python爬虫爬取牛客网面试经验

import requests
from lxml import etree
import re
from bs4 import BeautifulSoup
import random
import time
import os
import threading
from retry import retry



class niuke(object):

    def __init__(self):

        self.url='https://www.nowcoder.com/discuss/tag/{}?type=2&page={}'
        self.headers={"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.92 Safari/537.36"}
        self.prefix='https://www.nowcoder.com'
        self.origin_url='https://www.nowcoder.com/discuss/tags?type=2'

    def get_enterprise(self):

        r=requests.get(self.origin_url,headers=self.headers)
        tree=etree.HTML(r.text)
        enterprise=tree.xpath('//div[@data-nav="企业"]/ul[@class="discuss-tags-mod"]/li/a/@data-href')
        enterprise_name=tree.xpath('//div[@d