c#實(shí)現(xiàn)網(wǎng)頁(yè)圖片提取工具代碼分享
public Array MatchHtml(string html,string com)
{
List<string> urls = new List<string>();
html = html.ToLower();
//獲取SRC標(biāo)簽中的URL
Regex regexSrc = new Regex("src=\"[^\"]*[(.jpg)(.png)(.gif)(.bmp)(.ico)]\"");
foreach(Match m in regexSrc.Matches(html))
{
string src = m.Value;
src = src.Replace("src=","").Replace("\"","");
if (!src.Contains("http"))
src = com + src;
if(!urls.Contains(src))
urls.Add(src);
}
//獲取HREF標(biāo)簽中URL
Regex regexHref = new Regex("href=\"[^\"]*[(.jpg)(.png)(.gif)(.bmp)(.ico)]\"");
foreach (Match m in regexHref.Matches(html))
{
string href = m.Value;
href = href.Replace("href=", "").Replace("\"", "");
if (!href.Contains("http"))
href = com + href;
if(!urls.Contains(href))
urls.Add(href);
}
return urls.ToArray();
}
[DllImport("kernel32.dll")]
static extern bool SetConsoleMode(IntPtr hConsoleHandle, int mode);
[DllImport("kernel32.dll")]
static extern bool GetConsoleMode(IntPtr hConsoleHandle, out int mode);
[DllImport("kernel32.dll")]
static extern IntPtr GetStdHandle(int handle);
const int STD_INPUT_HANDLE = -10;
const int ENABLE_QUICK_EDIT_MODE = 0x40 | 0x80;
public static void EnableQuickEditMode()
{
int mode; IntPtr handle = GetStdHandle(STD_INPUT_HANDLE);
GetConsoleMode(handle, out mode);
mode |= ENABLE_QUICK_EDIT_MODE;
SetConsoleMode(handle, mode);
}
static void Main(string[] args)
{
EnableQuickEditMode();
int oldCount = 0;
Console.Title = "TakeImageFromInternet";
string path = "E:\\Download\\loading\\";
while (true)
{
Console.Clear();
string countFile = "E:\\CountFile.txt";//用來(lái)計(jì)數(shù)的文本,以至于文件名不重復(fù)
int cursor = 0;
if (File.Exists(countFile))
{
string text = File.ReadAllText(countFile);
try
{
cursor =oldCount = Convert.ToInt32(text);//次數(shù)多了建議使用long
}
catch { }
}
Console.Write("please input a url:");
string url = "http://www.baidu.com/";
string temp = Console.ReadLine();
if (!string.IsNullOrEmpty(temp))
url = temp;
Match mcom = new Regex(@"^(?i)http://(\w+\.){2,3}(com(\.cn)?|cn|net)\b").Match(url);//獲取域名
string com = mcom.Value;
//Console.WriteLine(mcom.Value);
Console.Write("please input a save path:");
temp = Console.ReadLine();
if (Directory.Exists(temp))
path = temp;
Console.WriteLine();
WebClient client = new WebClient();
byte[] htmlData = null;
htmlData = client.DownloadData(url);
MemoryStream mstream = new MemoryStream(htmlData);
string html = "";
using (StreamReader sr = new StreamReader(mstream))
{
html = sr.ReadToEnd();
}
Array urls = new MatchHtmlImageUrl().MatchHtml(html,com);
foreach (string imageurl in urls)
{
Console.WriteLine(imageurl);
byte[] imageData = null;
try
{
imageData = client.DownloadData(imageurl);
}
catch { }
if (imageData != null && imageData.Length>0)
using (MemoryStream ms = new MemoryStream(imageData))
{
try
{
string ext = Aping.Utility.File.FileOpration.ExtendName(imageurl);
ImageFormat format = ImageFormat.Jpeg;
switch (ext)
{
case ".jpg":
format = ImageFormat.Jpeg;
break;
case ".bmp":
format = ImageFormat.Bmp;
break;
case ".png":
format = ImageFormat.Png;
break;
case ".gif":
format = ImageFormat.Gif;
break;
case ".ico":
format = ImageFormat.Icon;
break;
default:
continue;
}
Image image = new Bitmap(ms);
if (Directory.Exists(path))
image.Save(path + "\\" + cursor + ext, format);
}
catch(Exception ex) { Console.WriteLine(ex.Message); }
}
cursor++;
}
mstream.Close();
File.WriteAllText(countFile, cursor.ToString(), Encoding.UTF8);
Console.WriteLine("take done...image count:"+(cursor-oldCount).ToString());
}
}
相關(guān)文章
Unity實(shí)現(xiàn)移動(dòng)物體到鼠標(biāo)點(diǎn)擊位置
這篇文章主要為大家詳細(xì)介紹了Unity實(shí)現(xiàn)移動(dòng)物體到鼠標(biāo)點(diǎn)擊位置,文中示例代碼介紹的非常詳細(xì),具有一定的參考價(jià)值,感興趣的小伙伴們可以參考一下2020-08-08C#創(chuàng)建Windows服務(wù)與服務(wù)的安裝、卸載
這篇文章介紹了C#創(chuàng)建Windows服務(wù)與服務(wù)的安裝、卸載,對(duì)大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價(jià)值,需要的朋友們下面隨著小編來(lái)一起學(xué)習(xí)學(xué)習(xí)吧2022-02-02c# 在windows服務(wù)中 使用定時(shí)器實(shí)例代碼
這篇文章主要介紹了c# 在windows服務(wù)中 使用定時(shí)器實(shí)例代碼,有需要的朋友可以參考一下2013-12-12WCF實(shí)現(xiàn)進(jìn)程間管道通信Demo分享
下面小編就為大家分享一篇WCF實(shí)現(xiàn)進(jìn)程間管道通信Demo,具有很好的參考價(jià)值,希望對(duì)大家有所幫助。一起跟隨小編過(guò)來(lái)看看吧2017-12-12C# 批量生成隨機(jī)密碼必須包含數(shù)字和字母并用加密算法加密
這篇文章主要介紹了C# 批量生成隨機(jī)密碼必須包含數(shù)字和字母并用加密算法加密,需要的朋友參考下2017-01-01