From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- inc/3rdparty/site_config/standard/npr.org.txt | 32 +++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/npr.org.txt (limited to 'inc/3rdparty/site_config/standard/npr.org.txt') diff --git a/inc/3rdparty/site_config/standard/npr.org.txt b/inc/3rdparty/site_config/standard/npr.org.txt new file mode 100644 index 00000000..afab0eb3 --- /dev/null +++ b/inc/3rdparty/site_config/standard/npr.org.txt @@ -0,0 +1,32 @@ +title: //div[contains(@class, 'storytitle')]//h1 +author: //p[@class="byline"]/span +body: //div[@id='storyspan02']//*[@class='duration' or @class='download' or contains(@class, 'photo')] | //div[@id='storytext'] | //div[@class='transcript'] +date: //meta[@name="date"]/@content + +strip: //div[@class='enlarge_measure'] +strip: //div[@class='enlarge_html'] +strip: //a[@class='enlargeicon'] +strip: //div[contains(@class, 'bookedition')] +strip: //div[@class='textsize'] +strip: //ul[@class='genres'] +strip: //span[@class='bull'] +strip_id_or_class: secondary +strip_id_or_class: con1col +strip: //h3[@class='conheader'] + +replace_string( ): +replace_string(
):

Transcript

+ +prune: no +strip://div[@class="ecommercepop"] +strip://span[@class="bull"] +strip://span[@class="purchaseLink"] +strip://div[@class="enlarge_html"] +strip://div[@class="enlarge_measure"] +strip://div[@class="container con1col small"] +strip://a[contains(@class, "enlargebtn")] +strip://div[contains(@class, "bucketwrap internallink")] + +test_url: http://www.npr.org/blogs/thetwo-way/2011/07/12/137799301/sports-loses-its-escapist-gleam-in-a-summer-of-court-dates +test_url: http://www.npr.org/2012/07/04/156190948/feeling-under-siege-catholic-leadership-shifts-right +test_url: http://www.npr.org/2012/12/13/166480907/the-years-best-sci-fi-crosses-galaxies-and-genres \ No newline at end of file -- cgit v1.2.3