Web page capture-PHP Tutorial-php.cn

Web page capture

WBOY

Release： 2016-07-25 08:49:44

Original

1144 people have browsed it

header('Content-Type:text/html;charset=utf-8');
/**
* A class for grabbing pictures
* @author tangpan
*/
class download_image {
public $_save_path = NULL; / /Picture saving road
public $_limit_size = NULL; //Limit the size of the picture
public static $_img_url_old = array(); //Storage the captured picture link address
public static $_a_page_url = array(); // Store the crawled page
public function __construct( $_save_path, $_limit_size) {
$this->_save_path = $_save_path;
$this->_limit_size = $_limit_size;
}
public function get_all_page_image( $site_url ) {
if ( $site_url == '' ) {
return false;
}
if ( ! in_array( $site_url, self::$_a_page_url ) ) { //Determine whether the current page has been crawled
self::$ _a_page_url[] = $site_url; //Save the hyperlink into a static array
} else {
return; //If it has been crawled, jump out
}
$this->download_the_page_image( $site_url );
$content = @file_get_contents($site_url);
$a_page_url = "|]+href=['" ]?([^ '"?]+)['" >]|U";
$ all_url = array();
preg_match_all( $a_page_url, $content, $all_url, PREG_SET_ORDER );
if ( $all_url != NULL ) {
foreach( $all_url as $key => $val ) {
/**
* Static hyperlinks to prevent entering an infinite loop
* Exit the current page link representation ('', '#', '/')
*/
if ( trim($val[1]) != '' && ! in_array( $val[1], self::$_a_page_url ) && ! in_array( $val[1], array('# ','/',$site_url) ) ) {
self::$_a_page_url[] = $val[1]; //Write qualified hyperlinks into a static array
}
}
}
if ( self ::$_a_page_url != NULL ) {
foreach( self::$_a_page_url as $keys => $vals ) {
if ( strpos( $vals, 'http://' ) === false ) { // When the hyperlink does not contain http://, it cannot be accessed directly
// When the image link address is a relative address, the address is reassembled
$a_domain_url = substr( $site_url, 0, strpos( $site_url, '/',8 ) + 1 );
$a_img_url = $a_domain_url.$vals;
}
//Recursive call, access each hyperlink page
$this->get_all_page_image( $a_img_url );
}
}
}
/**
* Download all image links under the current page
* @param $site_url
*/
public function download_the_page_image( $site_url ) {
// Get all the contents of the current link address page
$img_pattern = NULL;
$content = @file_get_contents( $site_url );
$img_pattern = "|< img[^>]+src=['" ]?([^ '"?]+)['" >]|U";
//Globally match all image links in
$img_out = array();
preg_match_all( $img_pattern, $content, $img_out, PREG_SET_ORDER );
echo '
'. $site_url . 'Total found' . count($img_out) . 'Pictures< /h1>';
//print_r($img_out[1]);
foreach( $img_out as $key => $val ) {
//echo htmlspecialchars($val[1]).'
';
$this->save_one_image( $site_url, $val[1]);
}
}
public function save_one_image( $site_url, $img_url ) {
if ( strpos( $img_url, 'http ://' ) === false ) {
// When the image link address is a relative address, the address is reassembled
$domain_url = substr( $site_url, 0, strpos( $site_url, '/',8 ) + 1 ) ;
$img_url = $domain_url.$img_url;
}
$pic_name = basename( $img_url ); //Get the picture name
if ( in_array( $img_url, self::$_img_url_old ) ) {
echo $img_url . 'This image has been captured!
';
return;
}
//Get the image content and write it into a string
$img_data = @file_get_contents( $img_url );
if ( strlen($img_data) < $this->_limit_size ) { //The image size is within the limit
$img_boo = @file_put_contents( $this->_save_path.md5(microtime()).$pic_name, $img_data );
if ( $img_boo ) {
echo $img_url .'The picture was saved successfully!
';
self::$_img_url_old[] = $img_url;
} else {
echo $img_url .'Picture saving failed!
';
}
} else {
echo $img_url .'The image size is within the limit outside!
';
}
}
}
set_time_limit(0);
$download_images = new download_image('surces_Img/',1024*1024*100);
$download_images-> get_all_page_image('http://www.22mm.cc/');
?>

Copy code

Web page capture

'. $site_url . 'Total found' . count($img_out) . 'Pictures< /h1>';