需求：智联上找工作的时候，工作地点在搜索页面只能看到城市-区。看不到具体的地址。（离家近的工作肯定优先考虑） 思路：爬取搜索页面（页面一）然后进去其中一个内页，再爬工作地点（页面二），【废话】 利用的库：re，csv，bs4，requests 基本功能已实现。 下一步方向，调取地图api 计算离家距离。 运算速度方面的话，可以考虑多线程处理。

  

 

 

 

 

以下代码拿来就用哈！

import requests from bs4 import BeautifulSoup import re import csv location = "广州" search = "网络工程师" fileName = location + "-" + search + ".csv" with open(fileName, "w", newline="") as datacsv:     csvwriter = csv.writer(datacsv, dialect=("excel"))     # res = requests.get("https://sou.zhaopin.com/jobs/searchresult.ashx?jl=%E4%BD%9B%E5%B1%B1&kw=%E7%BD%91%E7%BB%9C%E5%B7%A5%E7%A8%8B%E5%B8%88&sm=0&p=1")     Url = ("https://sou.zhaopin.com/jobs/searchresult.ashx?jl=%s&kw=%s&sm=0&p=1" % (location, search))     res = requests.get(Url)     res.encoding = 'utf-8'     soup = BeautifulSoup(res.text,'html.parser')     all_work = []     for link in soup.find_all('a'):         if re.search("com/[0-9]*.htm",str(link.get('href'))):             all_work.append(link.get('href'))     for i in all_work:         work = []         res2 = requests.get(i)         res2.encoding = 'utf-8'         soup2 = BeautifulSoup(res2.text,'html.parser')         for z in soup2.find_all("h2"):             work.append((z.get_text()).split()[0])         work_list = str(soup2.get_text()).split()         work_list2 = []         count_y = 0         for y in work_list:             count_y +=1             if "职位月薪" in y:                 work_list2 = work_list[count_y-1:count_y+6]                 for xx in work_list2:                     work.append(xx)                 csvwriter.writerow(work)                 break     datacsv.close()