diff options
| -rw-r--r-- | allthingsd.com.txt | 7 |
1 files changed, 5 insertions, 2 deletions
diff --git a/allthingsd.com.txt b/allthingsd.com.txt index 581f9da..f8c67d0 100644 --- a/allthingsd.com.txt +++ b/allthingsd.com.txt @@ -1,10 +1,13 @@ title://div[@class="article-title"]/h1[@class="title"] date: //p[@class="article-date"] -body://*[@class="article-body article-text"] +body://div[contains(@class, "article-body")] # Trim out related posts at bottom of article strip://blockquote[@class="memo"] +tidy: no + # Yup, no idea why author won't work... author://div[@class="page-header article-header clearfix"]/p[@class="title"] # [Marco:] Author won't work here because the page defines the "home" link under the author's name as rel="author", which always gets priority if the page has defined it. -test_url: http://allthingsd.com/20120513/exclusive-yahoos-thompson-out-levinsohn-in-board-settlement-with-loeb-nears-completion/
\ No newline at end of file +test_url: http://allthingsd.com/20120513/exclusive-yahoos-thompson-out-levinsohn-in-board-settlement-with-loeb-nears-completion/ +test_url: http://allthingsd.com/20131010/google-cio-ben-fried-on-how-google-works/
\ No newline at end of file |