一. 思路概述

1.拉勾網采用Ajax技術，加載網頁時會向后端發送Ajax異步請求，因此首先找到數據接口；

2.后端會返回json的數據，分析數據，找到單個招聘對應的positionId，拼接出具體的url；

3.解析url，使用xpath獲取數據。

二. 分析數據接口

三. 詳細代碼

#encoding: utf-8import requests
from lxml import etree
import time
import reheaders = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36',"Referer": 'https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput=',"Cookie": 'user_trace_token=20200524155122-083f0df9-307f-44ee-8266-fceb6af1028b; _ga=GA1.2.728245592.1590306686; LGUID=20200524155125-3d15f82a-9111-4024-98da-9c1422b856dd; JSESSIONID=ABAAAECABFAACEA42866F7C54F46B971C0B595641303F73; WEBTJ-ID=20200524155129-17245aa50d74ec-0946ac3961652a-f7d1d38-1327104-17245aa50d980; RECOMMEND_TIP=true; _gid=GA1.2.369120051.1590306690; index_location_city=%E5%8C%97%E4%BA%AC; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2217245aab6d623b-09a44787242115-f7d1d38-1327104-17245aab6d7237%22%2C%22%24device_id%22%3A%2217245aab6d623b-09a44787242115-f7d1d38-1327104-17245aab6d7237%22%7D; sajssdk_2015_cross_new_user=1; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1590306685,1590324851; LGSID=20200524205410-e3cbacc7-ae0f-4d56-a775-67d45085e31d; PRE_UTM=m_cf_cpt_baidu_pcbt; PRE_HOST=sp0.baidu.com; PRE_SITE=https%3A%2F%2Fsp0.baidu.com%2F9q9JcDHa2gU2pMbgoY3K%2Fadrc.php%3Ft%3D06KL00c00fA1VH%5F0w3dM0FNkUsKEU%5FGX00000rUBx7C00000xs000y.THL0oUhY1x60UWY3rj04n1cdnNtzndqCmyqxTAT0T1dhmymYmhm1P10snH6dmvR10ZRqfbwDfHuDPWnsnRP7f1uDPbfLrDc1rHPDPjfknY7ArjD0mHdL5iuVmv-b5Hn1PWRzP1DYnHThTZFEuA-b5HDv0ARqpZwYTZnlQzqLILT8UA7MULR8mvqVQvk9UhwGUhTVTA7Muiqsmzq1uy7zmv68pZwVUjqdIAdxTvqdThP-5ydxmvuxmLKYgvF9pywdgLKWmMf0mLFW5HR4PWRs%26tpl%3Dtpl%5F11534%5F22672%5F17382%26l%3D1518133990%26attach%3Dlocation%253D%2526linkName%253D%2525E6%2525A0%252587%2525E5%252587%252586%2525E5%2525A4%2525B4%2525E9%252583%2525A8-%2525E6%2525A0%252587%2525E9%2525A2%252598-%2525E4%2525B8%2525BB%2525E6%2525A0%252587%2525E9%2525A2%252598%2526linkText%253D%2525E3%252580%252590%2525E6%25258B%252589%2525E5%25258B%2525BE%2525E6%25258B%25259B%2525E8%252581%252598%2525E3%252580%252591%2525E5%2525AE%252598%2525E6%252596%2525B9%2525E7%2525BD%252591%2525E7%2525AB%252599%252520-%252520%2525E4%2525BA%252592%2525E8%252581%252594%2525E7%2525BD%252591%2525E9%2525AB%252598%2525E8%252596%2525AA%2525E5%2525A5%2525BD%2525E5%2525B7%2525A5%2525E4%2525BD%25259C%2525EF%2525BC%25258C%2525E4%2525B8%25258A%2525E6%25258B%252589%2525E5%25258B%2525BE%21%2526xp%253Did%28%252522m3365271417%5Fcanvas%252522%29%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FH2%25255B1%25255D%25252FA%25255B1%25255D%2526linkType%253D%2526checksum%253D154%26ie%3Dutf-8%26f%3D8%26tn%3D88093251%5F23%5Fhao%5Fpg%26wd%3D%25E6%258B%2589%25E5%258B%25BE%25E7%25BD%2591%26oq%3D%25E6%258B%2589%25E5%258B%25BE%25E7%25BD%2591%26rqlang%3Dcn; PRE_LAND=https%3A%2F%2Fwww.lagou.com%2Flanding-page%2Fpc%2Fsearch.html%3Futm%5Fsource%3Dm%5Fcf%5Fcpt%5Fbaidu%5Fpcbt; TG-TRACK-CODE=index_search; X_HTTP_TOKEN=50fc797f56a45533494523095182b5415766d31319; _gat=1; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1590325496; LGRID=20200524210515-c04502d0-30cb-4056-bbd3-4d96e0564e1e; SEARCH_ID=00630409e0a54ce59315f7af9b9fcce1','Origin': 'https://www.lagou.com',"X-Anit-Forge-Code": "0","X-Anit-Forge-Token": "None",'X-Requested-With': "XMLHttpRequest"
}def request_list_page():url = 'https://www.lagou.com/jobs/positionAjax.json?city=%E5%8C%97%E4%BA%AC&needAddtionalResult=false'data = {'first': "false",'pn': 1,'kd': 'python'}for x in range(1,21):data['pn'] = xresponse = requests.post(url, headers=headers, data=data)# print(type(response))# json方法：如果返回來的是json數據。那么這個方法會自動的load成字典result = response.json()# print(result)positions = result['content']['positionResult']['positionId']for position in positions:positionId = position['positionId']position_url = 'https://www.lagou.com/jobs/%s.html' % positionIdprint(position_url)parse_postion_detail(position_url)breakbreakdef parse_postion_detail(url):positions = []response = requests.get(url,headers=headers)text = response.texthtml = etree.HTML(text)position_name = html.xpath("//span[@class='name']/text()")[0]job_request_spans = html.xpath("//dd[@class='job_request']//span")salary = job_request_spans[0].xpath('.//text()')[0].strip()city = job_request_spans[1].xpath(".//text()")[0].strip()city = re.sub(r"[\s/]","",city)work_years = job_request_spans[2].xpath(".//text()")[0].strip()work_years = re.sub(r"[\s/]","",work_years)education = job_request_spans[3].xpath(".//text()")[0].strip()education = re.sub(r"[\s/]","",education)desc = "".join(html.xpath("//dd[@class='job_bt']//text()")).strip()position = {'name': position_name,'salary': salary,'city': city,'work_years': work_years,'education': education,'desc': desc}positions.append(position)print(position)print('=' * 40)def main():request_list_page()if __name__ == '__main__':main()