diff options
Diffstat (limited to 'inc/3rdparty/site_config/standard/theguardian.com.txt')
-rwxr-xr-x | inc/3rdparty/site_config/standard/theguardian.com.txt | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/inc/3rdparty/site_config/standard/theguardian.com.txt b/inc/3rdparty/site_config/standard/theguardian.com.txt index 88e2ecf4..c8b70e6f 100755 --- a/inc/3rdparty/site_config/standard/theguardian.com.txt +++ b/inc/3rdparty/site_config/standard/theguardian.com.txt | |||
@@ -1,5 +1,5 @@ | |||
1 | title: //div[@id='main-article-info']//h1 | 1 | title: //div[@id='main-article-info']//h1 |
2 | body: //div[@id='article-wrapper'] | 2 | body: //figure[contains(@itemprop, "associatedMedia")] | //div[contains(@itemprop, "articleBody")] |
3 | date: //li[@class='publication']//time[@pubdate] | //li[@class='publication']//data[@pubdate] | 3 | date: //li[@class='publication']//time[@pubdate] | //li[@class='publication']//data[@pubdate] |
4 | strip: //div[contains(@class, 'email-subscription')] | 4 | strip: //div[contains(@class, 'email-subscription')] |
5 | strip: //div[contains(@class, 'kindleWidget')] | 5 | strip: //div[contains(@class, 'kindleWidget')] |
@@ -11,6 +11,8 @@ native_ad_clue: //meta[@property="video:tag" and contains(@content, "Partner zon | |||
11 | prune: no | 11 | prune: no |
12 | tidy: no | 12 | tidy: no |
13 | 13 | ||
14 | strip_id_or_class: -expand- | ||
15 | |||
14 | test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption | 16 | test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption |
15 | test_contains: The National Security Agency has made repeated attempts to develop | 17 | test_contains: The National Security Agency has made repeated attempts to develop |
16 | test_contains: The agency did not directly address those questions, instead providing a statement. | 18 | test_contains: The agency did not directly address those questions, instead providing a statement. |