scrapy爬取文件

import scrapy
import json

# 执行命令：scrapy crawl qiubai
class QiubaiSpider(scrapy.Spider):
    name = 'qiubai'
    start_urls = ['https://www.baidu.com']

    def parse(self, response):
        id_list = []
        a = 0
        li_list = response.xpath('//*[@id="cnblogs_post_body"]/div')
        for li in li_list:
            author = li.xpath('.//text()').extract()
            author = ''.join(author)
            a += 1
            print( author)
            id_list.append(author)
        fp = open('./qiubai.txt', 'w', encoding='utf-8')
        json.dump(id_list, fp, ensure_ascii=False)