[文本处理] 【已解决】求助BAT如何批量获取网页的标题(title)和描述(description)？

hotkean

我现在有个文本a.txt  里面有N行URL网址，如何批处理实现导出每个URL的标题呢并且保存为a-title.txt
如a.txt内网址为
http://www.bathome.net
https://www.qq.com/
导出a-title.txt内容为：
批处理之家 批处理_BAT_CMD_DOS_VBS_Perl_Python_PowerShell - Powered by Discuz!
腾讯首页

顺便再求助一下大家，导出网站description的文本文件a-des.txt的批处理，一并多谢了！

pcl_test

//&cls&cscript -nologo -e:jscript "%~f0"<"url列表.txt"&pause&exit /b

function BintoStr(strBin,strCharset){
    var stream = new ActiveXObject('ADODB.Stream')
    stream.Type = 1
    stream.Mode = 3
    stream.Open()
    stream.Write(strBin)
    stream.Position = 0
    stream.Type = 2
    stream.Charset = strCharset
    return stream.ReadText
}

function getHtmlTxt(strURL){
    var http = new ActiveXObject('Msxml2.XMLHTTP');
    try{
        http.open('GET', strURL, false);
        http.send();
        var m = http.GetResponseHeader('Content-Type').match(/charset\s?=\s?([^\s;]+)/i);
        if (m){
            var contenttype = m[0].replace(/charset\s?=\s?/,'');
            var HtmlText = BintoStr(http.ResponseBody,contenttype);
            return HtmlText;
        }
        else{
            var m = http.ResponseText.match(/<\s?meta.+?charset\s?=\s?[^\s\"]+/i);
            if (m){
                var contenttype = m[0].replace(/.+?charset\s?=\s?/,'');
                var HtmlText = BintoStr(http.ResponseBody,contenttype);
                return HtmlText;
            }
            else return http.ResponseText;
        }
     }catch (e){}
}

//var fso = new ActiveXObject('Scripting.Filesystemobject');
var url = WScript.StdIn.ReadAll().split(/\s/);
var s = '';
for (var i=0; i<url.length; i++)
{
    var txt = getHtmlTxt(url[i]);
    if (!txt)
        s += url[i]+'\r\n拒绝访问\r\n\r\n';
    else{
        var title = /<title>([^<]+)<\/title>/i.exec(txt);
        var description = txt.match(/<\s?meta[^>]+?description[^>]*?>/i);
        if (title)
            var titlestr = title[1];
        else var titlestr = 'not found';
        if (description)
            var descriptionstr = description[0].replace(/.+?content\s?=\s?"([^"]+)".+/i, '$1');
        else var descriptionstr = 'not found';
        s += url[i]+'\r\ntitle:'+titlestr+'\r\ndescription:'+descriptionstr+'\r\n\r\n';
    }
}
WSH.echo(s);
复制代码

hotkean

多谢，如果是想把标题和描述分别导出为 a-title.txt 和 a-description.txt 两个文件（一行一行模式）  代码又应该如何修改呢？

pcl_test

回复 3# hotkean

38行开始替换

var fso = new ActiveXObject('Scripting.Filesystemobject');
var url = WScript.StdIn.ReadAll().split(/\s/);
var titlestr = descriptionstr = '';
for (var i=0; i<url.length; i++)
{
    var txt = getHtmlTxt(url[i]);
    if (txt) {
        var title = /<title>([^<]+)<\/title>/i.exec(txt);
        var description = txt.match(/<\s?meta[^>]+?description[^>]*?>/i);
        if (title)
             titlestr += title[1]+'\r\n';
        else titlestr += 'not found\r\n';
        if (description)
            descriptionstr += description[0].replace(/.+?content\s?=\s?"([^"]+)".+/i, '$1')+'\r\n';
        else descriptionstr += 'not found\r\n';
    }
    else{
        titlestr += 'access forbidden\r\n';
        descriptionstr += 'access forbidden\r\n';
    }
}
fso.CreateTextFile('title.txt',2).Write(titlestr);
fso.CreateTextFile('description.txt',2).Write(descriptionstr);
复制代码