代码如下：

-- coding: utf-8 --

import scrapy

class LinearSpider(scrapy.Spider): name = "linear" allowed_domains = ["ocw.mit.edu"] start_urls = ['https://ocw.mit.edu/courses/mathematics/18-06sc-linear-algebra-fall-2011/resource-index/']

def parse(self, response):
    page_hrefs = response.xpath("*//tr//td/a/@href").re(".*sum.pdf")
    for href in page_hrefs:
        new_url = 'https://ocw.mit.edu' + href
        print(new_url)
        yield scrapy.Request(new_url,callback=self.parse_href)

def parse_href(self,response):
    with open('linear.pdf','ab') as f:
        f.write(response.body)
        f.close()