批量下载搜狗词库
coreseek搜索引擎要用到mmseg,但是mmseg自带的词库不是很全面,导至搜索结果不精细。这个程序就是用来下载搜狗词库。
coreseek搜索引擎要用到mmseg,但是mmseg自带的词库不是很全面,导至搜索结果不精细。这个程序就是用来下载搜狗词库。
<?php
/*//echo microtime();
echo $start=strtotime(date("Y-m-01"))."<br/>";
echo urlencode(iconv("UTF-8","GB2312//IGNORE","中国的") );
echo urlencode("/");
require_once "pinyin.php";
$pinyin=new PY_deal();
echo join($pinyin->pinyin("麦包包批发,[魅惑/微光摇曳/青春密语]三种款式,自由选择!现只需50元/款!"));*/
$fp=fopen("dictory.txt", "a+");
for($i=1;$i<=4;$i++){
$curl=curl_init();
$url="http://pinyin.sogou.com/dict/search.php?word=%B0%A2%C0%EF%B0%CD%B0%CD%B2%FA%C6%B7%B4%CA%BB%E3&type=0&personal=1&page={$i}";
$options=array(CURLOPT_URL=>$url,CURLOPT_RETURNTRANSFER=>true,CURLOPT_HEADER=>false);
curl_setopt_array($curl, $options);
$rs=curl_exec($curl);
curl_close($curl);
$pattern_list="/\<dl\s+class\=\"dictlist\"\>([\S\s]+)?\<\/dl\>/i";
preg_match_all($pattern_list,$rs,$match);
$rs=$match[1][0];
$pattern="/\?id=(\d+?)\"/i";
preg_match_all($pattern,$rs,$match);
$rs=$match[1];
foreach($rs as $v){
$link="http://pinyin.sogou.com/dict/download_txt.php?id={$v}";
$curl=curl_init();
$options=array(CURLOPT_URL=>$link,CURLOPT_FILE=>$fp,CURLOPT_HEADER=>false);
curl_setopt_array($curl, $options);
curl_exec($curl);
curl_close($curl);
}
}
fclose($fp);
?>
2. [代码][PHP]代码 跳至 [1] [2] [全屏预览]
$fp=fopen("dictory.txt", "a+");
for($i=1;$i<=4;$i++){
$curl=curl_init();
$url="http://pinyin.sogou.com/dict/search.php?word=%B0%A2%C0%EF%B0%CD%B0%CD%B2%FA%C6%B7%B4%CA%BB%E3&type=0&personal=1&page={$i}";
$options=array(CURLOPT_URL=>$url,CURLOPT_RETURNTRANSFER=>true,CURLOPT_HEADER=>false);
curl_setopt_array($curl, $options);
$rs=curl_exec($curl);
curl_close($curl);
$pattern_list="/\<dl\s+class\=\"dictlist\"\>([\S\s]+)?\<\/dl\>/i";
preg_match_all($pattern_list,$rs,$match);
$rs=$match[1][0];
$pattern="/\?id=(\d+?)\"/i";
preg_match_all($pattern,$rs,$match);
$rs=$match[1];
foreach($rs as $v){
$link="http://pinyin.sogou.com/dict/download_txt.php?id={$v}";
$curl=curl_init();
$options=array(CURLOPT_URL=>$link,CURLOPT_FILE=>$fp,CURLOPT_HEADER=>false);
curl_setopt_array($curl, $options);
curl_exec($curl);
curl_close($curl);
}
}
fclose($fp);
- 上一篇:判断用户昵名是否合法(正则)
- 下一篇:PHP一个敏感信息过滤思路
精彩图集
精彩文章






