From 34c3a8b4d66cd5d80770a571768d7e7a5a96352c Mon Sep 17 00:00:00 2001 From: Bas Vb Date: Wed, 16 Apr 2014 15:22:47 +0200 Subject: [PATCH] remove empty data points --- FourmiCrawler/parsers/WikipediaParser.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/FourmiCrawler/parsers/WikipediaParser.py b/FourmiCrawler/parsers/WikipediaParser.py index 90eca6c..c489424 100644 --- a/FourmiCrawler/parsers/WikipediaParser.py +++ b/FourmiCrawler/parsers/WikipediaParser.py @@ -33,10 +33,13 @@ class WikipediaParser(Parser): item['value'] = prop_values[i].extract().encode('utf-8') item['source'] = "Wikipedia" items.append(item) - print "new: " + item['attribute'] - print item['value'] + #print "new: " + item['attribute'] + #print item['value'] + items=filter(lambda a: a['value']!='', items) + print items return items + def new_compound_request(self, compound): return Request(url=self.website[:-1] + compound, callback=self.parse)