FCS/FCS.Crawler/Content/Base/Tools/CommonMethod.cs

using FCS.Common;
using HtmlAgilityPack;
using System;
using System.IO;
using System.Net;
using System.Text;
using System.Text.RegularExpressions;

namespace FCS.Crawler.Tools
{
    public class CommonMethod
    {
        #region 获取全局唯一GUID

        /// <summary>
        /// 获取全局唯一GUID
        /// </summary>
        /// <param name="needReplace">是否需要替换-</param>
        /// <param name="format">格式化</param>
        /// <example>N：38bddf48f43c48588e0d78761eaa1ce6</example>>
        /// <example>P：(778406c2-efff-4262-ab03-70a77d09c2b5)</example>>
        /// <example>B：{09f140d5-af72-44ba-a763-c861304b46f8}</example>>
        /// <example>D：57d99d89-caab-482a-a0e9-a0a803eed3ba</example>>
        /// <returns></returns>
        public static string GetGuid(bool needReplace = true, string format = "N")
        {
            Guid res = NewSequentialGuid();//Guid.NewGuid();

            return needReplace ? res.ToString(format) : res.ToString();
        }

        [System.Runtime.InteropServices.DllImport("rpcrt4.dll", SetLastError = true)]
        private static extern int UuidCreateSequential(byte[] buffer);

        internal static object GetUrl(string Url)
        {
            string js = "";
            HtmlNode node = null;
            var htmlResource = NetHelper.GetUrlResponse(Url, Encoding.GetEncoding("utf-8"));
            js = GetJs(htmlResource);
            return js;
        }

        /// <summary>
        /// 创建有序GUID
        /// </summary>
        /// <returns></returns>
        private static Guid NewSequentialGuid()
        {
            byte[] raw = new byte[16];
            if (UuidCreateSequential(raw) != 0)
                throw new System.ComponentModel.Win32Exception(System.Runtime.InteropServices.Marshal.GetLastWin32Error());

            byte[] fix = new byte[16];

            // 反转 0..3
            fix[0x0] = raw[0x3];
            fix[0x1] = raw[0x2];
            fix[0x2] = raw[0x1];
            fix[0x3] = raw[0x0];

            // 反转 4 & 5
            fix[0x4] = raw[0x5];
            fix[0x5] = raw[0x4];

            // 反转 6 & 7
            fix[0x6] = raw[0x7];
            fix[0x7] = raw[0x6];

            // 后8位不做操作，实际为当前MAC地址
            fix[0x8] = raw[0x8];
            fix[0x9] = raw[0x9];
            fix[0xA] = raw[0xA];
            fix[0xB] = raw[0xB];
            fix[0xC] = raw[0xC];
            fix[0xD] = raw[0xD];
            fix[0xE] = raw[0xE];
            fix[0xF] = raw[0xF];

            return new Guid(fix);
        }

        #endregion 获取全局唯一GUID

        #region 常用的html获取js

        /// <summary>
        /// 根据htmL获取Js
        /// </summary>
        /// <param name="Url"></param>
        /// <returns></returns>
        public static string GetUrl()
        {
            string js = "";
            HtmlNode node = null;
            var htmlResource = NetHelper.GetUrlResponse("", Encoding.GetEncoding("utf-8"));
            js = GetJs(htmlResource);
            return js;
        }

        public static string GetJs(string html)
        {
            string js1 = "";
            //正则表达式获取jsData后面的js
            Regex r1 = new Regex(@"jsData/(\w|\W)*?"">");
            MatchCollection m1 = r1.Matches(html);
            foreach (Match item in m1)
            {
                js1 = item.Value.Replace("\">", "");
            }

            if (string.IsNullOrEmpty((js1)))
            {
                return "";
            }
            else
            {
                return js1;
            }
        }

        #endregion 常用的html获取js

        #region 根据htmL获取Js

        public static string HttpJs(string url)
        {
            WebRequest req = WebRequest.Create(url);
            WebResponse resp = req.GetResponse();
            StreamReader reader = new StreamReader(resp.GetResponseStream(), Encoding.UTF8);
            string html = reader.ReadToEnd();
            return html;
        }

        #endregion 根据htmL获取Js
    }
}