一般来说，当我爬到 www.cnn.com 或 www.foxnews.com 之类的网站时，代码是有效的，但现在我尝试了这个网站：https ://github.com/jasonwupilly/Obsidian/tree/master/Obsidian 我想要下载文件，例如当它爬行时有一个这样的链接：
https://github.com/jasonwupilly/Obsidian/blob/master/Obsidian/Obsidian.sln 所以我硬盘上的文件应该是 Obsidian.sln
这是我的爬取方法：
public List<string> webCrawler(string mainUrl, int levels)
{
List<string> csFiles = new List<string>();
wc = new System.Net.WebClient();
HtmlWeb hw = new HtmlWeb();
List<string> webSites;
csFiles.Add("temp string to know that something is happening in level = " + levels.ToString());
csFiles.Add("current site name in this level is : " + mainUrl);
try
{
HtmlAgilityPack.HtmlDocument doc = TimeOut.getHtmlDocumentWebClient(mainUrl, false, "", 0, "", "");
if (doc == null)
{
failed = true;
wccfg.failedUrls++;
failed = false;
}
else
{
done = true;
// progress should be reported here I guess
Object[] temp_arr = new Object[8];
temp_arr[0] = csFiles;
temp_arr[1] = mainUrl;
temp_arr[2] = levels;
temp_arr[3] = currentCrawlingSite;
temp_arr[4] = sitesToCrawl;
temp_arr[5] = done;
temp_arr[6] = wccfg.failedUrls;
temp_arr[7] = failed;
OnProgressEvent(temp_arr);
currentCrawlingSite.Add(mainUrl);
webSites = getLinks(doc);
removeDupes(webSites);
removeDuplicates(webSites, currentCrawlingSite);
removeDuplicates(webSites, sitesToCrawl);
if (wccfg.removeext == true)
{
for (int i = 0; i < webSites.Count; i++)
{
webSites.Remove(removeExternals(webSites, mainUrl, wccfg.localy));
}
}
if (wccfg.downloadcontent == true)
{
retwebcontent.retrieveImages(mainUrl);
}
if (wccfg.downloadallfiles == true)
{
retwebcontent.retrieveFiles(mainUrl);
}
if (levels > 0)
sitesToCrawl.AddRange(webSites);
webSites = FilterJunkLinks(webSites);
if (levels == 0)
{
return csFiles;
}
else
{
for (int i = 0; i < webSites.Count(); i++)//&& i < 20; i++)
{
if (wccfg.toCancel == true)
{
return new List<string>();
}
if (pause == true)
{
_busy.Reset();
}
else
{
_busy.Set();
string t = webSites[i];
if ((t.StartsWith("http://") == true) || (t.StartsWith("https://") == true))
{
csFiles.AddRange(webCrawler(t, levels - 1));
}
}
}
return csFiles;
}
}
return csFiles;
}
catch (WebException ex)
{
failed = true;
wccfg.failedUrls++;
return csFiles;
}
catch (Exception ex)
{
failed = true;
wccfg.failedUrls++;
throw;
}
}
在这个方法的开始，我有这一行：
HtmlAgilityPack.HtmlDocument doc = TimeOut.getHtmlDocumentWebClient(mainUrl, false, "", 0, "", "");
我在这一行上使用了一个断点并将其输入到类中：
using System;
using System.Collections.Generic;
using System.ComponentModel;
using System.Data;
using System.Drawing;
using System.Linq;
using System.Text;
using System.Windows.Forms;
using HtmlAgilityPack;
using System.IO;
using System.Text.RegularExpressions;
using System.Xml.Linq;
using System.Net;
using System.Web;
using System.Threading;
using DannyGeneral;
namespace GatherLinks
{
class TimeOut
{
static HtmlAgilityPack.HtmlDocument doc;
public TimeOut()
{
}
class MyClient : WebClient
{
public bool HeadOnly { get; set; }
protected override WebRequest GetWebRequest(Uri address)
{
WebRequest req = base.GetWebRequest(address);
if (HeadOnly && req.Method == "GET")
{
req.Method = "HEAD";
}
return req;
}
}
public static HtmlAgilityPack.HtmlDocument getHtmlDocumentWebClient(string url, bool useProxy, string proxyIp, int proxyPort, string usename, string password)
{
try
{
doc = null;
using (MyClient clients = new MyClient())
{
clients.HeadOnly = true;
byte[] body = clients.DownloadData(url);
// note should be 0-length
string type = clients.ResponseHeaders["content-type"];
clients.HeadOnly = false;
// check 'tis not binary... we'll use text/, but could
// check for text/html
if (type == null)
{
return null;
}
else
{
if (type.StartsWith(@"text/html"))
{
string text = clients.DownloadString(url);
doc = new HtmlAgilityPack.HtmlDocument();
WebClient client = new WebClient();
//client.Headers.Add("user-agent", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705;)");
client.Credentials = CredentialCache.DefaultCredentials;
client.Proxy = WebRequest.DefaultWebProxy;
if (useProxy)
{
//Proxy
if (!string.IsNullOrEmpty(proxyIp))
{
WebProxy p = new WebProxy(proxyIp, proxyPort);
if (!string.IsNullOrEmpty(usename))
{
if (password == null)
password = string.Empty;
NetworkCredential nc = new NetworkCredential(usename, password);
p.Credentials = nc;
}
}
}
doc.Load(client.OpenRead(url));
}
}
}
}
catch (Exception err)
{
}
return doc;
}
private static string GetUrl(string url)
{
string startTag = "Url: ";
string endTag = " ---";
int startTagWidth = startTag.Length;
int endTagWidth = endTag.Length;
int index = 0;
index = url.IndexOf(startTag, index);
int start = index + startTagWidth;
index = url.IndexOf(endTag, start + 1);
string g = url.Substring(start, index - start);
return g;
}
}
}
它在 getHtmlDocumentWebClient 方法中执行第一行，并且在到达该行时：
byte[] body = clients.DownloadData(url);
它跳转到方法：GetWebRequest 做完这行之后：return req; 它什么也不做，它返回程序，什么也没有发生。
只有当链接是：https ://github.com/jasonwupilly/Obsidian/tree/master/Obsidian
如果链接是www.cnn.com，例如它下载图片没有问题，也没有问题抓取。
代码有些长，但都已连接，所以我必须全部添加。
这里可能是什么问题？