diff options
Diffstat (limited to 'msnbc.msn.com.txt')
| -rw-r--r-- | msnbc.msn.com.txt | 21 |
1 files changed, 21 insertions, 0 deletions
diff --git a/msnbc.msn.com.txt b/msnbc.msn.com.txt new file mode 100644 index 0000000..f008d2d --- /dev/null +++ b/msnbc.msn.com.txt @@ -0,0 +1,21 @@ +title: //title +author: //div[@id='byline'] + +date: //div[contains(@class,'timestamp')]/abbr/text() + +body: //div[@id='intellitTXT'] + +strip: //div[@id='byline'] +strip: //div[contains(@class,'timestamp')] +strip: //div[contains(@class, 'ad-label')] +strip: //div[contains(@class, 'ad-break')] +strip: //span[contains(@class, 'x-video')] +strip: //span[contains(@class, 'inline')] +strip: //div[contains(@class, 'video')] +strip: //div[contains(@class, 'discuss')] +strip: //div[@id='most-popular'] +strip: //div[contains(@class,'drawer')] +strip: //*[contains(@class, 'hide')] + +footnotes: no +test_url: http://www.msnbc.msn.com/id/44748412/ns/business-world_business/#.TolUv-vfDbE
\ No newline at end of file |
