diff options
Diffstat (limited to 'nytimes.com.txt')
| -rw-r--r-- | nytimes.com.txt | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/nytimes.com.txt b/nytimes.com.txt index bcba93f..5712b64 100644 --- a/nytimes.com.txt +++ b/nytimes.com.txt @@ -1,5 +1,6 @@ title://h1[@class="articleHeadline"] body://div[@id="article"] +body://*[@itemprop="articleBody"] strip_id_or_class:articleTools strip_id_or_class:readerscomment #strip://div[contains(@class, "articleInline runaroundLeft")] @@ -32,6 +33,7 @@ replace_string: </div> date: substring-after(//*[contains(@class, 'dateline')], 'Published:') single_page_link: //link[contains(@href, 'pagewanted=all')] +single_page_link: concat(substring-before(//div[@id='pageLinks']//a[contains(@href, 'pagewanted=')]/@href, 'pagewanted='), 'pagewanted=all') #single_page_link: //a[contains(@href, 'pagewanted=all') and not(contains(@href, 'login'))] strip://ul[@id = 'toolsList'] @@ -41,4 +43,5 @@ author:substring-after(//h6[@class='byline'],'By ') test_url: http://www.nytimes.com/2011/07/24/books/review/an-academic-authors-unintentional-masterpiece.html test_url: http://www.nytimes.com/2012/06/10/arts/television/the-newsroom-aaron-sorkins-return-to-tv.html test_url: http://www.nytimes.com/2013/03/25/world/middleeast/israeli-military-responds-after-patrols-come-under-fire-from-syria.html -test_url: http://www.nytimes.com/2013/08/15/nyregion/when-the-new-york-city-subway-ran-without-rails.html
\ No newline at end of file +test_url: http://www.nytimes.com/2013/08/15/nyregion/when-the-new-york-city-subway-ran-without-rails.html +test_url: http://www.nytimes.com/2004/02/29/weekinreview/correspondence-class-consciousness-china-s-wealthy-live-creed-hobbes-darwin-meet.html
\ No newline at end of file |