From f9799c30d8d7a887454b9685bea7a37a5a0c4486 Mon Sep 17 00:00:00 2001 From: Bas Vb Date: Tue, 8 Apr 2014 14:59:09 +0200 Subject: [PATCH] Parse is runnable now. --- FourmiCrawler/parsers/WikipediaParser.py | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/FourmiCrawler/parsers/WikipediaParser.py b/FourmiCrawler/parsers/WikipediaParser.py index 6709472..724fb79 100644 --- a/FourmiCrawler/parsers/WikipediaParser.py +++ b/FourmiCrawler/parsers/WikipediaParser.py @@ -8,20 +8,18 @@ class WikipediaParser(Parser): website = "http://en.wikipedia.org/wiki/*" __spider = None - print "test1" #def __init__(self, csid): # self.website = "http://en.wikipedia.org/wiki/{id}".format(id=csid) def parse(self, response): - print "test1" + print response.url #self.log('A response from %s just arrived!' % response.url) - #def parse(): - sel = Selector("http://en.wikipedia.org/wiki/Methane") + sel = Selector(response) items = [] item = Result() item['attribute']="Melting point" - item['value']=site.xpath('//tr[contains(@href, "/wiki/Melting_point")]/text()').extract() - item['source']= self.website + item['value']="value1" # sel.xpath('//tr[contains(@href, "/wiki/Melting_point")]/text()').extract() + item['source']= "Wikipedia" items.append(item) print item['attribute'] print item['value']