import scrapy class DmozSpider(scrapy.Spider): name ="dmoz" allowed_domains = ["dmoz.org"] start_urls = [ "https://dmoztools.net/Computers/Programming/Languages/Python/Resources/" "https://dmoztools.net/Computers/Programming/Languages/Python/Books/" ] def parse(self,response): filename = response.url.split("/")[-2] with open(filename, 'wb') as f: f.write(response.body)
import scrapy class DmozSpider(scrapy.Spider):
阅读背景：
Scrapy：Python实现scrapy框架爬虫两个网址下载网页内容信息——Jason niu
来源：互联网
分享到：
