From 33acc0ccf771e1645be821d1f33e7fe20b44f9a7 Mon Sep 17 00:00:00 2001 From: Lukas Anzinger Date: Wed, 17 Feb 2016 22:13:58 +0100 Subject: theguardian.com: Rewrite and fix author and date extraction. --- theguardian.com.txt | 44 ++++++++++++++++++++++++++++---------------- 1 file changed, 28 insertions(+), 16 deletions(-) diff --git a/theguardian.com.txt b/theguardian.com.txt index 738e7d3..0a21de2 100644 --- a/theguardian.com.txt +++ b/theguardian.com.txt @@ -1,20 +1,29 @@ -title: //div[@id='main-article-info']//h1 -body: //figure[contains(@itemprop, "associatedMedia")] | //div[contains(@class, "content__article-body")] -body: //figure[contains(@itemprop, "associatedMedia")] | //div[contains(@itemprop, "articleBody")] -date: //li[@class='publication']//time[@pubdate] | //li[@class='publication']//data[@pubdate] -strip: //div[contains(@class, 'email-subscription')] -strip: //div[contains(@class, 'kindleWidget')] -#strip: //a[not(text())] -strip_id_or_class: pocket-btn -author: //li[@class='byline'] -native_ad_clue: //meta[@property="article:tag" and contains(@content, "Partner zone")] -native_ad_clue: //meta[@property="video:tag" and contains(@content, "Partner zone")] -prune: no -tidy: no +title: //h1[@itemprop='headline'] -parser: html5php +body: //article +strip: //article/header/div[contains(@class, 'content__header')] +strip: //article/header/div[contains(@class, 'content__logo-container')] +strip: //article//div[contains(@class, 'content__secondary-column')] +strip: //article//aside +strip: //article//div[contains(@class, 'block-share')] +strip: //article//div[@class='submeta'] +strip: //article//span[contains(@class, 'inline-expand-image')] +strip: //article//div[@class='kindleWidget'] +strip: //article//div[@class='email-subscription'] +strip: //article//script +strip: //article//figure[contains(@class, 'element-audio')] +strip: //article//a[contains(@style, 'display: none')] +strip: //article/div[@class='paidfor-band'] -strip_id_or_class: -expand- +author: //article//p[@class='byline'] +date: //article//time/@datetime +strip: //article//div[contains(@class, 'content__meta-container')] + +native_ad_clue: //meta[@property='article:tag' and contains(@content, 'partner zone')] +native_ad_clue: //meta[@property='video:tag' and contains(@content, 'partner zone')] + +prune: no +tidy: no test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption test_contains: The National Security Agency has made repeated attempts to develop @@ -25,5 +34,8 @@ test_contains: In August, the editor of the Guardian rang me up and asked if I w test_contains: As the second most senior judge in the country, Lord Hoffmann, said in 2004 about a previous version of our anti-terrorism laws test_url: http://www.theguardian.com/commentisfree/2014/jun/15/britishness-search-identity-my-part-in-camerons-odyssey +test_url: http://www.theguardian.com/world/2016/feb/17/ankara-explosion-turkey-injures-large-number-of-people-reports-say +test_url: http://www.theguardian.com/uk-news/2016/feb/11/trident-the-british-question + # Native ad -test_url: http://www.theguardian.com/sustainable-business/2014/jul/18/ben-jerry-turn-ice-cream-into-energy +test_url: http://www.theguardian.com/sustainable-business/fairtrade-partner-zone/chocolate-cocoa-production-risk -- cgit v1.3.1