From 4f5b66fff69b68666d4e114afa2d53382476b985 Mon Sep 17 00:00:00 2001 From: "Jip J. Dekker" Date: Tue, 18 Mar 2014 17:28:49 +0100 Subject: [PATCH] Basic structure to make sure the spider use an argument --- Fourmi/spiders/Chemspider.py | 7 ++++--- Fourmi/spiders/Wikipedia.py | 7 ++++--- 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/Fourmi/spiders/Chemspider.py b/Fourmi/spiders/Chemspider.py index 3fc74a0..b85b44d 100644 --- a/Fourmi/spiders/Chemspider.py +++ b/Fourmi/spiders/Chemspider.py @@ -3,9 +3,10 @@ from scrapy.spider import Spider class ChemspiderSpider(Spider): name = "Chemspider" allowed_domains = ["chemspider.com"] - start_urls = ( - 'http://www.chemspider.com/', - ) + + def __init__(self, compound=None, *args, **kwargs): + super(ChemspiderSpider, self).__init__(*args, **kwargs) + self.start_urls = ["http://chemspiderapiurl/something/%s" % compound] #[TODO] - Give an logical start url. def parse(self, response): pass diff --git a/Fourmi/spiders/Wikipedia.py b/Fourmi/spiders/Wikipedia.py index 03b202b..62ed026 100644 --- a/Fourmi/spiders/Wikipedia.py +++ b/Fourmi/spiders/Wikipedia.py @@ -3,9 +3,10 @@ from scrapy.spider import Spider class WikipediaSpider(Spider): name = "Wikipedia" allowed_domains = ["wikipedia.org"] - start_urls = ( - 'http://www.wikipedia.org/', - ) + + def __init__(self, compound=None, *args, **kwargs): + super(WikipediaSpider, self).__init__(*args, **kwargs) + self.start_urls = ["http://wikipediaurl/something/%s" % compound] #[TODO] - Give an logical start url. def parse(self, response): pass