diff options
Diffstat (limited to 'blogs.smithsonianmag.com.txt')
| -rw-r--r-- | blogs.smithsonianmag.com.txt | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/blogs.smithsonianmag.com.txt b/blogs.smithsonianmag.com.txt new file mode 100644 index 0000000..1bc65e7 --- /dev/null +++ b/blogs.smithsonianmag.com.txt @@ -0,0 +1,15 @@ +# metadata +author://div[@class = 'post']/div[@class='meta']/a[1] +date://div[@id = 'rap']/h2[1] +body://div[@class = 'post'] + +# wrapping caption and image +wrap_in(fieldset)://div[contains(@class, 'wp-caption')] + + +# clean up +strip://div[@class = 'post']/h3[@class = 'storytitle'] +strip://div[@class = 'post']/div[@class = 'social'] +strip://img[@style = 'display:none;'] +strip://img[@height='0' and @width='0'] +test_url: http://blogs.smithsonianmag.com/adventure/2011/10/tips-for-women-traveling-in-turkey/
\ No newline at end of file |