diff options
| -rw-r--r-- | nytimes.com.txt | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/nytimes.com.txt b/nytimes.com.txt index 07aeda4..4f1a8b9 100644 --- a/nytimes.com.txt +++ b/nytimes.com.txt @@ -2,6 +2,7 @@ title://h1[@class="articleHeadline"] body://div[@id="article"] body://*[@itemprop="articleBody"] body: //div[contains(concat(' ',normalize-space(@class),' '),' g-body-article-container ')] +body: //article[@id='story'] strip_id_or_class:articleTools strip_id_or_class:readerscomment #strip://div[contains(@class, "articleInline runaroundLeft")] @@ -43,6 +44,9 @@ test_contains: In this column I want to look at a not uncommon way of writing test_url: http://www.nytimes.com/2012/06/10/arts/television/the-newsroom-aaron-sorkins-return-to-tv.html test_contains: IF you’ve seen enough of Aaron Sorkin’s theater +test_url: https://www.nytimes.com/interactive/2016/books/review/best-books.html +test_contains: invention and speculation flow together + 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 test_url: http://www.nytimes.com/2004/02/29/weekinreview/correspondence-class-consciousness-china-s-wealthy-live-creed-hobbes-darwin-meet.html |