//我们拿下载图片举个例子
static WebClient client = new WebClient();
class Program
{
static WebClient client = new WebClient();
static void Main(string[] args)
{
string[] str = GetHvtImgUrls(@"http://www.imooc.com/");//下载地址
string url = "";
for (int i = 0; i < str.Length; i++)
{
url = str[i];
if (url.EndsWith(".jpg"))//判断是否是以jpg来结尾的
{
if (!url.Contains("http:"))//判断是不是以hppt:开头的
{
url = "http:" + url;
}
string filepath = @"D:\path练习\" + Guid.NewGuid() + ".jpg";
client.DownloadFile(url, filepath);
}
}
}
/// <summary>
/// 取得HTML中所有图片的 URL。
/// </summary>
/// <param name="sHtmlText">HTML代码</param>
/// <returns>图片的URL列表</returns>
public static string[] GetHvtImgUrls(string url)
{ string content = client.DownloadString(url);//获取返回的信息
// 定义正则表达式用来匹配 img 标签 (正则表达式很多,若想了解跟多欢迎点击https://baike.baidu.com/item/%E6%AD%A3%E5%88%99%E8%A1%A8%E8%BE%BE%E5%BC%8F/1700215?fr=aladdin)
Regex m_hvtRegImg = new Regex(@"<img\b[^<>]*?\bsrc[\s\t\r\n]*=[\s\t\r\n]*[""']?[\s\t\r\n]*(?<imgUrl>[^\s\t\r\n""'<>]*)[^<>]*?/?[\s\t\r\n]*>", RegexOptions.IgnoreCase);
// 搜索匹配的字符串
MatchCollection matches = m_hvtRegImg.Matches(content);
int m_i = 0;
string[] sUrlList = new string[matches.Count];
// 取得匹配项列表
foreach (Match match in matches)
sUrlList[m_i++] = match.Groups["imgUrl"].Value;
return sUrlList;
}