From 4250e0dc25383145760be08bae21ad1a2698e7c0 Mon Sep 17 00:00:00 2001 From: Jean-Christophe Date: Wed, 13 May 2015 14:12:09 +0200 Subject: [PATCH] Hotfix for #219 - Missing real fix Here the image extractor was initialized before the real scrape. So no information was store in self.article. This correction is ugly, and might benefit from a different fix. --- goose/crawler.py | 1 + 1 file changed, 1 insertion(+) diff --git a/goose/crawler.py b/goose/crawler.py index 34daf048..7c6a3500 100644 --- a/goose/crawler.py +++ b/goose/crawler.py @@ -181,6 +181,7 @@ def crawl(self, crawl_candidate): # image handling if self.config.enable_image_fetching: + self.image_extractor = self.get_image_extractor() # Hotfix for #219 self.get_image() # post cleanup