這套程式基於python3 ，使用requests和re正則表示式，只需要將程式儲存為.py檔案後，即可將抓取到的資料儲存到指定路徑的Excel檔案中。程式在終端中啟動，啟動命令：

#python3 檔名.py 關鍵字 城市
python3 zhilian.py python 杭州

程式碼如下：

# coding:utf-8
import requests
import re
import xlwt
import sys,os

workbook = xlwt.Workbook(encoding='utf-8')
booksheet = workbook.add_sheet('Sheet 1'
 
, cell_overwrite_ok=True)


class ZhiLian(object):
    def __init__(self):
        self.start_url = 'https://m.zhaopin.com/{}/?keyword={}&pageindex={}&maprange=3&islocation=0&order=4'
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Linux; Android 5.0; SM-G900P Build/LRX21T) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Mobile Safari/537.36"
 

        }
        self.test_url = '<section class="job-list.*?".*?>.*?<div class="job-name fl ">(.*?)</div>.*?<div class="fl">(.*?)</div>.*?<div class="comp-name fl">(.*?)</div>.*?<span class="ads">(.*?)</span>.*?<div class="time fr">(.*?)</div>'
 

        self.select_city_url = 'https://m.zhaopin.com/searchjob/selectcity'
        self.test_city = ' <a data-code="(.*?)" href="/(.*?)/">(.*?)</a>'

    def parse_url(self, url):
        '''傳送請求'''
        response = requests.get(url, headers=self.headers)
        return response.content.decode()

    def get_data(self, test_url, content):
        '''獲取資料'''

        content_list = re.findall(test_url, content, re.S)
        return content_list

    def get_content(self, content_list, DATA):
        '''提取資料'''
        for content in content_list:
            DATA.append((content[0], content[1], content[2], content[3], content[4]))

    def save_content(self, DATA, city, key_words):
        '''儲存到excel'''
        for i, row in enumerate(DATA):
            for j, col in enumerate(row):
                booksheet.write(i, j, col)
         #判斷儲存的路徑，如果和我的路徑不一樣，會自動儲存到當前程式檔案所在目錄
        if(os.path.isdir('/home/itcast/Desktop/')):
            workbook.save('/home/itcast/Desktop/{}_{}.xls'.format(city,key_words))
        else:
            workbook.save('{}_{}.xls'.format(city, key_words))

    def select_city(self, url, search_city):
        '''選擇城市,返回城市程式碼'''
        city_dict = {}
        city_code = None
        r = requests.get(url, headers=self.headers)
        content = r.content.decode()
        city_content = re.findall(self.test_city, content, re.S)
        # print(city_content)
        # print(len(city_content))
        # 構造一個字典儲存城市資訊
        for city in city_content:
            # '566': ['tangshan', '唐山']
            city_dict[city[0]] = [city[1], city[2]]
        # print(len(city_dict))
        for keys, value in city_dict.items():
            if search_city == value[1]:
                city_code = value[0] + '-' + keys
                # print(city_code)

        return city_code

    def deal_city(self, city):
        '''處理城市資訊'''
        city_code = self.select_city(self.select_city_url, city)
        if city_code == None:
            print("查詢城市不存在，請重試")
            sys.exit()
        return city_code

    def run(self, city, key_words):
        # 1.start_url
        # 2.傳送請求，獲取響應
        i = 1
        DATA = [('崗位', '月薪', '公司', '城市', '釋出時間')]
        city_code = self.deal_city(city)
        while True:

            url = self.start_url.format(city_code, key_words, i)
            content = self.parse_url(url)
            content_list = self.get_data(self.test_url, content)
            self.get_content(content_list, DATA)
            # 儲存資料
            self.save_content(DATA, city, key_words)
            # 判斷是否還有資料 限制儲存最大頁數
            if (len(content_list) == 0 or i>100):
                print("儲存完成,共{}頁資料".format(i - 1))
                break
            print("正在儲存第{}頁資料".format(i))
            i += 1


if __name__ == '__main__':
    key_words = sys.argv[1]
    city = sys.argv[2]
    zhilian = ZhiLian()
    zhilian.run(city, key_words)

爬取結果如下：