From 52db84191b113d70bb863ce4a0ee95163bfd650b Mon Sep 17 00:00:00 2001 From: Florent Date: Tue, 11 Jun 2013 16:14:51 +0200 Subject: [PATCH] Get newspaper source in author field --- modules/presseurop/pages/article.py | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/modules/presseurop/pages/article.py b/modules/presseurop/pages/article.py index ee0c9b74..6e6be574 100644 --- a/modules/presseurop/pages/article.py +++ b/modules/presseurop/pages/article.py @@ -44,6 +44,16 @@ class PresseuropPage(GenericNewsPage): title = title.split('|')[0] return title + def get_author(self): + author = GenericNewsPage.get_author(self) + try: + source = self.document.getroot().xpath( + "//span[@class='sourceinfo']/a")[0] + source = source.text + author = author + " | " + source + return author + except: + return author class DailyTitlesPage(PresseuropPage): def on_loaded(self):