Performing Sqlite Database Forensics

执行 SQLite 数据库取证

概述

SQLite 是全球部署最广泛的数据库引擎，几乎每个移动应用、Web 浏览器和许多桌面应用都使用它存储用户数据。在数字取证（Digital Forensics）中，SQLite 数据库是包含浏览器历史、消息记录、通话日志、GPS 位置、应用偏好设置和缓存内容的关键证据来源。取证分析超越了简单的 SQL 查询，需要检查内部 B 树（B-tree）页面结构、包含已删除记录的空闲列表（Freelist）页面、保存事务历史的写前日志（WAL，Write-Ahead Log）文件，以及数据库页面中删除后仍可能保留可恢复数据的未分配空间。

前置条件

• DB Browser for SQLite（sqlitebrowser）
• SQLite 命令行工具（sqlite3）
• Python 3.8+ 及 sqlite3 模块
• Belkasoft Evidence Center 或 Axiom（商业版）
• 十六进制编辑器（HxD、010 Editor）用于手动页面检查
• 理解 B 树数据结构

SQLite 内部结构

数据库头部（前 100 字节）

页面类型

已删除记录恢复

方法 1：空闲列表页面分析

删除记录时，SQLite 可能将其页面放入空闲列表而非立即覆盖。

import struct
import sqlite3
import os


def analyze_freelist(db_path: str) -> dict:
    """分析 SQLite 空闲列表，识别包含已删除数据的页面。"""
    with open(db_path, "rb") as f:
        # 读取头部
        header = f.read(100)
        page_size = struct.unpack(">H", header[16:18])[0]
        if page_size == 1:
            page_size = 65536
        first_freelist_page = struct.unpack(">I", header[32:36])[0]
        total_freelist_pages = struct.unpack(">I", header[36:40])[0]

        freelist_info = {
            "page_size": page_size,
            "first_freelist_page": first_freelist_page,
            "total_freelist_pages": total_freelist_pages,
            "trunk_pages": [],
            "leaf_pages": []
        }

        if first_freelist_page == 0:
            return freelist_info

        # 遍历空闲列表主干链
        trunk_page = first_freelist_page
        while trunk_page != 0:
            offset = (trunk_page - 1) * page_size
            f.seek(offset)
            page_data = f.read(page_size)

            next_trunk = struct.unpack(">I", page_data[0:4])[0]
            leaf_count = struct.unpack(">I", page_data[4:8])[0]

            leaves = []
            for i in range(leaf_count):
                leaf_page = struct.unpack(">I", page_data[8 + i * 4:12 + i * 4])[0]
                leaves.append(leaf_page)

            freelist_info["trunk_pages"].append({
                "page_number": trunk_page,
                "next_trunk": next_trunk,
                "leaf_count": leaf_count,
                "leaf_pages": leaves
            })
            freelist_info["leaf_pages"].extend(leaves)
            trunk_page = next_trunk

    return freelist_info


def extract_freelist_content(db_path: str, output_dir: str):
    """提取空闲列表页面的原始内容以供分析。"""
    info = analyze_freelist(db_path)
    os.makedirs(output_dir, exist_ok=True)

    with open(db_path, "rb") as f:
        page_size = info["page_size"]
        for page_num in info["leaf_pages"]:
            offset = (page_num - 1) * page_size
            f.seek(offset)
            page_data = f.read(page_size)
            output_file = os.path.join(output_dir, f"freelist_page_{page_num}.bin")
            with open(output_file, "wb") as out:
                out.write(page_data)

    return len(info["leaf_pages"])

方法 2：WAL（写前日志）分析

WAL 文件包含尚未检查点写回主数据库的待处理事务。

def parse_wal_header(wal_path: str) -> dict:
    """解析 SQLite WAL 文件头部和帧清单。"""
    with open(wal_path, "rb") as f:
        header = f.read(32)
        magic = struct.unpack(">I", header[0:4])[0]
        file_format = struct.unpack(">I", header[4:8])[0]
        page_size = struct.unpack(">I", header[8:12])[0]
        checkpoint_seq = struct.unpack(">I", header[12:16])[0]
        salt1 = struct.unpack(">I", header[16:20])[0]
        salt2 = struct.unpack(">I", header[20:24])[0]

        wal_info = {
            "magic": hex(magic),
            "format": file_format,
            "page_size": page_size,
            "checkpoint_sequence": checkpoint_seq,
            "frames": []
        }

        # 解析帧（每帧 24 字节头部 + page_size 数据）
        frame_offset = 32
        frame_num = 0
        file_size = os.path.getsize(wal_path)

        while frame_offset + 24 + page_size <= file_size:
            f.seek(frame_offset)
            frame_header = f.read(24)
            page_number = struct.unpack(">I", frame_header[0:4])[0]
            db_size_after = struct.unpack(">I", frame_header[4:8])[0]

            wal_info["frames"].append({
                "frame_number": frame_num,
                "page_number": page_number,
                "db_size_pages": db_size_after,
                "offset": frame_offset
            })
            frame_offset += 24 + page_size
            frame_num += 1

    return wal_info

方法 3：页面内未分配空间

活跃 B 树页面内已删除的单元在单元指针数组和单元内容区域之间的未分配区域留有数据。

def analyze_unallocated_space(db_path: str, page_number: int) -> dict:
    """分析特定 B 树页面内的未分配空间。"""
    with open(db_path, "rb") as f:
        header = f.read(100)
        page_size = struct.unpack(">H", header[16:18])[0]
        if page_size == 1:
            page_size = 65536

        offset = (page_number - 1) * page_size
        f.seek(offset)
        page_data = f.read(page_size)

        # 解析页面头部（根据类型为 8 或 12 字节）
        page_type = page_data[0]
        first_freeblock = struct.unpack(">H", page_data[1:3])[0]
        cell_count = struct.unpack(">H", page_data[3:5])[0]
        cell_content_offset = struct.unpack(">H", page_data[5:7])[0]
        if cell_content_offset == 0:
            cell_content_offset = 65536

        header_size = 12 if page_type in (0x02, 0x05) else 8
        cell_pointer_end = header_size + cell_count * 2

        unallocated_start = cell_pointer_end
        unallocated_end = cell_content_offset
        unallocated_size = unallocated_end - unallocated_start

        return {
            "page_number": page_number,
            "page_type": hex(page_type),
            "cell_count": cell_count,
            "unallocated_start": unallocated_start,
            "unallocated_end": unallocated_end,
            "unallocated_size": unallocated_size,
            "unallocated_data": page_data[unallocated_start:unallocated_end].hex()
        }

常见取证数据库

时间戳解码

from datetime import datetime, timedelta

def decode_chrome_timestamp(chrome_ts: int) -> datetime:
    """将 Chrome/WebKit 时间戳转换为 datetime（自 1601-01-01 的微秒数）。"""
    epoch_delta = 11644473600
    return datetime.utcfromtimestamp((chrome_ts / 1000000) - epoch_delta)

def decode_unix_timestamp(unix_ts: int) -> datetime:
    """将 Unix 时间戳转换为 datetime。"""
    return datetime.utcfromtimestamp(unix_ts)

def decode_mac_absolute_time(mac_ts: float) -> datetime:
    """将 Mac 绝对时间（自 2001-01-01 的秒数）转换为 datetime。"""
    mac_epoch = datetime(2001, 1, 1)
    return mac_epoch + timedelta(seconds=mac_ts)

def decode_mozilla_timestamp(moz_ts: int) -> datetime:
    """将 Mozilla PRTime（自 Unix 纪元的微秒数）转换为 datetime。"""
    return datetime.utcfromtimestamp(moz_ts / 1000000)

参考资料

• SQLite 文件格式：https://www.sqlite.org/fileformat2.html
• Belkasoft SQLite 分析：https://belkasoft.com/sqlite-analysis
• Spyder Forensics SQLite 培训：https://www.spyderforensics.com/sqlite-forensic-fundamentals-2025/
• 受损 SQLite 数据库的取证分析：https://www.forensicfocus.com/articles/forensic-analysis-of-damaged-sqlite-databases/