From 4b0c4acf96992a486277a14185615466e8938e6a Mon Sep 17 00:00:00 2001 From: "Jip J. Dekker" Date: Tue, 8 Apr 2014 11:40:30 +0200 Subject: [PATCH] Updated the wikipedia parser as an rightful subclass of Parser --- FourmiCrawler/parsers/WikipediaParser.py | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/FourmiCrawler/parsers/WikipediaParser.py b/FourmiCrawler/parsers/WikipediaParser.py index cd0a2eb..6709472 100644 --- a/FourmiCrawler/parsers/WikipediaParser.py +++ b/FourmiCrawler/parsers/WikipediaParser.py @@ -1,11 +1,12 @@ -import parser +from scrapy.http import Request +from parser import Parser from scrapy.selector import Selector from FourmiCrawler.items import Result -class WikipediaParser: +class WikipediaParser(Parser): - website = "http://en.wikipedia.org/wiki/Methane" - __spider = "WikipediaParser" + website = "http://en.wikipedia.org/wiki/*" + __spider = None print "test1" #def __init__(self, csid): @@ -27,3 +28,6 @@ class WikipediaParser: print item['source'] print "test" return items + + def new_compound_request(self, compound): + return Request(url=self.website[:-1] + compound, callback=self.parse) \ No newline at end of file