我正在研究网络爬虫。目前我抓取了整个内容,然后使用正则表达式删除<meta>, <script>, <style>
和其他标签并获取正文的内容。
但是,我正在尝试优化性能,我想知道是否有一种方法可以只抓取<body>
页面的?
namespace WebScraper
{
public static class KrioScraper
{
public static string scrapeIt(string siteToScrape)
{
string HTML = getHTML(siteToScrape);
string text = stripCode(HTML);
return text;
}
public static string getHTML(string siteToScrape)
{
string response = "";
HttpWebResponse objResponse;
HttpWebRequest objRequest =
(HttpWebRequest) WebRequest.Create(siteToScrape);
objRequest.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; " +
"Windows NT 5.1; .NET CLR 1.0.3705)";
objResponse = (HttpWebResponse) objRequest.GetResponse();
using (StreamReader sr =
new StreamReader(objResponse.GetResponseStream()))
{
response = sr.ReadToEnd();
sr.Close();
}
return response;
}
public static string stripCode(string the_html)
{
// Remove google analytics code and other JS
the_html = Regex.Replace(the_html, "<script.*?</script>", "",
RegexOptions.Singleline | RegexOptions.IgnoreCase);
// Remove inline stylesheets
the_html = Regex.Replace(the_html, "<style.*?</style>", "",
RegexOptions.Singleline | RegexOptions.IgnoreCase);
// Remove HTML tags
the_html = Regex.Replace(the_html, "</?[a-z][a-z0-9]*[^<>]*>", "");
// Remove HTML comments
the_html = Regex.Replace(the_html, "<!--(.|\\s)*?-->", "");
// Remove Doctype
the_html = Regex.Replace(the_html, "<!(.|\\s)*?>", "");
// Remove excessive whitespace
the_html = Regex.Replace(the_html, "[\t\r\n]", " ");
return the_html;
}
}
}
From Page_Load
我打电话给scrapeIt()
方法将我从页面文本框中获取的字符串传递给它。