From a4dc8c87112e2e541852e4c0aab3ed6782e5a6dd Mon Sep 17 00:00:00 2001 From: RTB Date: Tue, 8 Apr 2014 13:10:02 +0200 Subject: [PATCH] corrected Chemspider parser to be a subclass of Parser --- FourmiCrawler/parsers/ChemSpider.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/FourmiCrawler/parsers/ChemSpider.py b/FourmiCrawler/parsers/ChemSpider.py index bd69e58..3890150 100644 --- a/FourmiCrawler/parsers/ChemSpider.py +++ b/FourmiCrawler/parsers/ChemSpider.py @@ -1,3 +1,4 @@ +from parser import Parser from scrapy import log from scrapy.http import Request from scrapy.selector import Selector @@ -9,7 +10,7 @@ This parser will manage searching for chemicals through the ChemsSpider API, and parsing the resulting ChemSpider page. The token required for the API should be in a configuration file somewhere. """ -class ChemSpider: +class ChemSpider(Parser): website = "http://www.chemspider.com/*" __spider = 'ChemSpider' @@ -26,7 +27,7 @@ class ChemSpider: pass def new_compound_request(self,compound): - searchurl = website[:-1] + search % (compound, TOKEN) + searchurl = self.website[:-1] + self.search % (compound, TOKEN) log.msg('chemspider compound', level=log.DEBUG) print "ChemSpider compound" return Request(url=searchurl, callback=self.parse)