diff options
Diffstat (limited to 'techhive.com.txt')
| -rw-r--r-- | techhive.com.txt | 18 |
1 files changed, 18 insertions, 0 deletions
diff --git a/techhive.com.txt b/techhive.com.txt new file mode 100644 index 0000000..29720b0 --- /dev/null +++ b/techhive.com.txt @@ -0,0 +1,18 @@ +title: //div[@class='articleHead']//h1 +author: //div[@class="author-name"]/a[1] +body: //div[@class="main"] + +# remove 'From the Lab' and 'Recent posts' text +strip: //div[@class='blogLabel'] + +# remove byline and meta info +strip: //div[@class="article-meta"] +strip: //div[@class="author-info"] + +#strip tags and categories +strip: //div[@class="department"] + +#strip product cap links +strip: //div[@class="cap-main"] +strip: //div[@id="compare-lede"] +test_url: http://www.techhive.com/article/2010549/up-close-with-blackberry-10.html
\ No newline at end of file |