diff options
Diffstat (limited to 'technologyreview.com.txt')
| -rw-r--r-- | technologyreview.com.txt | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/technologyreview.com.txt b/technologyreview.com.txt new file mode 100644 index 0000000..d405eb1 --- /dev/null +++ b/technologyreview.com.txt @@ -0,0 +1,16 @@ +title: //header[@class='article-meta']/h1 +title: substring-before(//title, '|') + +body: //section[contains(@class, 'body')] + +# Author & Date for News and Featured Stories +author: //ul[@class='byline']/li/a +author: substring-before(substring-after(//ul[@class='byline']/li, 'By '), ' on') +date: substring-after(//ul[@class='byline']/li, 'on ') + +# Author & Date for "Views" +author: //div[@class='view-byline']/div[@class='meta']/h2[1] +date: //div[@class='view-byline']/div[@class='meta']/h2[2] + +next_page_link: //section[@class='pagination']/a[contains(@class, 'continue')] +test_url: http://www.technologyreview.com/news/427567/facebooks-telescope-on-human-behavior/
\ No newline at end of file |