diff options
Diffstat (limited to '.wordpress.com.txt')
| -rw-r--r-- | .wordpress.com.txt | 27 |
1 files changed, 27 insertions, 0 deletions
diff --git a/.wordpress.com.txt b/.wordpress.com.txt new file mode 100644 index 0000000..3aa82c8 --- /dev/null +++ b/.wordpress.com.txt @@ -0,0 +1,27 @@ +# try to target content block within div#content +body: //div[@id="content"]//div[contains(@class, 'entry-content') or contains(@class, 'entrytext') or @class='main' or @class='entry'] +# if that fails, get div#content +body: //div[@id='content'] +title: //meta[@property='og:title']/@content + +date: //div[@id='content']//span[contains(@class, 'entry-date')] +date: //div[contains(@class, 'entry-meta')]//time[@pubdate or @pubDate] +author: //div[contains(@class, 'entry-meta')]//a[@rel='author'] + +prune: no + +strip: //nav +strip: //header +strip: //*[@id='comments' or @id='respond'] +strip: //div[contains(@class, 'comments')] +strip_id_or_class: sharedaddy +strip_id_or_class: wpadvert +strip_id_or_class: commentlist +strip_id_or_class: sociable +strip_id_or_class: related_post +strip_id_or_class: wp-socializer +strip_id_or_class: addtoany +strip: //div[contains(@class, 'navigation')] +#strip: //iframe + +test_url: https://elisehahn.wordpress.com/2011/11/10/the-vatican-and-st-peters-basilica/
\ No newline at end of file |
