天涯社区离线阅读器（实现只看楼主功能）
长期逛天涯社区，许多的经典的帖子都有许多页，而且里面还夹杂了大量的回复或者广告，不能像MOP一样只看楼主，这样阅读起来非常不便，故此写了一个小程序实现离线阅读并只看楼主功能。实现的思路是通过
HttpWebRequest取得要查看的网页内容，然后用正则表达式将其中感性趣的部分取出来，我主要取了分页信息，同时分离出了各贴以及作者，这样可以实现查看任意一个人帖子的功能，如果需要的话可以将取出的数据保存在本地硬盘中以方便查看，在这个程序没有作本地保存。程序中的主要代码部分有：
1、从指定网址下载网页
public
string
Get_SourceHtml(
string
a_strUrl)
{
string strResult;
try
{
HttpWebRequest myReq = (HttpWebRequest)HttpWebRequest.Create(a_strUrl);
myReq.Timeout = 60000;
HttpWebResponse HttpWResp = (HttpWebResponse)myReq.GetResponse();
Stream myStream = HttpWResp.GetResponseStream();
StreamReader sr = new StreamReader(myStream, Encoding.Default);
strResult = sr.ReadToEnd();
myStream.Close();
}
catch (Exception exp)
{
strResult = "错误：" + exp.Message;
}
return strResult;
}
2、分离出帖子正文
public
string
SplitHtml(
string
htmlContent)
{
string result =htmlContent;
//剪切掉正文后面的内容
Regex regexObj = new Regex("</div><center>");
Match m = regexObj.Match(result);
if (m.Value != string.Empty)
{
result = result.Substring(0, result.IndexOf(m.Value));
}
//清除掉广告
regexObj =new Regex(@"<center><IFRAME(.|\s)+?</IFRAME></center>");
result=regexObj.Replace(result,"");
//剪切掉正文前面的内容
//regexObj = new Regex("<TABLE align=center border=0 cellSpacing=0 width='100%'>");
regexObj = new Regex(@"<span id='AddMyDigest'></span>");
m = regexObj.Match(result);
if (m.Value != string.Empty)
{
result = result.Substring(result.IndexOf(m.Value));
}
return result;
}
3、获取指定作者的发帖在本地生成新的Html文件以便在程序内嵌浏览器中查看
public
string
GetAuthorsContent(
string
SourceHtml,
string
AuthorName)
{
StringBuilder html = new StringBuilder();
html.Append("<Html><body>");
SourceHtml = SplitHtml(SourceHtml);
Regex r = new Regex(@"<TABLE(.|\s)+?</table>");
MatchCollection ms = r.Matches(SourceHtml);
for (int i = 0; i < ms.Count - 2; i++)
{
Match m = ms[i];
int start = SourceHtml.IndexOf(m.Value) + m.Value.Length;
string title = m.Value;
Regex re = new Regex(@"k>(.|\s)+?<");
Match m1 = re.Match(title);
string author = m1.Value;
if (author.Length > 0)
author = author.Substring(2, author.IndexOf("<") - 2);
if (author == AuthorName)
{
html.Append(title);
Match NextMatch = ms[i + 1];
string content;
if (NextMatch != null)
content = SourceHtml.Substring(start, SourceHtml.IndexOf(NextMatch.Value) - start);
else
content = SourceHtml.Substring(start);
html.Append(content);
html.Append("<br>");
}
}
html.Append("</body></html>");
return html.ToString();
}
4、获取分页数据
public
List
<
PageData
>
GetPages(
string
SourceHtml)
{
SourceHtml=SplitHtml(SourceHtml);
Regex r = new Regex(@"http:.+?((\[\d+\])|首页)");
MatchCollection ms = r.Matches(SourceHtml);
List<PageData> pages = new List<PageData>();
foreach (Match m in ms)
{
r = new Regex("><.+?>");
string s = r.Replace(m.Value, "");
s = s.Replace(">", "");
if (s.IndexOf("首页") >= 0)
pages.Add(new PageData(s.Substring(0, s.IndexOf("首页")),"首页"));
else
pages.Add(new PageData(s.Substring(0,s.IndexOf("[")),s.Substring(s.IndexOf("["))));
}
return pages;
}
完整源代码点击下载
1、从指定网址下载网页
public
string
Get_SourceHtml(
string
a_strUrl)
{
string strResult; try {
HttpWebRequest myReq = (HttpWebRequest)HttpWebRequest.Create(a_strUrl); myReq.Timeout = 60000; HttpWebResponse HttpWResp = (HttpWebResponse)myReq.GetResponse(); Stream myStream = HttpWResp.GetResponseStream(); StreamReader sr = new StreamReader(myStream, Encoding.Default); strResult = sr.ReadToEnd(); myStream.Close(); } catch (Exception exp) { strResult = "错误：" + exp.Message; } return strResult; }
public
string
SplitHtml(
string
htmlContent)
{ string result =htmlContent; //剪切掉正文后面的内容 Regex regexObj = new Regex("</div><center>"); Match m = regexObj.Match(result); if (m.Value != string.Empty) { result = result.Substring(0, result.IndexOf(m.Value)); } //清除掉广告 regexObj =new Regex(@"<center><IFRAME(.|\s)+?</IFRAME></center>"); result=regexObj.Replace(result,""); //剪切掉正文前面的内容 //regexObj = new Regex("<TABLE align=center border=0 cellSpacing=0 width='100%'>"); regexObj = new Regex(@"<span id='AddMyDigest'></span>"); m = regexObj.Match(result); if (m.Value != string.Empty) { result = result.Substring(result.IndexOf(m.Value)); } return result; }
public
string
GetAuthorsContent(
string
SourceHtml,
string
AuthorName)
{ StringBuilder html = new StringBuilder(); html.Append("<Html><body>"); SourceHtml = SplitHtml(SourceHtml); Regex r = new Regex(@"<TABLE(.|\s)+?</table>"); MatchCollection ms = r.Matches(SourceHtml); for (int i = 0; i < ms.Count - 2; i++) { Match m = ms[i]; int start = SourceHtml.IndexOf(m.Value) + m.Value.Length; string title = m.Value; Regex re = new Regex(@"k>(.|\s)+?<"); Match m1 = re.Match(title); string author = m1.Value; if (author.Length > 0) author = author.Substring(2, author.IndexOf("<") - 2); if (author == AuthorName) { html.Append(title); Match NextMatch = ms[i + 1]; string content; if (NextMatch != null) content = SourceHtml.Substring(start, SourceHtml.IndexOf(NextMatch.Value) - start); else content = SourceHtml.Substring(start); html.Append(content); html.Append("<br>"); } } html.Append("</body></html>"); return html.ToString(); }
public
List
<
PageData
>
GetPages(
string
SourceHtml)
{ SourceHtml=SplitHtml(SourceHtml); Regex r = new Regex(@"http:.+?((\[\d+\])|首页)"); MatchCollection ms = r.Matches(SourceHtml); List<PageData> pages = new List<PageData>(); foreach (Match m in ms) { r = new Regex("><.+?>"); string s = r.Replace(m.Value, ""); s = s.Replace(">", ""); if (s.IndexOf("首页") >= 0) pages.Add(new PageData(s.Substring(0, s.IndexOf("首页")),"首页")); else pages.Add(new PageData(s.Substring(0,s.IndexOf("[")),s.Substring(s.IndexOf("[")))); } return pages; }
完整源代码点击下载