diff options
Diffstat (limited to 'cbsnews.com.txt')
| -rw-r--r-- | cbsnews.com.txt | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/cbsnews.com.txt b/cbsnews.com.txt new file mode 100644 index 0000000..780bc15 --- /dev/null +++ b/cbsnews.com.txt @@ -0,0 +1,14 @@ +date: //meta[@name="published"]/@content +date: //div[@class="timeLine"] +title: //div[@id='contentBody']//h1 +author: //dl[@class="storyBlogByline"]/dd/a +body: //div[@id='storyMediaBox'] | //div[contains(@class, 'storyText')] + +# Content Pruning +strip: //div[@class="scrollingArrows"] +strip: //div[@class="timeLine"] +strip: //dl[@class="storyBlogByline"] + +prune: no + +test_url: http://www.cbsnews.com/8301-201_162-57366361/rescued-americans-dad-proud-of-the-u.s/
\ No newline at end of file |