diff options
Diffstat (limited to 'inc/3rdparty/site_config/standard/newyorker.com.txt')
-rw-r--r-- | inc/3rdparty/site_config/standard/newyorker.com.txt | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/inc/3rdparty/site_config/standard/newyorker.com.txt b/inc/3rdparty/site_config/standard/newyorker.com.txt new file mode 100644 index 00000000..5624aa8c --- /dev/null +++ b/inc/3rdparty/site_config/standard/newyorker.com.txt | |||
@@ -0,0 +1,10 @@ | |||
1 | title: //h1[@id='articlehed'] | //h2[@id="articleintro"] | ||
2 | body: //div[@id='articletext'] | ||
3 | |||
4 | strip: //ul[@id="bc"] | //div[@id="yrail"] | //div[@class="entry-keywords"] | //div[@class="entry-categories"] | //div[@class="socialUtils"] | //div[@id="footer"] | ||
5 | |||
6 | date: //h4[@id='articleauthor']/span[@class='dd dds'] | ||
7 | date: //div[@id="pagebody"]/div[@class='hentry entry']/div[@class='published'] | ||
8 | |||
9 | single_page_link: //div[@class='paginationViewSinglePage']/a | ||
10 | test_url: http://www.newyorker.com/online/blogs/culture/2012/06/mug-shot-web-sites.html \ No newline at end of file | ||