在使用 PHP 做簡單的爬蟲的時候,我們經常會遇到需要下載遠程圖片的需求,所以下面來簡單實現這個需求
1:使用curl
比如我們有下面這兩張圖片:
$images = [ 'https://img.alicdn.com/tps/TB1jjaYOFXXXXa2aXXXXXXXXXXX-276-402.jpg_150x10000q90.jpg', 'https://img.alicdn.com/tfs/TB15QQ5cgMPMeJjy1XbXXcwxVXa-520-280.jpg_q90_.webp' ];
第一步,我們可以直接來使用最簡單的代碼實現:
function download($url, $path = 'images/') { $ch = curl_init(); curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false); // 信任任何證書 curl_setopt($ch, CURLOPT_URL, $url); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 30); $file = curl_exec($ch); curl_close($ch); $filename = pathinfo($url, PATHINFO_BASENAME); $resource = fopen($path . $filename, 'a'); fwrite($resource, $file); fclose($resource); }
那么在下載遠程圖片的時候就可以這樣:
foreach ( $images as $url ) { download($url); }
1:封裝成一個類
縷清思路之后,我們可以將這個基本的功能封裝到一個類中:
class Spider { public function downloadImage($url, $path = 'images/') { $ch = curl_init(); curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false); // 信任任何證書 curl_setopt($ch, CURLOPT_URL, $url); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 30); $file = curl_exec($ch); curl_close($ch); $filename = pathinfo($url, PATHINFO_BASENAME); $resource = fopen($path . $filename, 'a'); fwrite($resource, $file); fclose($resource); } }
或者,我們還可以這樣稍微優化一下:
class Spider { public function downloadImage($url, $path='images/') { $ch = curl_init(); curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false); // 信任任何證書 curl_setopt($ch, CURLOPT_URL, $url); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 30); $file = curl_exec($ch); curl_close($ch); $this->saveAsImage($url, $file, $path); } private function saveAsImage($url, $file, $path) { $filename = pathinfo($url, PATHINFO_BASENAME); $resource = fopen($path . $filename, 'a'); fwrite($resource, $file); fclose($resource); } }
封裝成類之后,我們可以這樣調用代碼來下載圖片:
$spider = new Spider(); foreach ( $images as $url ) { $spider->downloadImage($url); }
這樣,對一般可訪問的遠程圖片下載就OK了....
或者再這樣完善下下載方法的封裝:
/** * 下載遠程圖片保存到本地 * @access public * @author lxhui<772932587@qq.com> * @since 1.0 * @return array * @params string $url 遠程圖片地址 * @params string $save_dir 需要保存的地址 * @params string $filename 保存文件名 */ function download($url, $save_dir = './public/upload/loan/',$filename='') { if(trim($save_dir)=='') $save_dir='./'; if(trim($filename)==''){//保存文件名 $allowExt = array('gif', 'jpg', 'jpeg', 'png', 'bmp'); $ext=strrchr($url,'.'); if(!in_array($ext,$allowExt)) return array('file_name'=>'','save_path'=>'','error'=>3); $filename=time().$ext; } if(0!==strrpos($save_dir,'/')) $save_dir.='/'; //創建保存目錄 if(!file_exists($save_dir)&&!mkdir($save_dir,0777,true)) return array('file_name'=>'','save_path'=>'','error'=>5); $ch = curl_init(); curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false); // 信任任何證書 curl_setopt($ch, CURLOPT_URL, $url); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 30); $file = curl_exec($ch); curl_close($ch); $filename = pathinfo($url, PATHINFO_BASENAME); $resource = fopen($save_dir . $filename, 'a'); fwrite($resource, $file); fclose($resource); unset($file,$url); return array('file_name'=>$filename,'save_path'=>$save_dir.$filename,'error'=>0); }
