From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- inc/3rdparty/site_config/standard/nytimes.com.txt | 85 +++++++++++++---------- 1 file changed, 49 insertions(+), 36 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/nytimes.com.txt (limited to 'inc/3rdparty/site_config/standard/nytimes.com.txt') diff --git a/inc/3rdparty/site_config/standard/nytimes.com.txt b/inc/3rdparty/site_config/standard/nytimes.com.txt old mode 100644 new mode 100755 index 8d9a794a..23c9ad11 --- a/inc/3rdparty/site_config/standard/nytimes.com.txt +++ b/inc/3rdparty/site_config/standard/nytimes.com.txt @@ -1,36 +1,49 @@ -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 +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")] +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_id_or_class:shareTools +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 + +find_string: