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/plus.google.com.txt | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/plus.google.com.txt (limited to 'inc/3rdparty/site_config/standard/plus.google.com.txt') diff --git a/inc/3rdparty/site_config/standard/plus.google.com.txt b/inc/3rdparty/site_config/standard/plus.google.com.txt new file mode 100644 index 00000000..50a5dbf5 --- /dev/null +++ b/inc/3rdparty/site_config/standard/plus.google.com.txt @@ -0,0 +1,17 @@ +body: //div[@id='contentPane']//div[@class='vg'] +body: //div[@id='contentPane'] + +# Grab the author by finding the first profile pic, then backing up a node and getting the title of tag which will be the author hopefully. Sorry can't test this due to parser errors, thanks google :( + +author: //div[@id='contentPane']//img[contains(@alt, 'profile photo')][1]/../@title + + +strip: //*[@title="People who +1'd this"]/../.. +strip: //*[contains(@class, 'a-b-f-i-Hg-Uf')] +strip: //*[@role='menu'] +strip: //img[contains(@alt, 'profile photo')] +strip: //*[@class='a-f-i-Ad'] + +tidy: no + +test_url: http://plus.google.com/u/0/117840649766034848455/posts/FddaP6jeCqp \ No newline at end of file -- cgit v1.2.3