From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- inc/3rdparty/site_config/standard/wyborcza.pl.txt | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/wyborcza.pl.txt (limited to 'inc/3rdparty/site_config/standard/wyborcza.pl.txt') diff --git a/inc/3rdparty/site_config/standard/wyborcza.pl.txt b/inc/3rdparty/site_config/standard/wyborcza.pl.txt old mode 100644 new mode 100755 index f99467c2..638583dc --- a/inc/3rdparty/site_config/standard/wyborcza.pl.txt +++ b/inc/3rdparty/site_config/standard/wyborcza.pl.txt @@ -1,11 +1,9 @@ -title:h1 -author: //*[@class = 'author'] -date: //*[@class = 'date'] -body: //*[@id = 'art'] -next_page_link: //*[@id='Str']/a[contains(text(), 'nastepne')] -strip: //*[@class = 'rel_zdjTOP'] -strip: //*[@id = 'rel'] -strip: //*[@class = 'txt_upl'] -strip: //*[@id='Str'] -strip: //*[@id='source'] -test_url: http://wyborcza.pl/1,123455,11536088,Gdy_peknie_fejs__obryzga_wszystko.html?as=1&startsz=x \ No newline at end of file +body: //div[@id='article'] +strip: //div[@class='head'] + +strip_id_or_class: txt_upl + +single_page_link: //div[@id='gazeta_article_tools']//a[contains(@class, 'print')] + +test_url: http://wyborcza.pl/1,123455,11536088,Gdy_peknie_fejs__obryzga_wszystko.html?as=1&startsz=x +test_url: http://wyborcza.pl/1,75478,14880255,Biskup_Dydycz_o_pedofilii_i_tajemnicy_spowiedzi__Zamiast.html \ No newline at end of file -- cgit v1.2.3