diff options
| -rw-r--r-- | sportsillustrated.cnn.com.txt | 26 |
1 files changed, 0 insertions, 26 deletions
diff --git a/sportsillustrated.cnn.com.txt b/sportsillustrated.cnn.com.txt deleted file mode 100644 index b3da813..0000000 --- a/sportsillustrated.cnn.com.txt +++ /dev/null @@ -1,26 +0,0 @@ -# main sportsillustrated.com articles -# -body: //div[@id="cnnStoryContent"] -title: //div[@id="cnnStoryHeadline"]//h1 -author: //div[@id="cnnSubBanner"]//strong -date: substring-after(//div[@id="cnnTimeStamp"], "Updated: ") -date: substring-after(//div[@id="cnnTimeStamp"], "Posted: ") - -# kill ugly font buttons -strip: //div[@id="cnnSCFontButtons"] - -# kill misc filler videos & etc -strip: //div[@class="cnnDivideContent"] -strip: //*[@class="cnnTMbox"] - -# si vault articles -# ------------- -body: //div[@class="siv_artPara"] -title: //div[@class="siv_artHeader"]//h1 -author: //div[@class="byline"] -date: //div[@class="date"] - -next_page_link: //div[@id='cnnStoryContinue']/a -strip_id_or_class: cnnstorypagination - -test_url: http://sportsillustrated.cnn.com/2012/writers/peter_king/02/27/combine/index.html
\ No newline at end of file |
