarea"]/h1 -strip_id_or_class: cnnByline -strip_id_or_class: cnn_strytmstmp -strip_id_or_class: cnn_strycaptiontxt -strip_id_or_class: cnn_strybtntoolsbttm -strip_id_or_class: cnn_strybtntools -strip_id_or_class: cnn_strybtmcntnt -strip_id_or_class: sharebar -#strip_id_or_class: cnn_containerwht -strip_id_or_class: cnn_stryathrtmp +body: //section[contains(@class, 'body-text')] -http_header(user-agent): Mozilla/5.0 (X11; CrOS x86_64 9000.91.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.110 Safari/537.36 +strip_id_or_class: highlights -replace_string(<a name="em0"></a>): <!-- a name --> -test_url: http://www.cnn.com/2012/05/13/us/new-york-police-policy/index.html?eref=rss_topstories +test_url: http://www.cnn.com/2012/05/13/us/new-york-police-policy/index.html test_contains: this discriminatory and ineffective practice test_url: http://rss.cnn.com/rss/edition.rss +test_url: http://rss.cnn.com/rss/edition_technology.rss |
