【完结】抓取电视剧剧情+各50元

lxh623 · 发表于 2021-10-10 17:47:24

本帖最后由 lxh623 于 2021-10-12 07:21 编辑

文本内是网址、一行一个。
文本c是，https://www.tvzn.com/8406/
文本d是，https://www.tvmao.com/drama/Ym4mXGVf

想得到如下结果：（写入新的文本）
TTT上海沧桑
第1集
1925年，湖南醴陵。................
第2集
................
................

两个网站，一个五十元。
谢谢！

zaqmlp · 发表于 2021-10-10 19:32:03

本帖最后由 zaqmlp 于 2021-10-10 20:53 编辑

<# :
rem www.tvzn.com
rem 另存为ANSI编码的bat
cls&echo off&cd /d "%~dp0"
powershell -NoProfile -ExecutionPolicy bypass "[IO.File]::ReadAllText('%~f0',[Text.Encoding]::GetEncoding('GB2312'))|Invoke-Expression"
pause
exit
#>
$infile='.\文本c.txt';
$outfile='.\结果.txt';
if(-not (test-path -liter $infile)){write-host ('"'+$infile+'" 未找到');exit;};
$enc=[System.Text.Encoding]::UTF8;
$webclient=New-Object System.Net.WebClient;
function gethtml($u){
$t='';
for($j=1;$j -le 3;$j++){
try{
$webclient.Headers.Add('User-Agent','Mozilla/5.0 (Windows NT 6.1; ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36');
$webclient.Encoding=$enc;
$t=$webclient.DownloadString($u);
break;
}catch{
write-host ('第'+$j.toString()+'次获取网页源码失败');
start-sleep -Seconds 3;
};
};
return $t;
};
$fs=New-Object System.IO.FileStream($outfile, [System.IO.FileMode]::Create);
$sw=New-Object System.IO.StreamWriter($fs, $enc);
$text=[IO.File]::ReadAllText($infile, $enc).split("`r`n",[StringSplitOptions]::RemoveEmptyEntries);
for($i=0;$i -lt $text.Count;$i++){
write-host ('--------------'+$text[$i]+'--------------');
$url=$text[$i].trimend(' /')
$url1=$url+'/juqingjieshao.html';
$html1=gethtml $url1;
$title='TTT';
$m1=[regex]::match($html1,'>([^<]+?)</h1></div>');
if($m1.Success){$title=$title+$m1.groups[1].value.replace('剧情介绍','');}
write-host $title;
$sw.WriteLine($title);
$m1=[regex]::match($html1,'<div id="danji"[^>]*?>([\s\S]+?)</div></div></div>');
if($m1.Success){
$m2=[regex]::matches($m1.groups[1].value, '<a class="link" href="([^"]+?)">(\d+)</a>');
for($j=$m2.Count-1;$j -ge 0;$j--){
$sw.WriteLine('第'+$m2[$j].groups[2].value+'集');
$url2=($url -replace '^(https?://[^/]+).+','$1')+$m2[$j].groups[1].value;
write-host ($m2[$j].groups[2].value+' '+$url2);
$html2=gethtml $url2;
$m3=[regex]::match($html2,'<div>.*?<center>.*?</center>.*?<br>([\s\S]+?)<div');
if($m3.Success){
$contant=(($m3.groups[1].value -replace '<p>','') -replace ' ',' ') -replace '</p>',"`r`n";
$contant=$contant.trim();
$sw.WriteLine($contant);
$sw.Flush();
}
}
}
$sw.WriteLine('');
}
$sw.Close();
$fs.Close();

复制代码

zaqmlp · 发表于 2021-10-10 19:32:51

本帖最后由 zaqmlp 于 2021-10-11 16:21 编辑

<# :
rem www.tvmao.com
rem 另存为ANSI编码的bat
cls&echo off&cd /d "%~dp0"
powershell -NoProfile -ExecutionPolicy bypass "[IO.File]::ReadAllText('%~f0',[Text.Encoding]::GetEncoding('GB2312'))|Invoke-Expression"
pause
exit
#>
$starturl=1;
$minilen=160;
$timeout=900;
$infile='.\文本b.txt';
$outfile='.\结果.txt';
if(-not (test-path -liter $infile)){write-host ('"'+$infile+'" 未找到');exit;};
$enc=[System.Text.Encoding]::UTF8;
$webclient=New-Object System.Net.WebClient;
function gethtml($u){
$t='';
for($j=1;$j -le 3;$j++){
try{
$webclient.Headers.Add('User-Agent','Mozilla/5.0 (Windows NT 6.1; ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36');
$webclient.Encoding=$enc;
$t=$webclient.DownloadString($u);
break;
}catch{
write-host ('第'+$j.toString()+'次获取网页源码失败');
start-sleep -Seconds 3;
};
};
return $t;
};
function getcontent($u){
$content='';
$html2=gethtml $u;
$m3=[regex]::match($html2,'<article class="clear epi_c"[^>]*?>([\s\S]+?)</article>');
if($m3.Success){
$content=((($m3.groups[1].value -replace '<p>','') -replace ' ',' ') -replace '</p>',"`r`n") -replace '<div(?: [^>]*?)?>[\s\S]+?</div>','';
$content=(($content -replace '<[^>]+?>','') -replace '</?[a-z]+','').trim();
}
return $content;
}
$fs=New-Object System.IO.FileStream($outfile, [System.IO.FileMode]::Append);
$sw=New-Object System.IO.StreamWriter($fs, $enc);
$text=[IO.File]::ReadAllText($infile, $enc).split("`r`n",[StringSplitOptions]::RemoveEmptyEntries);
for($i=0;$i -lt $text.Count;$i++){
if(($i+1) -ge $starturl){
write-host ('--------------'+$text[$i]+'--------------');
$result=New-Object -TypeName System.Collections.ArrayList;
$url=$text[$i].trimend(' /')
$url1=$url+'/episode';
$html1=gethtml $url1;
$title='TTT';
$m1=[regex]::match($html1,'title="([^"]+?)剧情介绍".*?>介绍');
if($m1.Success){$title=$title+$m1.groups[1].value.replace('剧情介绍','');}
write-host $title;
[void]$result.add($title);
$m1=[regex]::match($html1,'<div class="epipage clear">([\s\S]+?)</div>');
if($m1.Success){
$m2=[regex]::matches($m1.groups[1].value, '<li(?: [^>]*?)?>.*?href="([^"]+?)"[^>]*?>(\d+)</a></li>');
for($j=0;$j -lt $m2.Count;$j++){
[void]$result.add('第'+$m2[$j].groups[2].value+'集');
$url2=($url -replace '^(https?://[^/]+).+','$1')+$m2[$j].groups[1].value;
write-host ($m2[$j].groups[2].value+' '+$url2);
$t=0;
while(1){
$ct=getcontent $url2;
write-host $ct.length;
if($ct.length -gt $minilen){
[void]$result.add($ct);
break;
}else{
$t++;
}
if($t -ge 3){
$t=0;
write-host ('字符数少于'+$minilen+',暂停'+$timeout+'秒……');
start-sleep -Seconds $timeout;
}
}
}
}
$s=$result -join "`r`n";
$sw.WriteLine($s);
$sw.WriteLine('');
$sw.Flush();
}
}
$sw.Close();
$fs.Close();

复制代码

went · 发表于 2021-10-10 19:53:39

tvzn.bat

#&cls&@cd /d "%~dp0" & powershell -c "Get-Content '%~0' | Select-Object -Skip 1 | Out-String | Invoke-Expression" &pause&exit
cls
#whr
$whr = New-Object -ComObject 'WinHttp.WinHttpRequest.5.1'
#变量设置
$list_file = 'c.txt' #电视剧名称列表文件
$out_file = 'info.txt' #输出信息文件
#函数获取所有分集链接
function Get-PartList($url) {
$url += 'juqingjieshao.html'
$whr.Open('GET',$url,$false)
$whr.Send()
$txt = $whr.ResponseText
$whr.Abort()
$title = ''
if($txt -match '(?s)<title>(.*?)</title>'){
$title = $Matches[1] -replace '剧情介绍.*$',''
}
return &{
$title
[regex]::Matches($txt,'<a class="link" href="(.*?)">(.*?)</a>') | Sort-Object {[int]$_.Groups[2].Value} | foreach {
$_.Groups[2].Value + '|' + 'https://www.tvzn.com' + $_.Groups[1].Value
}
}
}
#函数根据分集链接获取剧情内容
function Get-PartInfo($part_list){
#标题
$title = $part_list[0]
Write-Host $title
'TTT' + $title
#分集
if($part_list.Count -gt 1){
for($i = 1; $i -lt $part_list.Count; $i++){
$arr = $part_list[$i] -split '\|'
Write-Host (' 第{0}集 {1}' -f $arr[0],$arr[1])
#---------------------------------
$url = $arr[1]
$whr.Open('GET',$url,$false)
$whr.Send()
$txt = $whr.ResponseText
$whr.Abort()
if($txt -match '(?s)<div class="tn-detail-text".*?</p>'){
'第{0}集' -f $arr[0]
$Matches[0] -replace '<.*?>| |\s+',''
}
}
}
}
#读取文本内容并解析
Get-Content $list_file | foreach {
$part_list = Get-PartList -url $_
$data = Get-PartInfo -part_list $part_list
Out-File -InputObject $data $out_file -Append
}

复制代码

lxh623 · 发表于 2021-10-11 07:51:14

回复 3# zaqmlp
电视猫
信息不全，后面总是少了。麻烦检查一下。
谢谢！

went · 发表于 2021-10-11 11:09:35

tvmao.bat

#&cls&@cd /d "%~dp0" & powershell -c "Get-Content '%~0' | Select-Object -Skip 1 | Out-String | Invoke-Expression" &pause&exit
cls
#whr
$whr = New-Object -ComObject 'WinHttp.WinHttpRequest.5.1'
#设置请求头
function Set-RequestHeader($whr){
$whr.SetRequestHeader('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36 Edg/94.0.992.38');
$whr.SetRequestHeader('Host','www.tvmao.com')
$whr.SetRequestHeader('Connection','Keep-Alive')
}
#函数根据url链接获取所有分集的链接
function Get-PartUrlList($url){
if($url -eq $null){
return $null
}
$whr.Open('GET',$url,$false)
Set-RequestHeader -whr $whr
$whr.Send()
$txt = $whr.ResponseText
$whr.Abort()
$title = ''
$pattern = '<strong class="font24">(.*?)</strong>'
if($txt -match $pattern){
$title = $Matches[1]
}
$pattern = '<div class="epipage.*?>.*?</div>'
if($txt -match $pattern){
$pattern = '(?s)href="(.*?)"'
return &{
$title
[regex]::Matches($Matches[0],$pattern) | foreach {
'https://www.tvmao.com' + $_.Groups[1].Value
}
}
}
return $null
}
#函数根据分集url获取分集剧情
function Get-PartInfo($part_url){
if($part_url -match '-(\d+)$'){
Write-Host ('解析第{0}集 {1}' -f $Matches[1],$part_url)
'第{0}集' -f $Matches[1]
} else {
return;
}
$whr.Open('GET',$part_url,$false)
Set-RequestHeader -whr $whr
$whr.Send()
$txt = $whr.ResponseText
$whr.Abort()
$pattern = '(?s)<article class=".*?epi_c">.*?</article>'
if($txt -match $pattern){
$Matches[0] -replace '(?s)<.*?>','' -replace '(?s)$.*?转载许可$.*$','' -replace '^\s+|\s+$',''
}
}
#--------------------------------------------------------------------
#变量设置
$list_file = 'd.txt' #列表文件
$out_file = 'tvmao_info.txt' #输出信息文件
#--------------------------------------------------------------------
Get-Content $list_file | foreach {
$part_list = Get-PartUrlList -url ($_ + '/episode')
Write-Host $part_list[0]
if($part_list.Count -gt 1){
$data = &{
'TTT' + $part_list[0]
for($i = 1;$i -lt $part_list.Count; $i++){
Get-PartInfo -part_url $part_list[$i]
}
}
Out-File -InputObject $data $out_file -Append
}
Write-Host '----------------'
}

复制代码

zaqmlp · 发表于 2021-10-11 16:23:33

回复 5# lxh623

已修改

		自动登录	找回密码
密码			注册

[新手上路]批处理新手入门导读	[视频教程]批处理基础视频教程	[视频教程]VBS基础视频教程	[批处理精品]批处理版照片整理器
[批处理精品]纯批处理备份&还原驱动	[批处理精品]CMD命令50条不能说的秘密	[在线下载]第三方命令行工具	[在线帮助]VBScript / JScript 在线参考

【完结】抓取电视剧剧情+各50元

评分

评分

评分

评分

浏览过的版块