diff options
Diffstat (limited to 'newyorker.com.txt')
| -rw-r--r-- | newyorker.com.txt | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/newyorker.com.txt b/newyorker.com.txt new file mode 100644 index 0000000..f1e2ffa --- /dev/null +++ b/newyorker.com.txt @@ -0,0 +1,10 @@ +title: //h1[@id='articlehed'] | //h2[@id="articleintro"] +body: //div[@id='articletext'] + +strip: //ul[@id="bc"] | //div[@id="yrail"] | //div[@class="entry-keywords"] | //div[@class="entry-categories"] | //div[@class="socialUtils"] | //div[@id="footer"] + +date: //h4[@id='articleauthor']/span[@class='dd dds'] +date: //div[@id="pagebody"]/div[@class='hentry entry']/div[@class='published'] + +single_page_link: //div[@class='paginationViewSinglePage']/a +test_url: http://www.newyorker.com/online/blogs/culture/2012/06/mug-shot-web-sites.html
\ No newline at end of file |
