Php remote website image capture and save code

Php remote website image capture and save code

Example: php code for capturing website data. /** * A category used to capture images * * @ Package default * @ Author WuJunwei */ Class download_image { Public $ save_path; // save the image capture address // The size limit of the captured image (unit: Byte) is greater than the size limit. Public $ img_size = 0; // Define a static array to record the URL of a previously crawled hyperlink to avoid repeated capturing Public static $ a_url_arr = array (); /** * @ Param String $ save_path: address for saving the captured image * @ Param Int $ img_size: address for saving the captured image */ Public function _ construct ($ save_path, $ img_size) { $ This-> save_path = $ save_path; $ This-> img_size = $ img_size; } /** * Recursive method for downloading and capturing pictures on the home page and its subpages (recursive recursion) * * @ Param String $ capture_url the URL used to capture the image * */ Public function recursive_download_images ($ capture_url) { If (! In_array ($ capture_url, self: $ a_url_arr) // never captured { Self: $ a_url_arr [] = $ capture_url; // included in the static array } Else // crawled and exited the function directly { Return; } $ This-> download_current_page_images ($ capture_url); // download all images on the current page // Use @ to block the warning error caused by the unreadable captured address. $ Content = @ file_get_contents ($ capture_url ); // Match the href attribute of tag? Previous regular expressions $ A_pattern = "|] + href = ['\"]? ([^ '\ "?] +) ['\ ">] | U "; Preg_match_all ($ a_pattern, $ content, $ a_out, PREG_SET_ORDER ); $ Tmp_arr = array (); // defines an array to store the hyperlink address for capturing images in the current loop. Foreach ($ a_out as $ k => $ v) { /** * Remove the null '', '#', '/' and repeated values in the hyperlink. * 1: The value of the hyperlink address cannot be equal to the url of the currently crawled page. Otherwise, the url will be in an endless loop. * 2: The hyperlink is ''or '#', and '/' is also the current page, which will also fall into an endless loop, * 3: sometimes a hyperlink address appears multiple times on a webpage. if this address is not removed, a subpage is repeatedly downloaded) */ If ($ v [1] &! In_array ($ v [1], self: $ a_url_arr )&&! In_array ($ v [1], array ('#', '/', $ capture_url ))) { $ Tmp_arr [] = $ v [1]; } } Foreach ($ tmp_arr as $ k => $ v) { // URL of the hyperlink If (strpos ($ v, 'http ://')! = False) // if the url contains http: //, you can directly access { $ A_url = $ v; } Else // otherwise, it indicates the relative address. you need to splice the hyperlink's access address. { $ Domain_url = substr ($ capture_url, 0, strpos ($ capture_url, '/', 8) + 1 ); $ A_url = $ domain_url. $ v; } $ This-> recursive_download_images ($ a_url ); } } /** * Download all images on the current webpage * * @ Param String $ capture_url the webpage address used to capture images * @ Return Array an Array of the URLs of all img tags on the current webpage */ Public function download_current_page_images ($ capture_url) { $ Content = @ file_get_contents ($ capture_url); // block warning errors // Matching the src attribute of the img label? Previous regular expressions $ Img_pattern = "|] + src = ['\"]? ([^ '\ "?] +) ['\ ">] | U "; Preg_match_all ($ img_pattern, $ content, $ img_out, PREG_SET_ORDER ); $ Photo_num = count ($ img_out ); // Number of matched images Echo ''. $ capture_url." found ". $ photo_num." images "; Foreach ($ img_out as $ k => $ v) { $ This-> save_one_img ($ capture_url, $ v [1]); } } /** * How to save a single image * * @ Param String $ capture_url the webpage address used to capture images * @ Param String $ img_url the url of the image to be saved * */ Public function save_one_img ($ capture_url, $ img_url) { // Image path If (strpos ($ img_url, 'http ://')! = False) { // $ Img_url = $ img_url; } Else { $ Domain_url = substr ($ capture_url, 0, strpos ($ capture_url, '/', 8) + 1 ); $ Img_url = $ domain_url. $ img_url; } $ Pathinfo = pathinfo ($ img_url); // Obtain the image path information $ Pic_name = $ pathinfo ['basename']; // Obtain the image name. If (file_exists ($ this-> save_path. $ pic_name) // if the image exists, it indicates that it has been crawled and exits the function. { Echo $ img_url. 'the image has been captured! '; Return; } // Read the image content into a string $ Img_data = @ file_get_contents ($ img_url); // block the warning error caused by the inability to read the image address. If (strlen ($ img_data)> $ this-> img_size) // download an image with a larger size ratio. { $ Img_size = file_put_contents ($ this-> save_path. $ pic_name, $ img_data ); If ($ img_size) { Echo $ img_url. 'the image is saved successfully! '; } Else { Echo $ img_url. 'an error occurred while saving the image! '; } } Else { Echo $ img_url. 'reading the image failed! '; } } } // END Set_time_limit (120); // sets the maximum execution time of the script based on actual conditions. $ Download_img = new download_image ('E:/images/', 0); // instantiate the downloaded image object $ Download_img-> recursive_download_images ('http: // bbs.it-home.org/'); // recursive image capturing method // $ Download_img-> download_current_page_images ($ _ POST ['capture _ url']); // only capture the image of the current page ?>