From 2115f72570d53e37a57563043e5abe1ff499e75c Mon Sep 17 00:00:00 2001 From: Olivier Cortès Date: Mon, 16 Mar 2015 16:05:12 +0100 Subject: Update lefigaro datetime parser + add a recent test URL I checked the datetime XPath on first and third `test_url`. --- lefigaro.fr.txt | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/lefigaro.fr.txt b/lefigaro.fr.txt index e720e37..7e1d12d 100644 --- a/lefigaro.fr.txt +++ b/lefigaro.fr.txt @@ -2,7 +2,8 @@ title: //meta[@name='title']/@content author: //span[@class='sign']//a[@class='journaliste'] author: //meta[@name='author']/@content body: //*[@id='article']/div[@class='photo'] | //*[@id='article']/h2 | //*[@id='article']/div[@class='texte'] -date: //time[@pubdate]/@datetime +date: //li[contains(concat(' ',normalize-space(@class),' '),' fig-date-pub ')]//time prune: no test_url: http://www.lefigaro.fr/environnement/2011/11/10/01029-20111110ARTFIG00801-la-chine-confrontee-a-un-immense-defi-ecologique.php -test_url: http://www.lefigaro.fr/conjoncture/2012/11/20/20002-20121120ARTFIG00609-l-usager-devrait-payer-plus-pour-financer-les-transports.php \ No newline at end of file +test_url: http://www.lefigaro.fr/conjoncture/2012/11/20/20002-20121120ARTFIG00609-l-usager-devrait-payer-plus-pour-financer-les-transports.php +test_url: http://www.lefigaro.fr/social/2015/03/10/09010-20150310ARTFIG00312-encore-une-annee-noire-pour-l-emploi-salarie.php -- cgit v1.3.1