QQ空间说说和日志批量导出工具 v3
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
QQ空间说说和日志批量导出工具 v3
================================
功能：导出QQ空间的「说说」和「日志」，保存为txt文本，包含日期信息
依赖：仅Python标准库，无需pip install任何东西
使用方法：
1. 浏览器登录QQ空间
2. F12 → Network → 复制完整Cookie字符串
3. 运行本脚本，粘贴Cookie
获取完整Cookie步骤：
① 浏览器打开 https://user.qzone.qq.com/你的QQ号 并登录
② 按 F12 打开开发者工具
③ 切换到 Network(网络) 标签页
④ 刷新页面(F5)
⑤ 在请求列表中找到任意一个发往 qzone.qq.com 的请求，点击它
⑥ 在右侧 Headers(标头) 中找到 Request Headers 下的 Cookie
⑦ 右键复制完整的 Cookie 值（一整行很长的字符串）
⑧ 粘贴到脚本中运行
或者用 Application 标签页：
① F12 → Application(应用) → Cookies → https://user.qzone.qq.com
② 把所有Cookie拼成 "key1=value1; key2=value2; ..." 格式
③ 至少要包含 p_skey 和 uin
"""
import json
import os
import re
import sys
import time
import urllib.request
import urllib.parse
import urllib.error
from datetime import datetime
# ============================================================
# 配置区
# ============================================================
QQ_NUMBER = "100984450"
COOKIE = "" # 粘贴完整Cookie字符串，留空则运行时提示输入
OUTPUT_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), "qqzone_export")
# 请求间隔（秒）
REQUEST_DELAY = 1.0
# ============================================================
# Cookie 处理
# ============================================================
def extract_cookie_value(cookie_str, key):
"""从完整Cookie字符串中提取指定key的值"""
# 匹配 key=value 的模式
m = re.search(r'(?:^|;\s*)' + re.escape(key) + r'=([^;]+)', cookie_str)
if m:
return m.group(1).strip()
return ""
def get_g_tk(p_skey):
"""根据 p_skey 计算 g_tk 签名"""
h = 5381
for ch in p_skey:
h += (h << 5) + ord(ch)
return h & 0x7FFFFFFF
def build_headers(qq_number, cookie_str):
"""构建请求头，使用完整Cookie"""
return {
"User-Agent": (
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/125.0.0.0 Safari/537.36"
),
"Referer": f"https://user.qzone.qq.com/{qq_number}",
"Cookie": cookie_str,
"Accept": "*/*",
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
"Accept-Encoding": "identity", # 不压缩，避免解压问题
"Connection": "keep-alive",
}
# ============================================================
# HTTP 请求
# ============================================================
def http_get(url, headers, timeout=20):
"""用标准库发GET请求"""
req = urllib.request.Request(url, headers=headers)
try:
with urllib.request.urlopen(req, timeout=timeout) as resp:
return resp.read().decode("utf-8", errors="replace")
except urllib.error.HTTPError as e:
print(f" [HTTP {e.code}] {e.reason}")
try:
body = e.read().decode("utf-8", errors="replace")
# WAF拦截会返回HTML页面
if "waf.tencent.com" in body:
print(f" [WAF拦截] 腾讯WAF拒绝了请求，请检查Cookie是否完整且未过期")
else:
print(f" 响应内容: {body[:300]}")
except Exception:
pass
return None
except Exception as e:
print(f" [请求异常] {e}")
return None
def parse_jsonp(text):
"""从JSONP响应中提取JSON数据"""
if not text:
return None
text = text.strip()
# 尝试匹配 _preloadCallback({...}) 等格式
m = re.search(r'_\w+Callback\((.*)\)\s*;?\s*$', text, re.DOTALL)
if m:
try:
return json.loads(m.group(1))
except json.JSONDecodeError:
pass
# 去掉末尾分号
text = text.rstrip(";").strip()
if text.startswith("(") and text.endswith(")"):
text = text[1:-1]
try:
return json.loads(text)
except json.JSONDecodeError:
pass
# 提取第一个 { 到最后一个 }
first = text.find("{")
last = text.rfind("}")
if first != -1 and last != -1 and last > first:
try:
return json.loads(text[first:last + 1])
except json.JSONDecodeError:
pass
return None
# ============================================================
# 文本处理
# ============================================================
def clean_html(text):
"""清理HTML标签和实体"""
if not text:
return ""
text = re.sub(r'<br\s*/?>', '\n', text, flags=re.IGNORECASE)
text = re.sub(r'<p[^>]*>', '\n', text, flags=re.IGNORECASE)
text = re.sub(r'</p>', '\n', text, flags=re.IGNORECASE)
text = re.sub(r'<div[^>]*>', '\n', text, flags=re.IGNORECASE)
text = re.sub(r'</div>', '\n', text, flags=re.IGNORECASE)
text = re.sub(r'<[^>]+>', '', text)
entities = {
' ': ' ', '<': '<', '>': '>',
'&': '&', '"': '"', ''': "'",
'“': '"', '”': '"',
'…': '...', '—': '—',
}
for entity, char in entities.items():
text = text.replace(entity, char)
text = re.sub(r'&#(\d+);', lambda m: chr(int(m.group(1))), text)
text = re.sub(r'\n{3,}', '\n\n', text)
return text.strip()
def save_file(filepath, content):
"""保存文本到文件"""
d = os.path.dirname(filepath)
if d:
os.makedirs(d, exist_ok=True)
with open(filepath, "w", encoding="utf-8") as f:
f.write(content)
def safe_filename(name, max_len=60):
"""生成安全的文件名"""
name = re.sub(r'[<>:"/\\|?*\n\r\t]', '_', name)
name = name.strip().strip('.')
if len(name) > max_len:
name = name[:max_len]
return name if name else "untitled"
# ============================================================
# 说说导出
# ============================================================
# 说说API多前缀，h5优先（user.qzone被WAF拦501）
SHUOSHUO_API_PREFIXES = [
"https://h5.qzone.qq.com/proxy/domain/taotao.qq.com",
"https://user.qzone.qq.com/proxy/domain/taotao.qq.com",
]
def fetch_shuoshuo_page(qq_number, cookie_str, g_tk, pos, num=20):
"""获取一页说说数据，依次尝试多个API前缀"""
params = {
"uin": qq_number,
"ftype": "0",
"sort": "0",
"pos": str(pos),
"num": str(num),
"replynum": "100",
"g_tk": str(g_tk),
"callback": "_preloadCallback",
"code_version": "1",
"format": "jsonp",
"need_private_comment": "1",
}
headers = build_headers(qq_number, cookie_str)
for prefix in SHUOSHUO_API_PREFIXES:
url = prefix + "/cgi-bin/emotion_cgi_msglist_v6?" + urllib.parse.urlencode(params)
text = http_get(url, headers)
if not text:
continue
if "waf.tencent.com" in text:
print(f" [WAF拦截] {prefix}，尝试下一个...")
continue
data = parse_jsonp(text)
if data is not None:
return data
return None
def export_shuoshuo(qq_number, cookie_str, g_tk, output_dir):
"""导出全部说说"""
all_items = []
pos = 0
num = 20
print()
print("=" * 60)
print(" 开始导出说说")
print("=" * 60)
while True:
print(f" 获取第 {pos + 1} ~ {pos + num} 条...")
data = fetch_shuoshuo_page(qq_number, cookie_str, g_tk, pos, num)
if not data:
print(" 返回数据为空，停止")
break
code = data.get("code", -1)
if code != 0:
msg = data.get("message") or data.get("msg") or ""
print(f" 接口返回 code={code}, message={msg}")
print(f" 完整返回(前300字): {str(data)[:300]}")
if code in [-3000, -3001, -4001]:
print(" [提示] 登录态可能已失效，请重新获取Cookie！")
break
msglist = data.get("msglist") or []
if not msglist:
print(" 没有更多说说了")
break
for item in msglist:
content = clean_html(item.get("content", ""))
ts = item.get("created_time", 0)
if ts:
date_str = datetime.fromtimestamp(ts).strftime("%Y-%m-%d %H:%M:%S")
else:
date_str = "未知日期"
pic_urls = []
for pic in (item.get("pic") or []):
u = pic.get("url1") or pic.get("url") or pic.get("url2") or pic.get("url3") or ""
if u:
pic_urls.append(u)
all_items.append({
"date": date_str,
"content": content,
"pics": pic_urls,
"forward_from": item.get("rtname", ""),
})
preview = content[:40].replace("\n", " ") if content else "(空)"
print(f" [{date_str}] {preview}...")
pos += num
total = data.get("total", 0)
if total and pos >= total:
print(f" 已获取全部 {total} 条说说")
break
if len(msglist) < num:
print(" 已获取全部说说")
break
time.sleep(REQUEST_DELAY)
# ---- 写文件 ----
txt_path = os.path.join(output_dir, "说说.txt")
lines = []
lines.append("QQ空间说说导出")
lines.append(f"QQ号: {qq_number}")
lines.append(f"导出时间: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
lines.append(f"共计 {len(all_items)} 条说说")
lines.append("=" * 60)
lines.append("")
for i, item in enumerate(all_items, 1):
lines.append(f"【第{i}条】")
lines.append(f"日期: {item['date']}")
lines.append(f"内容: {item['content']}")
if item["pics"]:
lines.append("图片:")
for j, url in enumerate(item["pics"], 1):
lines.append(f" 图{j}: {url}")
if item["forward_from"]:
lines.append(f"转发自: {item['forward_from']}")
lines.append("-" * 60)
lines.append("")
save_file(txt_path, "\n".join(lines))
print(f"\n 说说已保存: {txt_path}")
print(f" 共计 {len(all_items)} 条")
return len(all_items)
# ============================================================
# 日志导出
# ============================================================
# 日志API域名: b.qzone.qq.com
# 列表接口: /cgi-bin/blognew/get_abs
# 详情接口: /cgi-bin/blognew/blog_output_data
# 代理前缀: user.qzone.qq.com/proxy/domain/b.qzone.qq.com
# 多个可能的代理前缀，依次尝试
BLOG_API_PREFIXES = [
"https://user.qzone.qq.com/proxy/domain/b.qzone.qq.com",
"https://h5.qzone.qq.com/proxy/domain/b.qzone.qq.com",
]
def try_api_endpoints(path, params, qq_number, cookie_str):
"""依次尝试多个API前缀，返回第一个成功的响应"""
headers = build_headers(qq_number, cookie_str)
for prefix in BLOG_API_PREFIXES:
url = prefix + path + "?" + urllib.parse.urlencode(params)
text = http_get(url, headers)
if not text:
continue
# 检查是否是WAF页面或错误页面
if "waf.tencent.com" in text:
print(f" [WAF拦截] {prefix}")
continue
data = parse_jsonp(text)
if data is not None:
return data
# 如果JSONP解析失败但文本不为空，也返回文本（可能是纯HTML）
if len(text) > 100:
return text
return None
def fetch_blog_count(qq_number, cookie_str, g_tk):
"""获取日志总数和分类信息"""
params = {
"inCharset": "utf-8",
"outCharset": "utf-8",
"format": "jsonp",
"hostUin": qq_number,
"uin": qq_number,
"g_tk": str(g_tk),
"blogType": "0",
"reqInfo": "2",
}
result = try_api_endpoints("/cgi-bin/blognew/get_abs", params, qq_number, cookie_str)
if not result or not isinstance(result, dict):
print(f" [调试] 获取日志分类失败")
return 0, []
if result.get("code") != 0:
print(f" [调试] 日志分类接口 code={result.get('code')}, msg={result.get('message', '')}")
return 0, []
d = result.get("data") or {}
cate_info = d.get("cateInfo") or {}
cate_list = cate_info.get("categoryList") or []
total = sum(c.get("num", 0) for c in cate_list)
if not total:
total = d.get("total", 0)
return total, cate_list
def fetch_blog_list_page(qq_number, cookie_str, g_tk, pos, num=100):
"""获取一页日志列表"""
params = {
"inCharset": "utf-8",
"outCharset": "utf-8",
"format": "jsonp",
"hostUin": qq_number,
"uin": qq_number,
"g_tk": str(g_tk),
"blogType": "0",
"reqInfo": "1",
"pos": str(pos),
"num": str(num),
}
return try_api_endpoints("/cgi-bin/blognew/get_abs", params, qq_number, cookie_str)
def fetch_blog_detail(qq_number, cookie_str, g_tk, blog_id):
"""获取单篇日志详情"""
params = {
"inCharset": "utf-8",
"outCharset": "utf-8",
"format": "jsonp",
"uin": qq_number,
"blogid": str(blog_id),
"numperpage": "15",
"ref": "qzone",
"g_tk": str(g_tk),
}
result = try_api_endpoints("/cgi-bin/blognew/blog_output_data", params, qq_number, cookie_str)
if not result:
return ""
# 如果是dict（JSONP解析成功）
if isinstance(result, dict):
d = result.get("data") or result
if isinstance(d, dict):
content = d.get("content") or d.get("html") or d.get("blogContent") or ""
if content:
return content
elif isinstance(d, str):
return d
# 可能整个JSON里没有直接的content字段，尝试其他方式
return str(result)
# 如果是字符串（纯HTML响应）
return result
def extract_blog_content(raw_text):
"""从HTML或JSONP响应中提取日志正文"""
if not raw_text:
return ""
# 如果是dict
if isinstance(raw_text, dict):
d = raw_text.get("data") or raw_text
if isinstance(d, dict):
content = d.get("content") or d.get("html") or d.get("blogContent") or ""
if content:
return clean_html(content)
elif isinstance(d, str):
return clean_html(d)
return ""
# 字符串处理
text = raw_text
# 尝试提取 blogDetailDiv
m = re.search(r'id=["\']blogDetailDiv["\'][^>]*>(.*?)</div>', text, re.DOTALL | re.IGNORECASE)
if m:
return clean_html(m.group(1))
# 尝试提取 blogContainerDiv
m = re.search(r'id=["\']blogContainerDiv["\'][^>]*>(.*?)</div>', text, re.DOTALL | re.IGNORECASE)
if m:
return clean_html(m.group(1))
# 尝试提取 contentDiv
m = re.search(r'class=["\']blog_detail["\'][^>]*>(.*?)</div>', text, re.DOTALL | re.IGNORECASE)
if m:
return clean_html(m.group(1))
# 如果是完整HTML页面
if "<html" in text.lower() or "<body" in text.lower():
text = re.sub(r'<script[^>]*>.*?</script>', '', text, flags=re.DOTALL | re.IGNORECASE)
text = re.sub(r'<style[^>]*>.*?</style>', '', text, flags=re.DOTALL | re.IGNORECASE)
text = re.sub(r'<head[^>]*>.*?</head>', '', text, flags=re.DOTALL | re.IGNORECASE)
return clean_html(text)
# 直接清理
return clean_html(text)
def blog_id_to_date(blog_id):
"""blogId 本质是Unix时间戳，转换为日期字符串"""
try:
ts = int(float(blog_id))
if ts > 1000000000:
return datetime.fromtimestamp(ts).strftime("%Y-%m-%d %H:%M:%S")
except (ValueError, TypeError, OSError):
pass
return ""
def export_blogs(qq_number, cookie_str, g_tk, output_dir):
"""导出全部日志"""
all_blogs = []
pos = 0
num = 100
print()
print("=" * 60)
print(" 开始导出日志")
print("=" * 60)
# 获取日志总数
total, cate_list = fetch_blog_count(qq_number, cookie_str, g_tk)
if cate_list:
print(f" 日志分类:")
for c in cate_list:
print(f" - {c.get('category', '未知')}: {c.get('num', 0)} 篇")
print(f" 日志总数: {total} 篇")
if total == 0:
print(" [提示] 未获取到日志总数，尝试直接拉取...")
while True:
print(f" 获取日志列表 pos={pos} num={num} ...")
data = fetch_blog_list_page(qq_number, cookie_str, g_tk, pos, num)
if not data:
print(" 返回数据为空，停止")
break
if not isinstance(data, dict):
print(f" [错误] 返回的不是JSON，前200字符: {str(data)[:200]}")
break
code = data.get("code", -1)
if code != 0:
msg = data.get("message") or data.get("msg") or ""
print(f" 接口返回 code={code}, message={msg}")
print(f" 完整返回(前500字): {str(data)[:500]}")
if code in [-3000, -3001, -4001]:
print(" [提示] 登录态可能已失效，请重新获取Cookie！")
break
d = data.get("data") or {}
blog_list = d.get("list") or d.get("blogList") or []
if not blog_list:
print(" 没有更多日志了")
break
print(f" 本次获取到 {len(blog_list)} 篇日志")
for blog in blog_list:
blog_id = blog.get("blogId") or blog.get("blogid") or ""
title = clean_html(blog.get("title", "无标题"))
category = blog.get("cate") or blog.get("category") or "未分类"
pub_time = blog.get("pubTime") or blog.get("pubtime") or ""
if not pub_time and blog_id:
pub_time = blog_id_to_date(blog_id)
if not pub_time:
pub_time = "未知日期"
print(f" 获取详情: 《{title}》 ({pub_time})")
content = ""
if blog_id:
raw = fetch_blog_detail(qq_number, cookie_str, g_tk, blog_id)
if raw:
content = extract_blog_content(raw)
else:
print(f" [警告] 日志详情返回为空")
time.sleep(0.5)
all_blogs.append({
"title": title,
"date": pub_time,
"category": category,
"content": content,
"blog_id": str(blog_id),
})
pos += num
if total and pos >= total:
print(f" 已获取全部 {total} 篇日志")
break
if len(blog_list) < num:
print(" 已获取全部日志")
break
time.sleep(REQUEST_DELAY)
# ---- 写文件 ----
blog_dir = os.path.join(output_dir, "日志")
os.makedirs(blog_dir, exist_ok=True)
for i, blog in enumerate(all_blogs, 1):
safe_title = safe_filename(blog["title"])
safe_date = blog["date"].replace(":", "-").replace(" ", "_") if blog["date"] else "未知日期"
fname = f"{i:03d}_{safe_date}_{safe_title}.txt"
fpath = os.path.join(blog_dir, fname)
body = f"标题: {blog['title']}\n"
body += f"日期: {blog['date']}\n"
body += f"分类: {blog['category']}\n"
body += f"日志ID: {blog.get('blog_id', '')}\n"
body += "=" * 60 + "\n\n"
body += blog["content"]
save_file(fpath, body)
summary_path = os.path.join(output_dir, "日志汇总.txt")
lines = []
lines.append("QQ空间日志导出")
lines.append(f"QQ号: {qq_number}")
lines.append(f"导出时间: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
lines.append(f"共计 {len(all_blogs)} 篇日志")
lines.append("=" * 60)
lines.append("")
for blog in all_blogs:
lines.append(f"标题: {blog['title']}")
lines.append(f"日期: {blog['date']}")
lines.append(f"分类: {blog['category']}")
lines.append("-" * 60)
lines.append(blog["content"])
lines.append("=" * 60)
lines.append("")
save_file(summary_path, "\n".join(lines))
print(f"\n 日志已保存:")
print(f" 汇总文件: {summary_path}")
print(f" 单篇目录: {blog_dir}")
print(f" 共计 {len(all_blogs)} 篇")
return len(all_blogs)
# ============================================================
# 主程序
# ============================================================
def main():
print()
print("=" * 60)
print(" QQ空间 说说 + 日志 批量导出工具 v3")
print(" 仅使用Python标准库，无需安装任何依赖")
print("=" * 60)
print()
qq_number = QQ_NUMBER.strip()
cookie_str = COOKIE.strip()
if not qq_number:
qq_number = input("请输入你的QQ号: ").strip()
else:
print(f"QQ号: {qq_number}")
if not cookie_str:
print()
print("需要完整Cookie才能访问QQ空间数据。")
print()
print("获取完整Cookie的方法（推荐用Network标签页）：")
print(" 1. 浏览器打开 https://user.qzone.qq.com/%s 并登录" % qq_number)
print(" 2. 按 F12 打开开发者工具")
print(" 3. 切换到 Network(网络) 标签页")
print(" 4. 刷新页面(F5)")
print(" 5. 在请求列表中点击任意一个发往 qzone.qq.com 的请求")
print(" 6. 右侧 Headers(标头) → Request Headers → 找到 Cookie")
print(" 7. 复制完整的Cookie值（一整行很长的字符串）")
print()
print(" 或者用Application标签页：")
print(" F12 → Application → Cookies → 把所有项拼成 key=value; key=value 格式")
print(" 至少要包含 p_skey 和 uin 两个Cookie")
print()
cookie_str = input("请粘贴完整Cookie: ").strip()
if not cookie_str:
print("[错误] Cookie不能为空！")
sys.exit(1)
# 从Cookie中提取 p_skey
p_skey = extract_cookie_value(cookie_str, "p_skey")
if not p_skey:
print("[错误] Cookie中未找到 p_skey，请确保复制了完整的Cookie！")
sys.exit(1)
g_tk = get_g_tk(p_skey)
output_dir = OUTPUT_DIR
os.makedirs(output_dir, exist_ok=True)
print()
print(f"QQ号: {qq_number}")
print(f"p_skey: {p_skey[:10]}...{p_skey[-5:]}")
print(f"g_tk: {g_tk}")
print(f"Cookie长度: {len(cookie_str)} 字符")
print(f"输出目录: {output_dir}")
print()
# 导出说说
ss_count = export_shuoshuo(qq_number, cookie_str, g_tk, output_dir)
# 导出日志
blog_count = export_blogs(qq_number, cookie_str, g_tk, output_dir)
# 总结
print()
print("=" * 60)
print(" 全部导出完成！")
print(f" 说说: {ss_count} 条")
print(f" 日志: {blog_count} 篇")
print(f" 输出目录: {output_dir}")
print("=" * 60)
print()
print("文件结构:")
print(f" {output_dir}/")
print(f" ├── 说说.txt (全部说说汇总)")
print(f" ├── 日志汇总.txt (全部日志汇总)")
print(f" └── 日志/ (每篇日志单独文件)")
print(f" ├── 001_日期_标题.txt")
print(f" ├── 002_日期_标题.txt")
print(f" └── ...")
if __name__ == "__main__":
main()
