diff options
Diffstat (limited to 'nytimes.com.txt')
| -rw-r--r-- | nytimes.com.txt | 36 |
1 files changed, 36 insertions, 0 deletions
diff --git a/nytimes.com.txt b/nytimes.com.txt new file mode 100644 index 0000000..b421951 --- /dev/null +++ b/nytimes.com.txt @@ -0,0 +1,36 @@ +title://h1[@class="articleHeadline"] +body://div[@id="article"] +strip_id_or_class:articleTools +strip_id_or_class:readerscomment +#strip://div[contains(@class, "articleInline runaroundLeft")] +strip: //div[contains(@class, "doubleRule")] +# strip image credit - appears as a bold heading +strip: //div[contains(@class, "articleInline")]//h6 +strip_id_or_class:enlargeThis +strip_id_or_class:pageLinks +strip_id_or_class:memberTools +strip_id_or_class:articleExtras +strip_id_or_class:singleAd +strip_id_or_class:byline +strip_id_or_class:dateline +strip_id_or_class:articleheadline +strip_id_or_class:articleBottomExtra +strip://a[contains(@href, 'nytimes.com/adx/')] +strip: //nyt_byline +strip: //span[contains(@class, 'slideshow') or contains(@class, 'video')] +strip: //p[@class='caption']//a[contains(., 'More Photos')] + +prune: no +tidy: no + +date: substring-after(//*[contains(@class, 'dateline')], 'Published:') + +single_page_link: //link[contains(@href, 'pagewanted=all')] +#single_page_link: //a[contains(@href, 'pagewanted=all') and not(contains(@href, 'login'))] + +strip://ul[@id = 'toolsList'] +strip://h6[@class = 'kicker'] +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
\ No newline at end of file |