Archived
1
0
This repository has been archived on 2025-03-03. You can view files and clone it, but cannot push or open issues or pull requests.

13 lines
405 B
Python

from scrapy.spider import Spider
class WikipediaSpider(Spider):
name = "Wikipedia"
allowed_domains = ["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