class GzhController extends BaseController
{
public $layout='main';
/**
* {@inheritdoc}
*/
public function actions()
{
return [
'error' => [
'class' => 'yii\web\ErrorAction',
'layout' => 'empty'
]
];
}
//微信内容div正则
private $wxContentDiv = '/<div class="rich_media_content " id="js_content" style="visibility: hidden;">(.*?)<\/div>/s';
//微信图片样式
private $imageStyle = 'style="max-width: 677px !important;height: auto !important;visibility: visible !important;"';
public function actionCraw()
{
$url = 'https://mp.weixin.qq.com/s/1wCHJEqxOWxSSeNJTlqmzQ';
$content = $this->_get($url);
$basicInfo = $this->articleBasicInfo($content);
list($content_html, $content_text) = $this->contentHandle($content);
$data = array_merge($basicInfo,['content_html' => $content_html,'content_text' => $content_text]);
exit($data['content_html']);
}
/**
* 爬取内容
* @param $url
* @return false|string
* @author bignerd
* @since 2016-08-16T10:13:58+0800
*/
private function _get($url)
{
return file_get_contents($url);
}
/**
* 处理微信文章源码,提取文章主体,处理图片链接
* @author bignerd
* @since 2016-08-16T15:59:27+0800
* @param $content 抓取的微信文章源码
* @return [带图html文本,无图html文本]
*/
private function contentHandle($content)
{
$content_html_pattern = $this->wxContentDiv;
preg_match_all($content_html_pattern, $content, $html_matchs);
if(empty(array_filter($html_matchs))) {
echo '文章不存在';
exit();
}
$content_html = $html_matchs[0][0];
//去除掉hidden隐藏
$content_html = str_replace('style="visibility: hidden;"','',$content_html);
//过滤掉iframe
$content_html = preg_replace('/<iframe(.*?)<\/iframe>/','',$content_html);
$path = '../article/';
/** @var 带图片html文本 */
$content_html = preg_replace_callback('/data-src="(.*?)"/',
function($matches) use ($path){
$suffix = substr($matches[1],strrpos($matches[1],'wx_fmt=')+7,strlen($matches[1]));//获取图片后缀
return 'src="' . $path . $this->getImg($matches[1],$suffix).'" '.$this->imageStyle;
},
$content_html);
//添加微信样式
$content_html = '<div style="max-width: 677px;margin-left: auto;margin-right: auto;">'.$content_html. '</div>';
/** @var 无图html文本 */
$content_text = preg_replace('/<img.*?>/s','',$content_html);
return [$content_html,$content_text];
}
/**
* 获取文章的基本信息
* @author bignerd
* @since 2016-08-16T17:16:32+0800
* @param $content 文章详情源码
* @return $basicInfo
*/
private function articleBasicInfo($content)
{
//待获取item
$item = [
'ct' => 'date',//发布时间
'msg_title' => 'title',//标题
'msg_desc' => 'digest',//描述
'msg_link' => 'content_url',//文章链接
'msg_cdn_url' => 'cover',//封面图片链接
'nickname' => 'wechatname',//公众号名称
];
$basicInfo = [
'author' => '',
'copyright_stat' => '',
];
foreach ($item as $k => $v) {
if($k == 'msg_title')
$pattern = '/ var '.$k.' = (.*?)\.html\(false\);/s';
else
$pattern = '/ var '.$k.' = "(.*?)";/s';
preg_match_all($pattern,$content,$matches);
if(array_key_exists(1, $matches) && !empty($matches[1][0])){
$basicInfo[$v] = $this->htmlTransform($matches[1][0]);
}else{
$basicInfo[$v] = '';
}
}
//2020/4/3获取作者已失效
// /** 获取作者 */
// preg_match('/<em class="rich_media_meta rich_media_meta_text">(.*?)<\/em>/s', $content, $matchAuthor);
// if(!empty($matchAuthor[1])) $basicInfo['author'] = $matchAuthor[1];
// /** 文章类型 */
// preg_match('/<span id="copyright_logo" class="rich_media_meta meta_original_tag">(.*?)<\/span>/s', $content, $matchType);
// if(!empty($matchType[1])) $basicInfo['copyright_stat'] = $matchType[1];
return $basicInfo;
}
/**
* 特殊字符转换
* @author bignerd
* @since 2016-08-16T17:30:52+0800
* @param $string
* @return $string
*/
private function htmlTransform($string)
{
$string = str_replace('"','"',$string);
$string = str_replace('&','&',$string);
$string = str_replace('amp;','',$string);
$string = str_replace('<','<',$string);
$string = str_replace('>','>',$string);
$string = str_replace(' ',' ',$string);
$string = str_replace("\\", '',$string);
return $string;
}
/**
* @param $url
* @return string
*/
private function getImg($url,$suffix){
$refer = "http://www.qq.com/";
$opt = [
'http'=>[
'header'=>"Referer: " . $refer
]
];
$context = stream_context_create($opt);
//接受数据流
$file_contents = file_get_contents($url,false, $context);
$imageSteam = Imagecreatefromstring($file_contents);
$path = 'article/';
if(!file_exists($path))
mkdir($path,0777,true);
$fileName = time().rand(0,99999) . '.'.$suffix;
//生成新图片
if ($suffix == 'png'){
$bg = imagecolorallocate($imageSteam, 0, 0, 0);
imagecolortransparent($imageSteam,$bg);
imagefill($imageSteam, 0, 0, $bg);
imagepng($imageSteam, $path . $fileName);
}elseif ($suffix == 'gif'){
imagegif($imageSteam, $path . $fileName);
}else{
imagejpeg($imageSteam, $path . $fileName);
}
return $fileName;
}
}