萬盛學電腦網

您现在的位置: 萬盛學電腦網 >> 程式設計 >  >> 網路程式設計 >> PHP 程式設計

PHP 郵件解析:使用 Mail_mimeDecode 從原始郵件提取主旨、發件人、正文與附件

為什麼需要專業郵件解析庫?

原始郵件(RFC 5322/MIME)結構複雜:多部分、Base64/Quoted-Printable 編碼、巢狀結構、編碼宣告、附件內嵌。手工正則解析極其脆弱。PEAR Mail_mimeDecode 是成熟解決方案,現代替代品有 php-mime-mail-parser/php-mime-mail-parser。

Mail_mimeDecode 核心用法

<?php
require_once 'Mail/mimeDecode.php';

$rawEmail = file_get_contents('php://stdin'); // 或從 POP3/IMAP 獲取

$params = [
    'include_bodies' => true,    // 包含正文內容
    'decode_bodies' => false,    // 手動解碼以控制編碼
    'decode_headers' => true,    // 自動解碼標題
];

$decoder = new Mail_mimeDecode($rawEmail);
$structure = $decoder->decode($params);

if (PEAR::isError($structure)) {
    die('郵件解析失敗:' . $structure->getMessage());
}

// 結構分析
print_r($structure);
/*
stdClass Object
(
    [headers] => Array ( [subject] => ..., [from] => ..., [to] => ..., [date] => ... )
    [ctype] => text/plain
    [ctype_parameters] => Array ( [charset] => utf-8 )
    [body] => 原始正文(未解碼)
    [parts] => Array ( ... 多部分結構 ...)
)
*/
?>

完整解析器:提取主旨、發件人、純文本/HTML 正文、附件

<?php
class EmailParser
{
    public function parse(string $rawEmail): array
    {
        require_once 'Mail/mimeDecode.php';
        
        $decoder = new Mail_mimeDecode($rawEmail);
        $structure = $decoder->decode([
            'include_bodies' => true,
            'decode_bodies' => false, // 我們自己處理編碼
            'decode_headers' => true,
        ]);
        
        if (PEAR::isError($structure)) {
            throw new RuntimeException('Parse failed: ' . $structure->getMessage());
        }
        
        return $this->extractParts($structure);
    }
    
    private function extractParts(stdClass $part, int $depth = 0): array
    {
        $result = [
            'headers' => $part->headers ?? [],
            'content_type' => $part->ctype ?? 'text/plain',
            'charset' => $part->ctype_parameters['charset'] ?? 'utf-8',
            'encoding' => $part->headers['content-transfer-encoding'] ?? '7bit',
            'disposition' => $part->disposition ?? 'inline',
            'filename' => $part->d_parameters['filename'] ?? ($part->ctype_parameters['name'] ?? null),
            'body_raw' => $part->body ?? '',
            'body' => '',
            'attachments' => [],
            'parts' => [],
        ];
        
        // 解碼正文
        $result['body'] = $this->decodeBody($result['body_raw'], $result['encoding'], $result['charset']);
        
        // 處理子部分
        if (!empty($part->parts)) {
            foreach ($part->parts as $subPart) {
                $subResult = $this->extractParts($subPart, $depth + 1);
                
                if ($subResult['disposition'] === 'attachment' || $subResult['filename']) {
                    $result['attachments'][] = $subResult;
                } else {
                    $result['parts'][] = $subResult;
                }
            }
        }
        
        return $result;
    }
    
    private function decodeBody(string $body, string $encoding, string $charset): string
    {
        // 1. 解碼傳輸編碼
        switch (strtolower($encoding)) {
            case 'base64':
                $body = base64_decode($body);
                break;
            case 'quoted-printable':
                $body = quoted_printable_decode($body);
                break;
            case '7bit':
            case '8bit':
            case 'binary':
            default:
                break;
        }
        
        // 2. 轉換字符編碼到 UTF-8
        $charset = strtoupper($charset);
        if ($charset !== 'UTF-8' && function_exists('iconv')) {
            $body = @iconv($charset, 'UTF-8//IGNORE', $body) ?: $body;
        }
        
        return $body;
    }
    
    /** 獲取最佳正文:優先 text/plain,其次 text/html */
    public function getBestBody(array $parsed): string
    {
        // 遞歸查找
        $finder = function (array $part) use (&$finder) {
            if (str_starts_with($part['content_type'], 'text/plain')) {
                return $part['body'];
            }
            foreach ($part['parts'] as $sub) {
                if ($text = $finder($sub)) return $text;
            }
            return null;
        };
        
        $plain = $finder($parsed);
        if ($plain) return $plain;
        
        // 找 HTML 並轉純文本
        $htmlFinder = function (array $part) use (&$htmlFinder) {
            if (str_starts_with($part['content_type'], 'text/html')) {
                return $part['body'];
            }
            foreach ($part['parts'] as $sub) {
                if ($html = $htmlFinder($sub)) return $html;
            }
            return null;
        };
        
        $html = $htmlFinder($parsed);
        return $html ? $this->htmlToText($html) : '';
    }
    
    private function htmlToText(string $html): string
    {
        $dom = new DOMDocument();
        @$dom->loadHTML('' . $html);
        $text = '';
        foreach ($dom->getElementsByTagName('body')->item(0)?->childNodes ?? [] as $node) {
            $text .= $this->nodeToText($node) . "\n";
        }
        return trim($text);
    }
    
    private function nodeToText(DOMNode $node): string
    {
        if ($node->nodeType === XML_TEXT_NODE) return $node->textContent;
        if (in_array($node->nodeName, ['br', 'p', 'div', 'li'])) return "\n";
        $text = '';
        foreach ($node->childNodes as $child) $text .= $this->nodeToText($child);
        return $text;
    }
}
?>

POP3 郵件收取與解析整合流程

<?php
// 使用 Net_POP3 (PEAR) 或 php-imap 擴展
// 這裡展示概念流程

function fetchAndParseEmails(string $host, int $port, string $user, string $pass): Generator
{
    // 連接 POP3
    $pop3 = new Net_POP3();
    if (!$pop3->connect($host, $port)) throw new Exception('連接失敗');
    if (!$pop3->login($user, $pass)) throw new Exception('登入失敗');
    
    $list = $pop3->getListing();
    $parser = new EmailParser();
    
    foreach ($list as $msg) {
        $raw = $pop3->getMsg($msg['msg_id']);
        $parsed = $parser->parse($raw);
        
        // 業務邏輯:提取關鍵資訊
        yield [
            'msg_id' => $msg['msg_id'],
            'from' => $parsed['headers']['from'] ?? '',
            'subject' => $parsed['headers']['subject'] ?? '',
            'date' => $parsed['headers']['date'] ?? '',
            'body_text' => $parser->getBestBody($parsed),
            'attachments' => array_map(fn($a) => [
                'filename' => $a['filename'],
                'type' => $a['content_type'],
                'size' => strlen($a['body_raw']),
                'content' => $a['body_raw'], // 或存檔後返回路徑
            ], $parsed['attachments']),
        ];
        
        // 標記刪除或保留
        // $pop3->deleteMsg($msg['msg_id']);
    }
    
    $pop3->disconnect();
}
?>

現代替代庫:php-mime-mail-parser(Composer 友善、無 PEAR 依賴)

<?php
// composer require php-mime-mail-parser/php-mime-mail-parser
use PhpMimeMailParser\Parser;

$parser = new Parser();
$parser->setText($rawEmail); // 或 setPath($filePath)

$to = $parser->getHeader('to');
$from = $parser->getHeader('from');
$subject = $parser->getHeader('subject');
$textBody = $parser->getMessageBody('text');
$htmlBody = $parser->getMessageBody('html');
$attachments = $parser->getAttachments();

foreach ($attachments as $attachment) {
    $filename = $attachment->getFilename();
    $content = $attachment->getContent();
    $mimeType = $attachment->getContentType();
    // file_put_contents("/tmp/$filename", $content);
}
?>

常見問題與解決

問題原因解決
中文主旨亂碼RFC 2047 編碼 (=?UTF-8?B?...?=)decode_headers=true 自動處理,或手動 iconv_mime_decode()
附件檔名亂碼檔名編碼同主旨用 mailparse_rfc822_parse_addresses() 或 Parser 內建方法
大郵件記憶體耗盡一次性載入完整郵件用 imap_fetchbody 分段獲取、或流式解析庫
內嵌圖片 CID 引用HTML 中 <img src="cid:...">解析附件 Content-ID,替換 HTML 中對應 CID
簽名驗證 (DKIM/SPF/DMARC)需檢查標頭用 mailparse 或專用 DKIM 驗證庫

總結

郵件解析關鍵在於:正確處理 MIME 多部分結構、傳輸編碼解碼、字符集轉換、附件識別。現代專案建議使用 php-mime-mail-parser 替代 PEAR 套件,無依賴衝突、支援 Composer、API 更直觀。若處理大量郵件,考慮 IMAP IDLE 推模式替代 POP3 輪詢,並將附件存儲到物件存儲而非資料庫。

copyright © 萬盛學電腦網 all rights reserved