使用php批量抓取QQ空间相册链接
优采云 发布时间: 2020-07-25 08:03前言
小杰之前发布的文章《为什么QQ空间与我们渐行渐远？》
里面就提及小杰会抽空备份QQ空间的相片php 采集qq空间文章，但是在网上找了许久也没有找到一个有效的工具
作为一个Phper，淦就完事了，所以顶着严寒，搞了三个小时总算把QQ空间所有相片备份了
小杰也希望能帮到有同样诉求的同学，所以公开代码
Ps：采用QQ空间api，有效时间不确定php 采集qq空间文章，如果发觉api生效，请自己抓取api。
手动验证了一下相册数与抓到的链接数，一个都不差，/宾果
源码
<?php
/**
* QzoneImgDown
* QQ空间相册图片地址批量获取
* @author Youngxj
* @DateTime 2019-12-01
* @Blog https://blog.youngxj.cn
*/
class QzoneImgDown
{
// 调用方法
// 请登录https://h5.qzone.qq.com/获取你的cookie以及g_tk和uin
// $g_tk = '';
// $res_uin = ''; // 该uin为你的QQ号（常规情况下）
// $cookie = '';
// $qzone = new QzoneImgDown($g_tk, $uin, $cookie);
// echo $qzone->getList();
// Ps：该类库仅用于获取自己QQ空间照片链接，至于QQ好友相册没有适配
// 获取的下载链接请使用下载工具进行下载（php不方便下载）
public function __construct($g_tk, $res_uin, $cookie)
{
$this->g_tk = $g_tk;
$this->res_uin = $res_uin;
// 相册列表接口
$this->listApi = 'https://mobile.qzone.qq.com/list?g_tk=' . $this->g_tk . '&format=json&list_type=album&action=0&res_uin=' . $this->res_uin . '&count=99';
// 相册图片列表接口
$this->imgApi = 'https://h5.qzone.qq.com/webapp/json/mqzone_photo/getPhotoList2?g_tk=' . $this->g_tk . '&uin=' . $this->res_uin . '&albumid=xxxxxxxxxxxxx&ps=0&pn=20&password=&password_cleartext=0&swidth=1080&sheight=1920';
$this->cookie = $cookie;
}
/**
* 获取图片列表
* @Author Youngxj
* @DateTime 2019-12-01
* @param [type] $url 相册ajax数据
* @return [type] [description]
*/
private function getImg($url)
{
// echo $url;exit;
$json = $this->curl_request($url, '', '', $this->cookie);
$arr = json_decode($json, 1);
if (isset($arr['data']['album']['name'])) {
$fileName = $arr['data']['album']['name'];
$myfile = @fopen($fileName . '.txt', 'a+');
if(!$myfile){
exit('文件写入失败，请检查目录读写权限是否正常');
}
$photos = array_values($arr['data']['photos']);
// echo json_encode($arr['data']['photos']);exit;
foreach ($photos as $key => $value) {
foreach ($photos[$key] as $keys => $values) {
// var_dump($key);var_dump($keys);
// var_dump($photos[$key][$keys]['1']['url']);
echo $text = $photos[$key][$keys]['1']['url'] . "\n";
fwrite($myfile, $text);
}
}
fclose($myfile);
}
}
/**
* 计算翻页
* @Author Youngxj
* @DateTime 2019-12-01
* @param [type] $url [description]
* @return [type] [description]
*/
private function ret($url)
{
$json = $this->curl_request($url, '', '', $this->cookie);
$arr = json_decode($json, 1);
// echo json_encode($arr);exit;
if (isset($arr['data']['album']['name'])) {
$total_count = $arr['data']['total_count'];
$page_count = ceil($total_count / 20);
// var_dump($total_count);exit;
for ($i = 0; $i <= $page_count; $i++) {
// var_dump($i);
$url = $this->url_set_value($url, 'ps', $i * 20);
// var_dump($url);exit;
$this->getImg($url);
}
// var_dump($page_count);exit;
// exit;
} else {
exit('error');
}
}
/**
* 获取相册列表
* @Author Youngxj
* @DateTime 2019-12-01
* @return [type] [description]
*/
public function getList()
{
$json = $this->curl_request($this->listApi, '', '', $this->cookie);
$arr = json_decode($json, 1);
if (isset($arr['data']['vFeeds'])) {
$newArr = $arr['data']['vFeeds'];
foreach ($newArr as $key => $value) {
$albumid = $newArr[$key]['pic']['albumid'];
$url = $this->url_set_value($this->imgApi, 'albumid', $albumid);
// echo $url."\n";
echo $this->ret($url);
}
} else {
exit('error');
}
}
/**
* curl模拟提交
* @param [type] $url 访问的URL
* @param string $post post数据(不填则为GET)
* @param string $referer 自定义来路
* @param string $cookie 提交的$cookies
* @param integer $returnCookie 是否返回$cookies
* @param string $ua 自定义UA
* @return [type] [description]
*/
private function curl_request($url, $post = '', $referer = '', $cookie = '', $returnCookie = 0, $ua = 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0')
{
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_USERAGENT, $ua);
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($curl, CURLOPT_AUTOREFERER, 1);
curl_setopt($curl, CURLOPT_TIMEOUT, 60);
curl_setopt($curl, CURLOPT_REFERER, $referer);
curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false);
$httpheader = "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8";
$httpheader = "Accept-Encoding:gzip, deflate";
$httpheader = "Accept-Language:zh-CN,zh;q=0.9";
$httpheader = "Connection:close";
curl_setopt($curl, CURLOPT_HTTPHEADER, $httpheader);
curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, false);
if ($post) {
curl_setopt($curl, CURLOPT_POST, 1);
curl_setopt($curl, CURLOPT_POSTFIELDS, http_build_query($post));
}
if ($cookie) {
curl_setopt($curl, CURLOPT_COOKIE, $cookie);
}
curl_setopt($curl, CURLOPT_HEADER, $returnCookie);
curl_setopt($curl, CURLOPT_TIMEOUT, 10);
curl_setopt($curl, CURLOPT_ENCODING, "gzip");
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
$data = curl_exec($curl);
if (curl_errno($curl)) {
return curl_error($curl);
}
curl_close($curl);
if ($returnCookie) {
list($header, $body) = explode("\r\n\r\n", $data, 2);
preg_match_all("/Set\-Cookie:([^;]*);/", $header, $matches);
$info['cookie'] = substr($matches[1][1], 1);
$info['content'] = $body;
return $info;
} else {
return $data;
}
}
/**
* 替换get参数
* @Author Youngxj
* @DateTime 2019-12-01
* @param [type] $url 地址
* @param [type] $key key
* @param [type] $value val
* @return [type] [description]
*/
private function url_set_value($url, $key, $value)
{
$a = explode('?', $url);
$url_f = $a[0];
$query = $a[1];
parse_str($query, $arr);
$arr[$key] = $value;
return $url_f . '?' . http_build_query($arr);
}
}
Ps：如何获取cookie及uin小杰就不再赘言了该泛型仅用于获取自己QQ空间相片链接，至于QQ好友相册没有适配获取的下载链接请使用下载工具进行下载（php不便捷下载）
