aboutsummaryrefslogtreecommitdiffhomepage
path: root/inc/3rdparty/site_config/standard/npr.org.txt
diff options
context:
space:
mode:
Diffstat (limited to 'inc/3rdparty/site_config/standard/npr.org.txt')
-rw-r--r--inc/3rdparty/site_config/standard/npr.org.txt32
1 files changed, 32 insertions, 0 deletions
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 @@
1title: //div[contains(@class, 'storytitle')]//h1
2author: //p[@class="byline"]/span
3body: //div[@id='storyspan02']//*[@class='duration' or @class='download' or contains(@class, 'photo')] | //div[@id='storytext'] | //div[@class='transcript']
4date: //meta[@name="date"]/@content
5
6strip: //div[@class='enlarge_measure']
7strip: //div[@class='enlarge_html']
8strip: //a[@class='enlargeicon']
9strip: //div[contains(@class, 'bookedition')]
10strip: //div[@class='textsize']
11strip: //ul[@class='genres']
12strip: //span[@class='bull']
13strip_id_or_class: secondary
14strip_id_or_class: con1col
15strip: //h3[@class='conheader']
16
17replace_string(<a name="more">&nbsp;</a>): <!-- no more -->
18replace_string(<div class="transcript">): <div class="transcript"><h2>Transcript</h2>
19
20prune: no
21strip://div[@class="ecommercepop"]
22strip://span[@class="bull"]
23strip://span[@class="purchaseLink"]
24strip://div[@class="enlarge_html"]
25strip://div[@class="enlarge_measure"]
26strip://div[@class="container con1col small"]
27strip://a[contains(@class, "enlargebtn")]
28strip://div[contains(@class, "bucketwrap internallink")]
29
30test_url: http://www.npr.org/blogs/thetwo-way/2011/07/12/137799301/sports-loses-its-escapist-gleam-in-a-summer-of-court-dates
31test_url: http://www.npr.org/2012/07/04/156190948/feeling-under-siege-catholic-leadership-shifts-right
32test_url: http://www.npr.org/2012/12/13/166480907/the-years-best-sci-fi-crosses-galaxies-and-genres \ No newline at end of file