diff options
Diffstat (limited to 'theguardian.com.txt')
| -rw-r--r-- | theguardian.com.txt | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/theguardian.com.txt b/theguardian.com.txt new file mode 100644 index 0000000..2b50949 --- /dev/null +++ b/theguardian.com.txt @@ -0,0 +1,8 @@ +title: //div[@id='main-article-info']//h1 +body: //div[@id='article-wrapper'] +date: //li[@class='publication']//time[@pubdate] | //li[@class='publication']//data[@pubdate] +strip: //div[contains(@class, 'email-subscription')] +author: //li[@class='byline'] +prune: no +tidy: no +test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption
\ No newline at end of file |