原文网址:http://blog.csdn.net/yizhiduxiu11/archive/2010/09/ 13/5881442.aspx
首先获得网页的Html代码,然后用正则表达式分析其中图片的下载地址,最后自动逐个下载。
Code
using System.Net;
/**/
/// Download Image from website
/// better to put into threads
///
private void DownloadImage()
{
WebClient c = new WebClient();
//Get html code
string content = c.DownloadString(Uri);
Collection address = new Collection();
Collection name = new Collection();
//Analyse html code to get images address(Uri) and (Name) list
ParseHtml(content, Prefix, PicUriPrefix + @"(?[^""]*?)"">(?[^", address, name);
if (address.Count > 0 && name.Count > 0 && address.Count == name.Count)
{
if (Directory.Exists(folder) == false) Directory.CreateDirectory(folder);//Create folder
foreach (string add in address)
{
//Download images one by one
c.DownloadFile(add, Path.Combine(folder, name[address.IndexOf(add)] + ".jpg"));
}
}
}
/**
/// Parse Html using regular expressions
///
/// Html content
/// Uri prefix
/// regular expression
/// Image addresses collection
/// Image names collection
private void ParseHtml(string content, string prefix, string expression, Collection address, Collection name)
{
if (String.IsNullOrEmpty(expression) || address == null || name == null) return;
Regex re = new Regex(expression, RegexOptions.IgnoreCase | RegexOptions.Singleline | RegexOptions.RightToLeft);
MatchCollection mc = re.Matches(content);
if (mc == null || mc.Count == 0) return;
foreach (Match m in mc)
{
address.Add(prefix + m.Groups["Uri"].Value);
name.Add(m.Groups["Name"].Value);
}
}
Html部分代码如下:
Html code
alt="" src="/docfile/dyn/12345678LANGCCCCDDDDEEEEEEEERT09 ">BMW 3-series\par
alt="" src="/docfile/dyn/12345678LANGCCCCDDDDEEEEEEEEEE01 ">Toyota\par
alt="" src="/docfile/dyn/12345678LANGCCCCDDDDEEEEEEEEJY25 ">Polo cross\par
alt="" src="/docfile/dyn/12345678LANGCCCCDDDDEEEEEEEEMO02 ">Golf 4.5\par
要用正则表达式从中获得图片下载地址(例如:/docfile/dyn/12345678LANGCCCCDDDDEEEEEEEERT09)和图片名称(例如:BMW 3-series)
正则表达式部分如下:
Regular expression
@"/docfile/dyn/(?[^""]*?)"">(?[^"
注意其中group的用法(? *?),和引号的匹配用法,匹配双引号前面需要再带一个双引号。其中Uri这个group在dyn/后面,直到双引号结束;后面跟随着双引号和>,然后就是Name这个group;它以。
本文来自CSDN博客,转载请标明出处:http://blog.csdn.net/yizhiduxiu11/archive/2010/09/ 13/5881442.aspx
首先获得网页的Html代码,然后用正则表达式分析其中图片的下载地址,最后自动逐个下载。
Code
using System.Net;
/**/
/// Download Image from website
/// better to put into threads
///
private void DownloadImage()
{
WebClient c = new WebClient();
//Get html code
string content = c.DownloadString(Uri);
Collection address = new Collection();
Collection name = new Collection();
//Analyse html code to get images address(Uri) and (Name) list
ParseHtml(content, Prefix, PicUriPrefix + @"(?[^""]*?)"">(?[^", address, name);
if (address.Count > 0 && name.Count > 0 && address.Count == name.Count)
{
if (Directory.Exists(folder) == false) Directory.CreateDirectory(folder);//Create folder
foreach (string add in address)
{
//Download images one by one
c.DownloadFile(add, Path.Combine(folder, name[address.IndexOf(add)] + ".jpg"));
}
}
}
/**
/// Parse Html using regular expressions
///
/// Html content
/// Uri prefix
/// regular expression
/// Image addresses collection
/// Image names collection
private void ParseHtml(string content, string prefix, string expression, Collection address, Collection name)
{
if (String.IsNullOrEmpty(expression) || address == null || name == null) return;
Regex re = new Regex(expression, RegexOptions.IgnoreCase | RegexOptions.Singleline | RegexOptions.RightToLeft);
MatchCollection mc = re.Matches(content);
if (mc == null || mc.Count == 0) return;
foreach (Match m in mc)
{
address.Add(prefix + m.Groups["Uri"].Value);
name.Add(m.Groups["Name"].Value);
}
}
Html部分代码如下:
Html code
alt="" src="/docfile/dyn/12345678LANGCCCCDDDDEEEEEEEERT09 ">BMW 3-series\par
alt="" src="/docfile/dyn/12345678LANGCCCCDDDDEEEEEEEEEE01 ">Toyota\par
alt="" src="/docfile/dyn/12345678LANGCCCCDDDDEEEEEEEEJY25 ">Polo cross\par
alt="" src="/docfile/dyn/12345678LANGCCCCDDDDEEEEEEEEMO02 ">Golf 4.5\par
要用正则表达式从中获得图片下载地址(例如:/docfile/dyn/12345678LANGCCCCDDDDEEEEEEEERT09)和图片名称(例如:BMW 3-series)
正则表达式部分如下:
Regular expression
@"/docfile/dyn/(?[^""]*?)"">(?[^"
注意其中group的用法(? *?),和引号的匹配用法,匹配双引号前面需要再带一个双引号。其中Uri这个group在dyn/后面,直到双引号结束;后面跟随着双引号和>,然后就是Name这个group;它以。
本文来自CSDN博客,转载请标明出处:http://blog.csdn.net/yizhiduxiu11/archive/2010/09/ 13/5881442.aspx