恶意号码识别

自己用的原生系统的 android 手机没有恶意号码识别的功能，应用市场上的号码识别软件还需要通讯录这类的权限，用起来自己也不放心，于是就打算自己写一个应用来做这事；

搜索号码识别接口的时候, 在网上找到了这篇文章，但是原博主的文章里贴出的代码已经无法使用，就自己改了一下代码；

识别号码的原理

使用"360搜索"搜索号码 -> 分析返回的网页数据 -> 从网页数据中提取数据返回给客户端;
由于360搜索提供的格式可能会发生改变, 会造成接口无法使用, 下面贴出的源码也需要对应修改;

下图网页源码中的格式信息(截止2018/02)

补充对客服号码的识别(2018/2/10)

正常号码

正常号码格式

恶意号码

恶意号码格式

客服号码(如10086)

客服号码格式

PHP 代码:(PHP 5.4/5.5)

<?php
class Result{
 var  $phone;//号码
 var  $where;//归属地
 var  $cmcc;// 运营商
 var  $type;// 类型(广告推销/骚扰电话...)
 var  $tip;// 标记人数
}

// 获取网页数据
function get($url = '') {
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt ( $ch, CURLOPT_RETURNTRANSFER, true);
    $output = curl_exec($ch);
    curl_close($ch);
    return $output; 
}

// 获取 指定标签 内容
function get_tag( $attr, $value, $xml, $tag=null ) {  
  if( is_null($tag) )  
    $tag = '\w+';
  else  
    $tag = preg_quote($tag);
  $attr = preg_quote($attr);  
  $value = preg_quote($value);  
  
  // $tag_regex = "/<(".$tag.")[^>]*$attr\s*=\s*".  
  //               "(['\"])$value\\2[^>]*>(.*?)<\/\\1>/";
  $tag_regex2 = "/<".$tag."[^>]*".$attr."[^>]*".$value."[^>]*>([\s\S])*<\/".$tag.">/U";
  preg_match_all($tag_regex2,  
                 $xml,  
                 $matches,  
                 PREG_PATTERN_ORDER);
  return $matches[0];  
}

// 去除空白字符
function trimall($str){  
    $qian=array(" ","　","\t","\n","\r");
    return str_replace($qian, '', $str);  
}

header('Content-type:text/json'); 
$phone=$_GET['phone'];
$phone_t="";
$where_t="";
$cmcc_t="";
$type_t="";
$tip_t="";
// 从 360搜索 获取号码信息
$txt=get('https://www.so.com/s?q='.$phone);
// 获取有关号码的标签内容
$info=get_tag("class","mohe-mobileInfoContent",$txt,"td");

if (count($info)==0) {// 特殊服务热线,如10086
    $special_info=get_tag("id","mohe-biu_kefudianhua",$txt,"div");
    if (count($special_info)!=0) {
        $special_info_name=get_tag("class","title",$special_info[0],"h3");
        $special_info_number=get_tag("class","mh-item g-ellipsis",$txt,"li");
        $where_t=strip_tags ($special_info_name[0]);//去除标签
        $where_t=trimall($where_t);

        $phone_t=strip_tags ($special_info_number[0]);//去除标签
        $phone_t=trimall($phone_t);
    }
}else{
    // 归属地信息
    $where=get_tag("class","gclearfix mh-detail",$info[0],"div");
    if(count($where)==0){//不是恶意电话
       $where=get_tag("class","mh-detail",$info[0],"p");
       $oknumber=strip_tags ($where[0]);//去除标签
       $oknumber=trimall($oknumber);
       $number_info_detail=explode("&nbsp;&nbsp;",$oknumber);// 获取号码/归属地/运营商

       $phone_t=$number_info_detail[0];
       $where_t=$number_info_detail[1];
       $cmcc_t=$number_info_detail[2];
       $type_t=$type_t;

    }else{// 是恶意电话
       $evilnumber=strip_tags ($where[0]);//去除标签
       $evilnumber=trimall($evilnumber);
       $number_info_detail=explode("&nbsp;&nbsp;",$evilnumber);// 获取号码/归属地/运营商

       $phone_t=$number_info_detail[0];
       $where_t=$number_info_detail[1];
       $cmcc_t=$number_info_detail[2];

       // 获取恶意电话详细信息
       $type=get_tag("class","mohe-ph-mark",$info[0],"span");
       $number_type=strip_tags ($type[0]);//去除标签
       $number_type=trimall($number_type);
       if(count($type)!=0){
         $type_t=$number_type;
       }
       $tip_parent_contact=get_tag("class","mohe-tips",$info[0],"div");
       if(count($tip_parent_contact)!=0){
         $tip_array=get_tag("","",$tip_parent_contact[0],"span");
         if (count($tip_array)!=0) {
           $tip_array=get_tag("","",$tip_array[1],"b");
           if (count($tip_array)!=0) {
                $number_tip=strip_tags ($tip_array[0]);//去除标签
                $number_tip=trimall($number_tip);
                $tip_t=$number_tip;
            }
          }
        }
     }
}
$result=new Result();
$result->phone=$phone_t;
$result->where=$where_t;
$result->cmcc=$cmcc_t;
$result->type=$type_t;
$result->tip=$tip_t;
     
$json=json_encode($result,JSON_UNESCAPED_UNICODE);
echo $json;
?>

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

<?php

class Result{

var $phone;//号码

var $where;//归属地

var $cmcc;// 运营商

var $type;// 类型(广告推销/骚扰电话...)

var $tip;// 标记人数

}

// 获取网页数据

function get($url = '') {

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, $url);

curl_setopt ( $ch, CURLOPT_RETURNTRANSFER, true);

$output = curl_exec($ch);

curl_close($ch);

return $output;

}

// 获取指定标签内容

function get_tag( $attr, $value, $xml, $tag=null ) {

if( is_null($tag) )

$tag = '\w+';

else

$tag = preg_quote($tag);

$attr = preg_quote($attr);

$value = preg_quote($value);

// $tag_regex = "/<(".$tag.")[^>]*$attr\s*=\s*".

// "(['\"])$value\\2[^>]*>(.*?)<\/\\1>/";

$tag_regex2 = "/<".$tag."[^>]*".$attr."[^>]*".$value."[^>]*>([\s\S])*<\/".$tag.">/U";

preg_match_all($tag_regex2,

$xml,

$matches,

PREG_PATTERN_ORDER);

return $matches[0];

}

// 去除空白字符

function trimall($str){

$qian=array(" ","　","\t","\n","\r");

return str_replace($qian, '', $str);

}

header('Content-type:text/json');

$phone=$_GET['phone'];

$phone_t="";

$where_t="";

$cmcc_t="";

$type_t="";

$tip_t="";

// 从 360搜索获取号码信息

$txt=get('https://www.so.com/s?q='.$phone);

// 获取有关号码的标签内容

$info=get_tag("class","mohe-mobileInfoContent",$txt,"td");

if (count($info)==0) {// 特殊服务热线,如10086

$special_info=get_tag("id","mohe-biu_kefudianhua",$txt,"div");

if (count($special_info)!=0) {

$special_info_name=get_tag("class","title",$special_info[0],"h3");

$special_info_number=get_tag("class","mh-item g-ellipsis",$txt,"li");

$where_t=strip_tags ($special_info_name[0]);//去除标签

$where_t=trimall($where_t);

$phone_t=strip_tags ($special_info_number[0]);//去除标签

$phone_t=trimall($phone_t);

}

}else{

// 归属地信息

$where=get_tag("class","gclearfix mh-detail",$info[0],"div");

if(count($where)==0){//不是恶意电话

$where=get_tag("class","mh-detail",$info[0],"p");

$oknumber=strip_tags ($where[0]);//去除标签

$oknumber=trimall($oknumber);

$number_info_detail=explode("  ",$oknumber);// 获取号码/归属地/运营商

$phone_t=$number_info_detail[0];

$where_t=$number_info_detail[1];

$cmcc_t=$number_info_detail[2];

$type_t=$type_t;

}else{// 是恶意电话

$evilnumber=strip_tags ($where[0]);//去除标签

$evilnumber=trimall($evilnumber);

$number_info_detail=explode("  ",$evilnumber);// 获取号码/归属地/运营商

$phone_t=$number_info_detail[0];

$where_t=$number_info_detail[1];

$cmcc_t=$number_info_detail[2];

// 获取恶意电话详细信息

$type=get_tag("class","mohe-ph-mark",$info[0],"span");

$number_type=strip_tags ($type[0]);//去除标签

$number_type=trimall($number_type);

if(count($type)!=0){

$type_t=$number_type;

}

$tip_parent_contact=get_tag("class","mohe-tips",$info[0],"div");

if(count($tip_parent_contact)!=0){

$tip_array=get_tag("","",$tip_parent_contact[0],"span");

if (count($tip_array)!=0) {

$tip_array=get_tag("","",$tip_array[1],"b");

if (count($tip_array)!=0) {

$number_tip=strip_tags ($tip_array[0]);//去除标签

$number_tip=trimall($number_tip);

$tip_t=$number_tip;

}

$result=new Result();

$result->phone=$phone_t;

$result->where=$where_t;

$result->cmcc=$cmcc_t;

$result->type=$type_t;

$result->tip=$tip_t;

$json=json_encode($result,JSON_UNESCAPED_UNICODE);

echo $json;

使用方法:

将代码保存为 .php 文件, 放到有PHP服务的服务器上;
使用域名?phone=号码方式访问;

访问:
域名?phone=02568629204

返回:
{"phone":"02568629204","where":"江苏南京","cmcc":"","type":"广告推销","tip":"16"}

访问:

域名?phone=02568629204

{"phone":"02568629204","where":"江苏南京","cmcc":"","type":"广告推销","tip":"16"}

冷水