How to Build a Python Douyin Video Downloader Without Selenium

Program Demonstration

Hello, I am XiaoXiaoMing. I developed a Douyin video downloader; the interface looks like this:

If the local Chrome browser has never visited Douyin, clicking the start download button shows the following output:

Click "Visit Douyin homepage" to let the program open Douyin in Chrome, then click download again:

The video is a collection video:

Select the first option to download the entire collection:

The whole collection is downloaded at once:

Development Process

First, based on the previous article "Five Levels of Extracting Chrome Cookies", we read Chrome's installation path and local Douyin cookies:

"""
小小明的代码
CSDN主页：https://blog.csdn.net/as604049322
"""
__author__ = '小小明'
__time__ = '2022/1/23'

import base64
import json
import os
import sqlite3
import winreg

import win32crypt
from cryptography.hazmat.primitives.ciphers.aead import AESGCM

def load_local_key(localStateFilePath):
    "读取chrome保存在json文件中的key再进行base64解码和DPAPI解密得到真实的AESGCM key"
    with open(localStateFilePath, encoding='u8') as f:
        encrypted_key = json.load(f)['os_crypt']['encrypted_key']
    encrypted_key_with_header = base64.b64decode(encrypted_key)
    encrypted_key = encrypted_key_with_header[5:]
    key = win32crypt.CryptUnprotectData(encrypted_key, None, None, None, 0)[1]
    return key

def decrypt_value(key, data):
    "AESGCM解密"
    nonce, cipherbytes = data[3:15], data[15:]
    aesgcm = AESGCM(key)
    plaintext = aesgcm.decrypt(nonce, cipherbytes, None).decode('u8')
    return plaintext

def fetch_host_cookie(host):
    "获取指定域名下的所有cookie"
    userDataDir = os.environ['LOCALAPPDATA'] + r'\Google\Chrome\User Data'
    localStateFilePath = userDataDir + r'\Local State'
    cookiepath = userDataDir + r'\Default\Cookies'
    # 97版本已经将Cookies移动到Network目录下
    if not os.path.exists(cookiepath) or os.stat(cookiepath).st_size == 0:
        cookiepath = userDataDir + r'\Default\Network\Cookies'
    sql = f"select name,encrypted_value from cookies where host_key like '%.{host}'"
    cookies = {}
    key = load_local_key(localStateFilePath)
    with sqlite3.connect(cookiepath) as conn:
        cu = conn.cursor()
        for name, encrypted_value in cu.execute(sql).fetchall():
            cookies[name] = decrypt_value(key, encrypted_value)
    return cookies

def get_chrome_path():
    try:
        key = winreg.OpenKey(winreg.HKEY_CLASSES_ROOT, r"ChromeHTML\Application")
        path = winreg.QueryValueEx(key, "ApplicationIcon")[0]
        chrome_path = path[:path.rfind(",")]
        return chrome_path
    except FileNotFoundError as e:
        return

if __name__ == '__main__':
    print(fetch_host_cookie("douyin.com"))
    print(get_chrome_path())

With this utility class we no longer need Selenium.

The core video parsing code is:

def get_video_url(url, cookies):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36",
        "referer": "https://www.douyin.com"
    }
    res = requests.get(url, headers=headers, cookies=cookies)
    if res.status_code == 200:
        RENDER_DATA, = re.findall(r'<script id="RENDER_DATA" type="application/json">([^<>]+)</script>', res.text)
        data = json.loads(unquote(RENDER_DATA))
        key = '8' if url.find("collection") != -1 else '34'
        try:
            detail = data[key]['aweme']['detail']
            title = detail['desc']
        except Exception as e:
            print(f"{url}无效，报错的key:", e)
            return
        if not title:
            title, = re.findall(r"<title[^>]+>\s*([^>]+)\s*</title>", res.text)
        video_url = urljoin(url, detail['video']['playApi'])
        collection_urls = set(re.findall("//www.douyin.com/collection/\d+/\d+", res.text))
        collection_urls = [urljoin("https://www.douyin.com", url) for url in collection_urls]
        collection_urls.sort(key=lambda s: int(s[s.rfind('/') + 1:]))
        collection_title = re.findall(r"<h2 [^>]+>([^<>]+)</h2>", res.text)[0]
        return video_url, title, collection_urls, collection_title
    else:
        print('视频链接请求失败！！！')

The core video download code is:

def download_video(video_url, title, folder):
    start_time = time.time()
    res = requests.get(url=video_url, stream=True)
    done_size, total = 0, int(res.headers['content-length'])
    chunk_size = 1024 * 1024
    title = format_filename(title)
    file_size = round(int(res.headers['content-length']) / 1024 / 1024, 2)
    basename = f"{title}.mp4"
    filename = f"{folder}/{title}.mp4"
    if os.path.exists(filename):
        print(basename, "已存在，跳过...")
        return
    print("-----------------------------------")
    print(f'开始下载文件：{basename}
当前文件大小：{file_size}MB')
    with open(filename, 'wb') as f:
        for chunk in res.iter_content(chunk_size):
            f.write(chunk)
            done_size += len(chunk)
            cost_time = time.time() - start_time
            yield done_size, cost_time, total
    cost_time = time.time() - start_time
    print(f'文件：{basename} 下载完成！
耗时：{cost_time:.2f} 秒')

For analysis of video links, see the article "Using Python to Download Douyin Short Videos Without Watermark" at https://mp.weixin.qq.com/s?__biz=MzUzODA5MjM5NQ==&mid=2247497183&idx=1&sn=e68fb38785bf3f16070519f5679f3ebc&scene=21#wechat_redirect

UI Design Core Code

layout = [
    [sg.Text('抖音视频地址：', font=("楷体", 12)), sg.In(key='url', size=(70, 1), text_color="#bb8b59", default_text="https://www.douyin.com/video/6803929443069988103")],
    [sg.Checkbox('如果是一个合集则下载整个合集', key="download_collection", default=False),
     sg.Button('开始下载'),
     sg.Button('清空输出'),
     sg.Button('访问抖音主页'),
     sg.Button('访问当前地址')],
    [sg.Output(size=(85, 10), key="out", text_color="#15d36a")],
    [sg.ProgressBar(1000, size=(20, 20), key='video_bar', bar_color=("#bb8b59", "#295273")),
     sg.Text('000.0MB,00/00
00:00<00:00', key="message_video"),
     sg.ProgressBar(1000, size=(20, 20), key='progressbar', bar_color=("#15d36a", "#295273")),
     sg.Text('00.00MB/00.00MB
00.00MB/s', key="message")],
    [sg.Text('输出目录：', font=("楷体", 12)), sg.In(size=(35, 1), key="save_dir"), sg.FolderBrowse('...', target='save_dir', initial_folder="."), sg.Checkbox(' 下载完毕后 
打开所在目录', key="open_folder", default=True), sg.Button('打开输出目录')],
    [sg.Text("@小小明：https://blog.csdn.net/as604049322")]
]

Program Download

The complete code and packaged tool can be downloaded from:

https://gitcode.net/as604049322/python_gui/-/tree/master/douyin