油猴脚本开发详解+油猴爬虫脚本实例

*   大量的脚本资源
*   拥有可以从 Github 中进行脚本同步的功能
*   非常活跃的开放源代码发展模式

// ==UserScript==
// @name         New Userscript
// @namespace    http://tampermonkey.net/
// @version      0.1
// @description  try to take over the world!
// @author       You
// @match        https://newtab.firefoxchina.cn/newtab/as/activity-stream.html
// @grant        none
// ==/UserScript==

(function() {
    'use strict';

    // Your code here...
})();

// @include http://www.tampermonkey.net/*
// @include http://*
// @include https://*
// @include /^https://www.tampermonkey.net/.*$/ // @include *`

// @require https://code.jquery.com/jquery-2.1.4.min.js
// @require https://code.jquery.com/jquery-2.1.3.min.js#sha256=23456...
// @require https://code.jquery.com/jquery-2.1.2.min.js#md5=34567...,sha256=6789...
// @require tampermonkey://vendor/jquery.js
// @require tampermonkey://vendor/jszip/jszip.js`

// @resource icon1 http://www.tampermonkey.net/favicon.ico
// @resource icon2 /images/icon.png
// @resource html http://www.tampermonkey.net/index.html
// @resource xml http://www.tampermonkey.net/crx/tampermonkey.xml
// @resource SRIsecured1 http://www.tampermonkey.net/favicon.ico#md5=123434...
// @resource SRIsecured2 http://www.tampermonkey.net/favicon.ico#md5=123434...;sha256=234234...

// @connect <value>

*   域名可以是类似：tampermokey.net（这种可以允许子域名）
*   子域名可以类似：safari.tampermokey.net
*   self：可以将脚本当前运行的域列入白名单
*   localhost：访问本机地址
*   IP地址，类似：1.2.3.4

// @run-at document-start

// @run-at document-body

// @run-at document-end

// @run-at context-menu

// @grant GM_setValue
// @grant GM_getValue
// @grant GM_setClipboard
// @grant unsafeWindow
// @grant window.close
// @grant window.focus
// @grant window.onurlchange

// @grant    GM_addStyle

GM_addStyle(`html body{background-image: url(https://img-blog.csdnimg.cn/20191109172245482.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9maXp6ei5ibG9nLmNzZG4ubmV0，size_16,color_FFFFFF,t_70)`)

*   GM_setValue(key,value) 向 storage 中存储一个键值对，键为key，值为value
*   GM_getValue(key) 从 storage 中获取 key 的值
*   GM_listValues() 列出 storage 所有的值
*   GM_deleteValue(key) 从 storage 中删除 key 的值

// @grant        GM_setValue
// @grant        GM_getValue
// @grant        GM_deleteValue
// @grant        GM_listValues

GM_setValue('time1', '2019年11月10日11:43:28')
GM_setValue('time2', '2019年11月10日11:43:41')
console.log('获取time',GM_getValue('time')
console.log('storage中所有的值',GM_listValues())
GM_deleteValue('time1')
console.log('获取time1',GM_getValue('time1')
console.log('storage中所有的值',GM_listValues())

*  active：判断是否聚焦到新标签页
*  insert：在当前标签后面添加新标签
*  setParent：在标签关闭后重新聚焦当前标签
*  incognito：在隐私窗口下打开标签
*  loadInBackground：该参数与 active 参数的意义相反

// @grant GM_openInTab

GM_openInTab('https://www.baidu.com/', {active: true, insert: true, setParent:true})

// ==UserScript==
// @name         BoSSCookie
// @namespace    http://tampermonkey.net/
// @version      0.1
// @description  try to take over the world!
// @author       挖掘机小王子 微信:EnjoyByte
// @match        https://www.zhipin.com/*
// @grant        GM_xmlhttpRequest
// @run-at       document-start
// ==/UserScript==
(function() {
    'use strict';
    // Your code here...
    console.log(document.cookie)
    GM_xmlhttpRequest({
        method: "POST",
        url: 'http://127.0.0.1:7890/cookie',
        data: JSON.stringify(document.cookie),
        headers: { "Content-Type": "application/x-www-form-urlencoded" },
        onload: function(res){
            if(res.status === 200){
                console.log('Cookie发送成功')
            }else{
                console.log('Cookie发送失败')
                console.log(res)
            }
        },
        onerror : function(err){
            console.log('发生error')
            console.log(err)
        }
})
})();

from flask import Flask, request
app = Flask(__name__)


@app.route('/cookie', methods=['POST'])
def server_cookie():
    print(request.form)
    return 'Hello, World!'


if __name__ == '__main__':
    app.run(host='127.0.0.1', port=7890, debug=True)

import requests

class BoSSHoooCookie:
    def __init__(self):
        self.url = 'https://www.zhipin.com/c101280600/?query=%E5%89%8D%E7%AB%AF&page=4&ka=page-4'
        self.headers = {
            "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
             "accept-encoding": "gzip, deflate, br",
             "accept-language": "zh-CN,zh;q=0.9",
             "cache-control": "no-cache",
             "cookie": "lastCity=101280600; __g=-; Hm_lvt_194df3105ad7148dcf2b98a91b5e727a=1601108486,1602903650; __fid=fdd68354478c855dc66fc83074d7f503; __c=1602903650; __l=l=%2Fwww.zhipin.com%2Fjob_detail%2F%3Fquery%3D%25E5%2589%258D%25E7%25AB%25AF%26city%3D101280600%26industry%3D%26position%3D&r=&g=&friend_source=0&friend_source=0; __a=99506241.1597201399.1601108486.1602903650.36.5.8.36; Hm_lpvt_194df3105ad7148dcf2b98a91b5e727a=1602904819; __zp_stoken__=c1b6bKTIIG2I4NyFNHwREOEoJYVhYCwdTEyFfaWB3Zm0ZeD8jfXdhdSJ0E1R8RgVrNl1NRFB5ZglHO0APH2AGJT06KGoaaytaQnR%2BFDB5MlIbUT0JHFA3cldHOSY9CWMQMAxHV20GF303GAlsYQ%3D%3D; __zp_sseed__=PRWqNrACX/fbo2VFHSO1EBc2jZfQZTwMEcxix0w90Ro=; __zp_sname__=ec3b257b; __zp_sts__=1602904820323",
             "pragma": "no-cache",
             "referer": "https://www.zhipin.com/c101280600/?query=%E5%89%8D%E7%AB%AF&page=3&ka=page-3",
             "sec-fetch-dest": "document",
             "sec-fetch-mode": "navigate",
             "sec-fetch-site": "same-origin",
             "upgrade-insecure-requests": "1",
             "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36",
 }
    def hook(self):
        response = requests.get(self.url, headers=self.headers)
        print(response.status_code)
        print(response.text)
        return response
        
if __name__ == '__main__':
    boSS = BoSSHoooCookie()
    boSS.hook()

// ==UserScript==
// @name         药监局AjaxHook
// @namespace    http://tmpermonkey.net/
// @version      0.1
// @description  try to take over the world!
// @author       挖掘机小王子
// @match        http://app1.nmpa.gov.cn/datasearchcnda/face3/*
// @grant        none
// @require      https://unpkg.com/ajax-hook@2.0.3/dist/ajaxhook.min.js
// ==/UserScript==

ah.proxy({
    //请求发起前进入
    onRequest: (config, handler) => {
        console.log(config.url)
        handler.next(config);
    },
    //请求发生错误时进入，比如超时；注意，不包括http状态码错误，如404仍然会认为请求成功
    onError: (err, handler) => {
        console.log(err.type)
        handler.next(err)
    },
    //请求成功后进入
    onResponse: (response, handler) => {
        console.log(response.response)
        handler.next(response)
    }
})

// ==UserScript==
// @name         药监局列表页数据采集
// @namespace    http://tampermonkey.net/
// @version      0.3.7.4
// @description  try to take over the world!
// @author       挖掘机小王子
// @match        http://app1.sfda.gov.cn/datasearchcnda/face3/*
// @grant        none
// ==/UserScript==

(function() {
    'use strict';
    // Your code here...
    // 触发请求
    function triggerRequest() {

        // 点击
        var interval = null
        var response = null
        interval = setInterval(function () {
            parseResponse() // 获取响应并且发出到Redis
            // 检测是否需要翻页
            if (startPage <= endPage){
                devPage(startPage++) // 翻页
            }
            else {
                clearInterval(interval) // 结束
            }
        }, 500);

    }
    // 响应解析
    function parseResponse(){
        var res = null
        res = document.querySelectorAll('tbody tr p a').forEach((item)=>{httpPost('http://127.0.0.1:8883/ajaxHook', item.href)});
    }
    // 发出响应
    function httpPost(url, data) {
        fetch(url, {
            method: 'POST',
            mode: "cors",
            body: data
        });
    };
    var scope = '';
    scope = prompt('请输入采集的页数范围，示例格式：100-200')
    var startPage = parseInt(scope.split('-')[0]) // 开始页数
    var endPage = parseInt(scope.split('-')[1]) // 结束页数
    // 执行触发
    triggerRequest()
})();

// ==UserScript==
// @name         药监局Hook6SQk6G2z
// @namespace    http://tampermonkey.net/
// @version      0.1
// @description  try to take over the world!
// @author       挖掘机小王子 微信：EnjoyByte
// @match        http://app1.nmpa.gov.cn/data_nmpa/face3/*
// @run-at       document-start
// ==/UserScript==

(function() {
    'use strict';
    // WebSockets
    var ws = new WebSocket("ws://127.0.0.1:8765");
    // 客户端连接服务成功时触发
    ws.onopen = function() {
        console.log('客户端已连接！');
        ws.send("客户端已连接！")
    }
    // 服务端发送消息过来触发
    ws.onmessage = function(evt){
        console.log('服务端信息:', evt.data)
    }
    // 客户端关闭触发
    ws.onclose = function(){
        console.log('客户端关闭！')
        clearInterval(intervalid)
    }
    // 客户端出错触发
    ws.onerror = function(evt){
        console.log("触发失败:", evt)
    }
    // Hook Url
    var open = window.XMLHttpRequest.prototype.open;
    window.XMLHttpRequest.prototype.open = function open(method, url) {
        // Hook URL
        console.log(url)
        ws.send(JSON.stringify({"url": url}))
    };
    // 不断触发下一页事件的请求
    var intervalid = setInterval('devPage(2);', 500)
})();

import asyncio
import websockets
from redis import StrictRedis


class WsServer:

    def __init__(self, redis_host='127.0.0.1', redis_port=6379):
        self.redis_cli = StrictRedis(
            host=redis_host,
            port=redis_port,
            decode_responses=True
        )

    #  WebSocket 服务
    async def server(self, websocket, path):
        while True:
            url_cookie_form_data = await websocket.recv()  # 不断获取浏览器数据
            print(url_cookie_form_data)
            if 'http:' in url_cookie_form_data:
                self.redis_cli.lpush("nmpa:urls", url_cookie_form_data)

if __name__ == '__main__':
    wsserver = WsServer()
    start_server = websockets.serve(wsserver.server, "127.0.0.1", 8765)
    asyncio.get_event_loop().run_until_complete(start_server)
    asyncio.get_event_loop().run_forever()