/// <summary>
/// 获取视频对象
/// </summary>
/// <returns></returns>
public static async Task <List <VideosInfo> > GetVideoInfo(string url)
{
List <VideosInfo> videosInfos = new List <VideosInfo>();
var sourceHtmlDom = await AnalyticalContent.GetHtml(url);
Console.WriteLine("正在获取视频数据……");
var dom = htmlParser.ParseDocument(sourceHtmlDom);
var rows = dom.QuerySelectorAll("div.videos-text-align a");//元素选择器//行
foreach (var item in rows)
{
var videoHref = item.GetAttribute("href");
int _finded = videoHref.LastIndexOf("&page");//移除后面的
if (_finded != -1)
{
videoHref = videoHref.Substring(0, _finded);
}
videosInfos.Add(new VideosInfo {
PageUrl = videoHref,
Duration = item.GetElementsByTagName("span")[0].InnerHtml,
Thumb = item.GetElementsByClassName("img-responsive")[0].GetAttribute("src"),
Title = AnalyticalContent.HtmlToPlainText(item.GetElementsByClassName("video-title title-truncate m-t-5")[0].OuterHtml)
});
}
Console.WriteLine($"获取视频数据完成,共:{videosInfos.Count} 条数据.");
return(videosInfos);
}
private static async Task <Tuple <string, string> > GetVideoUrlFormVideoPage(string url)
{
try {
Thread.Sleep(500);
var sourceHtmlDom = await AnalyticalContent.GetHtml(url);
var dom = htmlParser.ParseDocument(sourceHtmlDom);
var videoHeader = dom.QuerySelectorAll("h4.login_register_header"); //元素选择器//行
var elements = dom.QuerySelectorAll("div.video-container video"); //元素选择器//行
var videoTitle = AnalyticalContent.HtmlToPlainText(videoHeader[0].InnerHtml).TrimEnd();
videoTitle = Regex.Replace(videoTitle, @"\s", "");
var content = elements[0].OuterHtml;
var res = DecryptString(GetEncryptionString(content));
res = res.Remove(0, 14); //移除前面定长字符
int _finded = res.LastIndexOf(@"type="); //移除后面的
if (_finded != -1)
{
res = res.Substring(0, _finded);
}
Console.WriteLine(@$ "获取视频成功：{videoTitle} : {res}");
return(Tuple.Create <string, string>(videoTitle, res));;
} catch (Exception ex) {
Console.WriteLine($"获取视频地址失败,错误:{ex.Message}");
return(null);
}
}
//======================Main Function======================
/// <summary>
/// 中药方剂图像
/// </summary>
private static void GetImageFromWeb2()
{
List <Medicine> medicineList = new List <Medicine>();
int TotalPageId = 46;//总共页数
if (!System.IO.Directory.Exists(MTsFilePath))
{
System.IO.Directory.CreateDirectory(MTsFilePath);
}
for (int pageId = 1; pageId <= TotalPageId; pageId++)
{
Console.WriteLine($"开始 第 {pageId} 页下载任务.");
#region "构造请求地址"
var Mic_sourceUrl = @$ "https://sys02.lib.hkbu.edu.hk/cmfid/index.asp?query=&lang=chs&pageid={pageId}";
#endregion "构造请求地址"
//加载HTML
var sourceHtmlDom = AnalyticalContent.GetHtml(Mic_sourceUrl);//下载显微鉴别 类型的
//HTML 解析成 IDocument对象
var dom = htmlParser.ParseDocument(sourceHtmlDom);
//解析 提取
#region "提取目标"
var textItems = dom.QuerySelectorAll("table#main_content_tb tbody tr td font a"); //元素选择器
var imgItems = dom.QuerySelectorAll("table#main_content_tb tbody tr td a img"); //元素选择器
Medicine medicine = new Medicine {
text = new List <string>(),
img = new List <string>()
};
for (int i = 0; i < 4; i++)
{
//拿到文字
var txt = textItems[i].InnerHtml;
medicine.text.Add(txt);
//拿到图片地址
var ImgUrl = "https://sys02.lib.hkbu.edu.hk/cmfid/" + imgItems[i].GetAttribute("src");
medicine.img.Add(ImgUrl);
//保存图片
//D:\Documents\ASP.NETCorRoadMap\src\ASP.NETCorRoadMap\ConsoleApp1\bin\Debug\netcoreapp3.1\中药方剂图像\xx.jpg
var oneFileName = txt + Path.GetExtension(ImgUrl);
FinallyPath = Path.Combine(MTsFilePath, oneFileName);
AnalyticalContent.GetImgRes(ImgUrl, FinallyPath);
}
medicineList.Add(medicine);
#endregion "提取目标"
Console.WriteLine($"结束 第 {pageId} 页下载任务.");
Console.WriteLine("===========================================");
}
}
/// <summary>
/// 获取这个字符串:
/// %3c%73%6f%75%72%63%65%20%73%72%63%3d%27%68%74%74%70%73%3a%2f%2f%66%64%63%2e%39%31%70%34%39%2e%63%6f%6d%2f%6d%33%75%38%2f%34%34%34%31%33%39%2f%34%34%34%31%33%39%2e%6d%33%75%38%27%20%74%79%70%65%3d%27%61%70%70%6c%69%63%61%74%69%6f%6e%2f%78%2d%6d%70%65%67%55%52%4c%27%3e
/// </summary>
/// <returns></returns>
private static string GetEncryptionString(string targetStr)
{
var t1 = targetStr.Split("//-->");
var t2 = t1[0].Split(@" <script>
< !--");
var t3 = t2[0].Split("document.write(strencode2(");
var t4 = AnalyticalContent.HtmlToPlainText(t3[1]);
t4 = t4.Replace(@"\", "").Replace(@"n", "").Replace("t", "");
return(t4);
}
/// <summary>
/// 下载歌词
/// </summary>
/// <param name="url">歌词地址</param>
private static string DownloadLyric(string url = "https://www.mulanci.org/lyric/sl105975/")
{
Thread.Sleep(300);
var res = "";
var sourceHtmlDom = AnalyticalContent.GetHtml(url);
var dom = htmlParser.ParseDocument(sourceHtmlDom);
var textItems = dom.QuerySelectorAll("div#lyric-content");//元素选择器 //pb-1
foreach (var item in textItems)
{
var text = item.InnerHtml;
var t1 = text.Replace("<br>", "\r\n");
var sd = t1.IndexOf("<div");
res = t1.Substring(0, sd - 1);
res = res.Replace(" 作词：李志", "作词：李志");
}
return(res);
}
/// <summary>
/// 获取所有歌词地址
/// </summary>
/// <returns></returns>
private List <LyricUrlModel> GetLyricUrls()
{
/**
* 李志( Li Zhi )
* 常用名：逼哥, Li Zhi, 李志
* 共收录20张专辑，203篇歌词。
* **/
Thread.Sleep(300);
var url = "https://www.mulanci.org/lyric/s4127/";
var sourceHtmlDom = AnalyticalContent.GetHtml(url);
var dom = htmlParser.ParseDocument(sourceHtmlDom);
var textItems = dom.QuerySelectorAll("div.pt-1 a");//元素选择器 //pb-1
List <LyricUrlModel> lyricUrlModels = new List <LyricUrlModel>();
foreach (var item in textItems)
{
var songName = item.InnerHtml
.Trim()
.Replace("李志", "")
.Replace("-", "")
.Replace(".", "")
.Replace(" ", "")
.Replace("(2014 Live i / O 版)", "")
.Replace(" ", "");
songName = Regex.Replace(songName, @"\{.*\}", ""); //过滤{}｛｝
songName = Regex.Replace(songName, @"\（.*\）", ""); //过滤{}｛｝
songName = Regex.Replace(songName, @"\(.*\)", ""); //过滤{}｛｝
songName = Regex.Replace(songName, @"\d", "");
lyricUrlModels.Add(new LyricUrlModel {
text = songName,
url = "https://www.mulanci.org/" + item.GetAttribute("href")
});
}
return(lyricUrlModels);
}
/// <summary>
/// 之前的显微鉴别
/// </summary>
private static void GetImageFromWeb()
{
if (!System.IO.Directory.Exists(MTsFilePath))
{
System.IO.Directory.CreateDirectory(MTsFilePath);
}
//有效值001-421
int Count = 421;
string pad = "";
List <string> test = new List <string>();
List <string> test1 = new List <string>();
List <string> test2 = new List <string>();
List <string> test3 = new List <string>();
List <string> test4 = new List <string>();
List <MyData> MyData = new List <MyData>();
//注意
for (int j = 409; j <= Count; j++)
{
Console.WriteLine($"第 {j} 次下载任务.");
MyData data = new MyData();
data.imgs = new List <string>();
#region "构造请求地址"
var sourceUrl = "http://libproject.hkbu.edu.hk/was40/detail?channelid=47953&lang=chs&searchword=pid=B00";
//下载带显微鉴别 的中药 的图片
pad = j.ToString().PadLeft(3, '0');
sourceUrl += pad;
var Mic_sourceUrl = @$ "http://libproject.hkbu.edu.hk/was40/function/cmmid_micro_uat.jsp?id=B00{pad}&lang=chs";
#endregion ""
//加载HTML
var sourceHtmlDom = AnalyticalContent.GetHtml(Mic_sourceUrl);//下载显微鉴别 类型的
//HTML 解析成 IDocument对象
var dom = htmlParser.ParseDocument(sourceHtmlDom);
//解析 提取
#region "提取目标名称"
var fileName = dom.QuerySelectorAll("p.text2");
if (fileName != null)
{
foreach (var p in fileName)
{
var name = AnalyticalContent.HtmlToPlainText(p.InnerHtml);// 沉香 Chenxiang
if (!string.IsNullOrEmpty(name))
{
name = name.Trim();
//"人参 Renshen"
var txtarr = name.Split(' ');
data.text = txtarr[0];
Console.WriteLine($"资源名称: {data.text}");
#region "提取底部文字"
var bottomTxt = dom.QuerySelectorAll("p.text");
if (bottomTxt != null)
{
foreach (var t in bottomTxt)
{
var txt = AnalyticalContent.HtmlToPlainText(t.InnerHtml);// 沉香 Chenxiang
txt = txt.Split("本记录")[0];
txt = txt.Replace(">", "");
var secondDir = Path.Combine(MTsFilePath, data.text);
if (!System.IO.Directory.Exists(secondDir))
{
System.IO.Directory.CreateDirectory(secondDir);
}
var oneFileName = data.text + ".txt";
var fPath = Path.Combine(secondDir, oneFileName);
FileInfo myFile = new FileInfo(fPath);
StreamWriter sw = myFile.CreateText();
string[] strs = { txt };
foreach (var s in strs)
{
sw.WriteLine(s);
}
sw.Close();
//存文本到txt
}
}
#endregion "提取底部文字"
#region "提取目标图片地址"
var image = dom.QuerySelectorAll("img");
if (image != null)
{
int count = 0;
foreach (var item in image)
{
var img = item.OuterHtml; //"<img src=\"images_mmd/trans.png\" height=\"18\">"
if (img.Contains("trsimage/mmd/micro")) //trsimage之前
//目标图片
{
var src = item.GetAttribute("src"); //"../trsimage/mmd/B00421.jpg"
var s = src.Replace("..", "");
var findSrc = "http://libproject.hkbu.edu.hk" + s; //"http://libproject.hkbu.edu.hk/../trsimage/mmd/B00421.jpg"
Console.WriteLine($"资源地址: { findSrc}");
data.imgs.Add(findSrc);
//下载
var secondDir = Path.Combine(MTsFilePath, data.text);
if (!System.IO.Directory.Exists(secondDir))
{
System.IO.Directory.CreateDirectory(secondDir);
}
count++;
var oneFileName = count.ToString() + Path.GetExtension(findSrc);
FinallyPath = Path.Combine(secondDir, oneFileName);
AnalyticalContent.GetImgRes(findSrc, FinallyPath);
}
}
}
#endregion "提取目标图片地址"
}
}
}
#endregion "提取目标名称"
}
}
