Fetching attachments from gmail via either python or php

Question

I have been trying to find information on how to retrieve attachments from a gmail account in either python or PHP, I\'m hoping that someone here can be of some help, thanks.

Answer 1

I found some code that works! this will download any attachments to a selected folder

<?php 

$gmail_username = 'username@gmail.com';
$gmail_password = 'mypassword';

$imap = imap_open ("{imap.gmail.com:993/imap/ssl}INBOX", $gmail_username, $gmail_password) or die("can't connect: " . imap_last_error());
$savefilepath = 'path/to/images_folder/'; //absolute path to images directory
$imagefilepath = 'images/'; //relative path to images directory

$headers = imap_headers($imap);
foreach ($headers as $mail) {
    $flags = substr($mail, 0, 4);
    //Check for unread msgs, get their UID, and queue them up
    if (strpos($flags, "U")) {
        preg_match('/[0-9]+/',$mail,$match);
        $new_msg[] = implode('',$match);     
    }
}

if ($new_msg) {
    foreach ($new_msg as $result) {
        $structure = imap_fetchstructure($imap,$result);
        $parts = $structure->parts;
        foreach ($parts as $part) {
            if ($part->parameters[0]->attribute == "NAME") {
                //Generate a filename with format DATE_RANDOM#_ATTACHMENTNAME.EXT
                $savefilename = date("m-d-Y") . '_' . mt_rand(rand(), 6) . '_' . $part->parameters[0]->value;
                save_attachment(imap_fetchbody($imap,$result,2),$savefilename,$savefilepath,$savethumbpath);
                imap_fetchbody($imap,$result,2); //This marks message as read
            } 
        }
    }
}

imap_close($imap);

function save_attachment( $content , $filename , $localfilepath, $thumbfilepath ) {
    if (imap_base64($content) != FALSE) {   
        $file = fopen($localfilepath.$filename, 'w');
        fwrite($file, imap_base64($content));
        fclose($file);
    }
}
?>

Answer 2

The php docs for imap_open explain connecting to gmail in the comments (e.g. 31-Oct-2007 07:50):

$mbox = imap_open("{imap.gmail.com:993/imap/ssl}INBOX", "username@gmail.com", "password") or die("can't connect: " . imap_last_error());

Where, obviously, you have to fill in the actual username and password as appropriate, and then to identify the attachments in the parts of the email you follow the instructions from: http://www.electrictoolbox.com/extract-attachments-email-php-imap/

Which, summarizing, says that you use:

// in a for($i=1;$i<$nummsgs;$i++) loop over all the messages in the inbox $structure = imap_fetchstructure($mbox, $i);

to identify the attachments in the structure. However, that is a rather elaborate process of deconstructing MIME messages (which have a lot of optional variability that must be accounted for), so the fundamentals/outline of a function for that is in that electrictoolbox page.

Answer 3

I recently worked on this topic and here is the code which works well. It also saves the details of the attachments in a word document with the following details:
-> Date
-> Time
-> From
-> Email ID
-> Subject










<?php 


 /*
    *   Gmail attachment extractor.
    *
    *   Downloads attachments from Gmail and saves it to a file.
    *   Uses PHP IMAP extension, so make sure it is enabled in your php.ini,
    *   extension=php_imap.dll
    *
    */

    header('Content-type:application\msword');
    header('Content-Disposition:attachment;Filename=document_name.doc');
    set_time_limit(0); 
    /* connect to gmail with your credentials */
    $hostname = '{imap.googlemail.com:993/imap/ssl}INBOX';
    $username = 'email@gmail.com';
    $password = 'password';
    /* try to connect */
    $inbox = imap_open($hostname,$username,$password) or die('Cannot connect to       
    Gmail: ' . imap_last_error());
    /* get all new emails. If set to 'ALL' instead 
    * of 'NEW' retrieves all the emails, but can be 
    * resource intensive, so the following variable, 
    * $max_emails, puts the limit on the number of emails downloaded.
    * 
    */
    $emails = imap_search($inbox,'ALL');
    /* useful only if the above search is set to 'ALL' */
    $max_emails = 110;


    /* if any emails found, iterate through each email */
    if($emails){
    $count = 1;

    /* put the newest emails on top */
    rsort($emails);
    /* for every email... */
    foreach($emails as $email_number){
    /* get information specific to this email */
    //$overview = imap_fetch_overview($inbox,$email_number,0);
    $check=imap_check($inbox);
    $result=imap_fetch_overview($inbox,"1:{$check->Nmsgs}",0);
    foreach($result as $overview){
    echo "#{$overview->msgno}({$overview->date})-From: {$overview->from}
    {$overview->subject}\n"}
    /* get mail message */
    $message = imap_fetchbody($inbox,$email_number,2);
    /* get mail structure */
    $structure =imap_fetchstructure($inbox, $email_number);
    //$functions = array('function1' => imap_fetchstructure($inbox,
    $email_number));
    //print_r(array_keys($functions));
    $attachments = array();
    //print_r(array_keys($attachments[$i]));
    if($structure->parts[$i]->ifdparameters){
    foreach($structure->parts[$i]->dparameters as $object){
    if(strtolower($object->attribute) == 'filename'){
    $attachments[$i]['is_attachment'] = true;
    $attachments[$i]['filename'] = $object->value;
        }
       }
      }
       if($structure->parts[$i]->ifparameters) 
       {
         foreach($structure->parts[$i]->parameters as $object) 
         {
             if(strtolower($object->attribute) == 'name') 
            {
                $attachments[$i]['is_attachment'] = true;
                $attachments[$i]['name'] = $object->value;
            }
        }
     }
     if($attachments[$i]['is_attachment']){
     $attachments[$i]['attachment']imap_fetchbody($inbox,$email_number,$i+1);
     /* 4 = QUOTED-PRINTABLE encoding */
     if($structure->parts[$i]->encoding == 3){ 
     $attachments[$i]['attachment'] = base64_decode($attachments[$i]  
           ['attachment']);
      }
      /* 3 = BASE64 encoding */
      elseif($structure->parts[$i]->encoding == 4){ 
      $attachments[$i]['attachment'] =              

      quoted_printable_decode($attachments[$i]['attachment']);
      }

       }
      }
     }
       /* iterate through each attachment and save it */
       foreach($attachments as $attachment)
       {
       if($attachment['is_attachment'] == 1){
        $filename = $attachment['name'];
        if(empty($filename)) $filename = $attachment['filename'];
        if(empty($filename)) $filename = time() . ".dat";
       /* prefix the email number to the filename in case two emails
       * have the attachment with the same file name.
       */
       $fp = fopen($email_number . "-" . $filename, "w+");
       fwrite($fp, $attachment['attachment']);
        fclose($fp);
        }

        }

          if($count++ >= $max_emails) break;


         }

       } 

        /* close the connection */

       imap_close($inbox);

  ?>

Answer 4

You will have to enable IMAP access to your GMail account (Settings → Forwarding and POP/IMAP), and then use imaplib.IMAP4_SSL to access it.

Use the raw text of every message as an argument to email.message_from_string in order to process any attachments.

Answer 5

I took the code above and fixed it and tested it. It works with PHP5.

<?php 

$gmail_username = 'email@gmail.com';
$gmail_password = 'password';
$imap = imap_open ("{imap.gmail.com:993/imap/ssl}INBOX", $gmail_username, $gmail_password) or die("can't connect: " . imap_last_error());
$savefilepath = '//Server/share/Local/Pathname/'; //absolute path to images directory
$imagefilepath = '/Local/Pathname/'; //relative path to images directory
$savethumbpath = '/Local/Pathname/'; //relative path to images directory
$headers = imap_headers($imap);
foreach ($headers as $mail) {
    $flags = substr($mail, 0, 4);
    //Check for unread msgs, get their UID, and queue them up
    if (strpos($flags, "U")) {
        preg_match('/[0-9]+/',$mail,$match);
        $new_msg[] = implode('',$match);     
    }
}
if ($new_msg) {
    foreach ($new_msg as $result) {
        $structure = imap_fetchstructure($imap,$result);
        $parts = $structure->parts;
        foreach ($parts as $part) {
            if ($part->parameters[0]->attribute == "NAME") {
                //Generate a filename with format DATE_RANDOM#_ATTACHMENTNAME.EXT
                $savefilename = date("m-d-Y") . '_' . rand() . '_' . $part->parameters[0]->value;
                   save_attachment(imap_fetchbody($imap,$result,2),$savefilename,$savefilepath,$savethumbpath);
                imap_fetchbody($imap,$result,2); //This marks message as read
            } 
        }
    }
}
/* grab emails */
$emails = imap_search($imap,'ALL');
/* if emails are returned, cycle through each... */
if($emails) {
  /* put the newest emails on top */
  $total = imap_num_msg($imap);
  /* for every email... */
  for( $i = $total; $i >= 1; $i--) {
        $headers = imap_header($imap, $i);
        $from = $headers->from[0]->mailbox . "@" . $headers->from[0]->host;
        echo $from . "\n";
        imap_delete($imap,$i);
        imap_mail_move($imap,"$i:$i", "[Gmail]/Trash"); // Change or remove this line if you are not connecting to gmail. The path to the Trash folder in your Gmail may be different, capitalization is relevant.
  }
}else{
        echo "no emails";
}
/* close the connection */
   imap_expunge($imap);
   imap_close($imap);

function save_attachment( $content , $filename , $localfilepath, $thumbfilepath ) {
     if (imap_base64($content) != FALSE) {   
         $file = fopen($localfilepath.$filename, 'w');
         fwrite($file, imap_base64($content));
         fclose($file);
     }
}
?>