本文章中所有内容仅供学习交流，严禁用于商业用途和非法用途，否则由此产生的一切后果均与作者无关，若有侵权，请私信我立即删除！
aHR0cHM6Ly93ZS41MWpvYi5jb20vcGMvc2VhcmNoP2tleXdvcmQ9amF2YSZzZWFyY2hUeXBlPTImc29ydFR5cGU9MCZtZXRybz0=
看到了熟悉的acw_sc__v2，不熟悉的推荐之前写的两篇文章：
不出意外第一次请求应该是设置acw_sc__v2
这个acw_sc__v2很多网站的算法都是通用的，我们可以直接用之前的代码，也可以自己跟跟看。
acw_sc__v2 生成js:
window = {};
var arg3 = null;
var arg4 = null;
var arg5 = null;
var arg6 = null;
var arg7 = null;
var arg8 = null;
var arg9 = null;
var arg10 = null;
var l = function (arg1) {
while (window["_phantom"] || window["__phantomas"]) {}
var _0x5e8b26 = "3000176000856006061501533003690027800375";
String["prototype"]["hexXor"] = function (_0x4e08d8) {
var _0x5a5d3b = "";
for (var _0xe89588 = 0; _0xe89588 < this["length"] && _0xe89588 < _0x4e08d8["length"]; _0xe89588 += 2) {
var _0x401af1 = parseInt(this["slice"](_0xe89588, _0xe89588 + 2), 16);
var _0x105f59 = parseInt(_0x4e08d8["slice"](_0xe89588, _0xe89588 + 2), 16);
var _0x189e2c = (_0x401af1 ^ _0x105f59)["toString"](16);
if (_0x189e2c["length"] == 1) {
_0x189e2c = "0" + _0x189e2c;
}
_0x5a5d3b += _0x189e2c;
}
return _0x5a5d3b;
};
String["prototype"]["unsbox"] = function () {
var _0x4b082b = [15, 35, 29, 24, 33, 16, 1, 38, 10, 9, 19, 31, 40, 27, 22, 23, 25, 13, 6, 11, 39, 18, 20, 8, 14, 21, 32, 26, 2, 30, 7, 4, 17, 5, 3, 28, 34, 37, 12, 36];
var _0x4da0dc = [];
var _0x12605e = "";
for (var _0x20a7bf = 0; _0x20a7bf < this["length"]; _0x20a7bf++) {
var _0x385ee3 = this[_0x20a7bf];
for (var _0x217721 = 0; _0x217721 < _0x4b082b["length"]; _0x217721++) {
if (_0x4b082b[_0x217721] == _0x20a7bf + 1) {
_0x4da0dc[_0x217721] = _0x385ee3;
}
}
}
_0x12605e = _0x4da0dc["join"]("");
return _0x12605e;
};
var _0x23a392 = arg1["unsbox"]();
arg2 = _0x23a392["hexXor"](_0x5e8b26);
console.log('arg2==>',arg2)
// setTimeout("reload(arg2)", 2);
return arg2
};
// var arg1 = "FAA6CB46CF724D58FF82E5310687947623413114";
// l(arg1)
# -*- coding: UTF-8 -*-
import time
import uuid
import requests
import re
import json
import execjs
headers = {
'Accept': 'application/json, text/plain, */*',
'Accept-Language': 'zh',
'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
'From-Domain': '51job_web',
'Pragma': 'no-cache',
'Referer': 'https://we.51job.com/pc/search?keyword=java&searchType=2&sortType=0&metro=',
'Sec-Fetch-Dest': 'empty',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'same-origin',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
'account-id': '',
'partner': '',
'property': '%7B%22partner%22%3A%22%22%2C%22webId%22%3A2%2C%22fromdomain%22%3A%2251job_web%22%2C%22frompageUrl%22%3A%22https%3A%2F%2Fwe.51job.com%2F%22%2C%22pageUrl%22%3A%22https%3A%2F%2Fwe.51job.com%2Fpc%2Fsearch%3Fkeyword%3Djava%26searchType%3D2%26sortType%3D0%26metro%3D%22%2C%22identityType%22%3A%22%22%2C%22userType%22%3A%22%22%2C%22isLogin%22%3A%22%E5%90%A6%22%2C%22accountid%22%3A%22%22%7D',
'sec-ch-ua': '"Not.A/Brand";v="8", "Chromium";v="114", "Google Chrome";v="114"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"',
'sign': '839932c059141791d8a003f0e6652e14facbf788a502df374fecf9c107d93b9e',
'user-token': '',
'uuid': '1687228791235576552',
}
params = {
'api_key': '51job',
'timestamp': '1687228791',
'keyword': 'java',
'searchType': '2',
'function': '',
'industry': '',
'jobArea': '000000',
'jobArea2': '',
'landmark': '',
'metro': '',
'salary': '',
'workYear': '',
'degree': '',
'companyType': '',
'companySize': '',
'jobType': '',
'issueDate': '',
'sortType': '0',
'pageNum': '1',
'requestId': '',
'pageSize': '20',
'source': '1',
'accountId': '',
'pageCode': 'sou|sou|soulb',
}
# 换成自己的代理，或者不用，单个ip应该有限制
proxies = {
"http":"http://xxx",
"https":"http://xxxx"
}
for i in range(1,3):
try:
# cookie = {'guid': 'd02dfbabd84858301947663946e1710f'}
session = requests.session()
print("第%s次请求：" % i)
response = session.get('https://we.51job.com/api/job/search-pc', params=params,proxies=proxies,headers=headers)
print(response.text[:300])
arg1 = re.findall("arg1='(.*?)';",response.text,re.S)[0]
print('arg1--->',arg1)
guid = str(uuid.uuid4()).replace("-", "")
cookie = {'guid': str(guid)}
with open('04.js', 'r', encoding='utf-8') as f:
js = f.read()
acw_sc__v2 = execjs.compile(js).call('l', arg1)
print('acw_sc__v2-->',acw_sc__v2)
cookie.update({"acw_sc__v2": acw_sc__v2})
# cookie.update({"acw_sc__v3": "649257ebe376df87b3db6a94c1e5ad37f42f783b"})
response2 = session.get('https://we.51job.com/api/job/search-pc', params=params,headers=headers,proxies=proxies,cookies=cookie) #
cookie.update(response2.cookies.get_dict())
response = session.get('https://we.51job.com/api/job/search-pc', params=params,headers=headers,proxies=proxies, cookies=cookie)
print(response.text)
time.sleep(0.5)
except Exception as e:
print(e)
测试结果：
测了一下风控，单个ip用acw_sc__v2请求多了会出滑块验证
过掉滑块，生成acw_sc__v3， cookie携带acw_sc__v3参数请求,使用单个ip
请求1000次还是成功的，再启动一下爬虫就是405响应：
再打开浏览器刷新就是这样：
这种情况就是ip被封掉了，浏览器再切换一下ip
又能正常访问了，确定是ip被限制了。
结论：请求量大的还是堆ip吧【狗头保命】