From b1f1d7e13ea1dd2e70b3459827582d226c7bb55e Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Sat, 5 Oct 2013 11:43:20 +0200 Subject: npr.org and theguardian.com --- npr.org.txt | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'npr.org.txt') diff --git a/npr.org.txt b/npr.org.txt index 5dc7e74..acd73e4 100644 --- a/npr.org.txt +++ b/npr.org.txt @@ -1,11 +1,11 @@ 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'] +body: //div[@id='primaryaudio']//*[@class='duration' or @class='download' or contains(@class, 'photo')] | //div[@id='storytext' or @id='supplementarycontent' or contains(@class, 'transcript')] date: //meta[@name="date"]/@content -strip: //div[@class='enlarge_measure'] -strip: //div[@class='enlarge_html'] -strip: //a[@class='enlargeicon'] +strip_id_or_class: enlarge_measure +strip_id_or_class: enlarge_html +strip: //a[contains(@class, 'enlargeicon')] strip: //div[contains(@class, 'bookedition')] strip: //div[@class='textsize'] strip: //ul[@class='genres'] @@ -16,6 +16,7 @@ strip: //h3[@class='conheader'] replace_string( ): replace_string(
):

Transcript

+replace_string(
):

Transcript

prune: no strip://div[@class="ecommercepop"] @@ -29,4 +30,5 @@ 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 +test_url: http://www.npr.org/2012/12/13/166480907/the-years-best-sci-fi-crosses-galaxies-and-genres +test_url: http://www.npr.org/templates/story/story.php?storyId=229103221 \ No newline at end of file -- cgit v1.3.1