diff options
author | Nicolas LÅ“uillet <nicolas.loeuillet@gmail.com> | 2013-12-06 10:13:03 +0100 |
---|---|---|
committer | Nicolas LÅ“uillet <nicolas.loeuillet@gmail.com> | 2013-12-06 10:13:03 +0100 |
commit | ac4d114214d820b20e18518a2dbc809337e39043 (patch) | |
tree | 27886128ef949b7f8dd174b0646b5a4d99883b44 /inc/3rdparty/site_config/standard/npr.org.txt | |
parent | d5501950e2470d52f6bf5954d2179010cdee0475 (diff) | |
download | wallabag-ac4d114214d820b20e18518a2dbc809337e39043.tar.gz wallabag-ac4d114214d820b20e18518a2dbc809337e39043.tar.zst wallabag-ac4d114214d820b20e18518a2dbc809337e39043.zip |
[add] new specific configuration files
Diffstat (limited to 'inc/3rdparty/site_config/standard/npr.org.txt')
-rw-r--r-- | inc/3rdparty/site_config/standard/npr.org.txt | 32 |
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 @@ | |||
1 | title: //div[contains(@class, 'storytitle')]//h1 | ||
2 | author: //p[@class="byline"]/span | ||
3 | body: //div[@id='storyspan02']//*[@class='duration' or @class='download' or contains(@class, 'photo')] | //div[@id='storytext'] | //div[@class='transcript'] | ||
4 | date: //meta[@name="date"]/@content | ||
5 | |||
6 | strip: //div[@class='enlarge_measure'] | ||
7 | strip: //div[@class='enlarge_html'] | ||
8 | strip: //a[@class='enlargeicon'] | ||
9 | strip: //div[contains(@class, 'bookedition')] | ||
10 | strip: //div[@class='textsize'] | ||
11 | strip: //ul[@class='genres'] | ||
12 | strip: //span[@class='bull'] | ||
13 | strip_id_or_class: secondary | ||
14 | strip_id_or_class: con1col | ||
15 | strip: //h3[@class='conheader'] | ||
16 | |||
17 | replace_string(<a name="more"> </a>): <!-- no more --> | ||
18 | replace_string(<div class="transcript">): <div class="transcript"><h2>Transcript</h2> | ||
19 | |||
20 | prune: no | ||
21 | strip://div[@class="ecommercepop"] | ||
22 | strip://span[@class="bull"] | ||
23 | strip://span[@class="purchaseLink"] | ||
24 | strip://div[@class="enlarge_html"] | ||
25 | strip://div[@class="enlarge_measure"] | ||
26 | strip://div[@class="container con1col small"] | ||
27 | strip://a[contains(@class, "enlargebtn")] | ||
28 | strip://div[contains(@class, "bucketwrap internallink")] | ||
29 | |||
30 | test_url: http://www.npr.org/blogs/thetwo-way/2011/07/12/137799301/sports-loses-its-escapist-gleam-in-a-summer-of-court-dates | ||
31 | test_url: http://www.npr.org/2012/07/04/156190948/feeling-under-siege-catholic-leadership-shifts-right | ||
32 | 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 | ||