Yyds dry goods inventory hand-in-hand teach you the development of Tiktok series video batch Downloader

Application demonstration

Hello everyone , I'm Xiaoming . Here we have developed a Tiktok Video Downloader , The opening effect is as follows ：

If the local Google viewer has never visited the Tiktok homepage before , Click the start download button and the following output will appear ：

At this point, we just need to click Visit Tiktok Homepage , The program will use the local Google viewer to access the Tiktok homepage . Click the download button again ：

You can see that this video is a collection video ：

Then the program only needs to check the first option to download the whole collection ：

In this way, the whole collection can be downloaded at one time ：

Development process

First of all, according to the previous article ： Extract Google viewer Cookie Five realms of

Read the location of Google Explorer installation and local Tiktok related cookie：

Log in and copy

      
      

       
       """
       
       
 Xiao Ming's code 
       
       
CSDN Home page ：https://blog.csdn.net/as604049322
       
       
"""
       
       
__author__ = ' Xiaoming '
       
       
__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):
       
       
    " Read chrome Save in json In the document key Proceed again base64 Decoding and DPAPI Decrypt to get the real 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 Decrypt "
       
       
    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):
       
       
    " Get all under the specified domain name cookie"
       
       
    userDataDir = os.environ['LOCALAPPDATA'] + r'\Google\Chrome\User Data'
       
       
    localStateFilePath = userDataDir + r'\Local State'
       
       
    cookiepath = userDataDir + r'\Default\Cookies'
       
       
    # 97 The version has already Cookies Move to Network Under the table of contents 
       
       
    if not os.path.exists(cookiepath) or os.stat(cookiepath).st_size == 0:
       
       
        cookiepath = userDataDir + r'\Default\Network\Cookies'
       
       
    # print(cookiepath)
       
       
    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())
      
      
      
      

       
       
1.
       
       
2.
       
       
3.
       
       
4.
       
       
5.
       
       
6.
       
       
7.
       
       
8.
       
       
9.
       
       
10.
       
       
11.
       
       
12.
       
       
13.
       
       
14.
       
       
15.
       
       
16.
       
       
17.
       
       
18.
       
       
19.
       
       
20.
       
       
21.
       
       
22.
       
       
23.
       
       
24.
       
       
25.
       
       
26.
       
       
27.
       
       
28.
       
       
29.
       
       
30.
       
       
31.
       
       
32.
       
       
33.
       
       
34.
       
       
35.
       
       
36.
       
       
37.
       
       
38.
       
       
39.
       
       
40.
       
       
41.
       
       
42.
       
       
43.
       
       
44.
       
       
45.
       
       
46.
       
       
47.
       
       
48.
       
       
49.
       
       
50.
       
       
51.
       
       
52.
       
       
53.
       
       
54.
       
       
55.
       
       
56.
       
       
57.
       
       
58.
       
       
59.
       
       
60.
       
       
61.
       
       
62.
       
       
63.
       
       
64.
       
       
65.
       
       
66.
       
       
67.
      
      

With this tool class , We no longer need to use selenium.

Then the core code of video parsing is as follows ：

Log in and copy

      
      

       
       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} Invalid , Wrong report key:", e)
       
       
            return
       
       
        if not title:
       
       
            title, = re.findall("<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("<h2 [^>]+>([^<>]+)</h2>", res.text)[0]
       
       
        return video_url, title, collection_urls, collection_title
       
       
    else:
       
       
        print(' Video link request failed ！！！')
      
      
      
      

       
       
1.
       
       
2.
       
       
3.
       
       
4.
       
       
5.
       
       
6.
       
       
7.
       
       
8.
       
       
9.
       
       
10.
       
       
11.
       
       
12.
       
       
13.
       
       
14.
       
       
15.
       
       
16.
       
       
17.
       
       
18.
       
       
19.
       
       
20.
       
       
21.
       
       
22.
       
       
23.
       
       
24.
       
       
25.
       
       
26.
       
       
27.
       
       
28.
      
      

The core code of video download ：

Log in and copy

      
      

       
       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, " Already exists , skip ...")
       
       
        return
       
       
    print("-----------------------------------")
       
       
    print(f' Start downloading files ：{basename}\n Current file size ：{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
       
       
            # print(f" speed of progress ：{done_size / total:.2%},{done_size / cost_time / 1024 / 1024:.2f}MB/s")
       
       
    cost_time = time.time() - start_time
       
       
    print(f' file ：{basename}  Download complete ！\n Time consuming ：{cost_time:0.2f}  second ')
      
      
      
      

       
       
1.
       
       
2.
       
       
3.
       
       
4.
       
       
5.
       
       
6.
       
       
7.
       
       
8.
       
       
9.
       
       
10.
       
       
11.
       
       
12.
       
       
13.
       
       
14.
       
       
15.
       
       
16.
       
       
17.
       
       
18.
       
       
19.
       
       
20.
       
       
21.
       
       
22.
       
       
23.
      
      

Analysis of video links , You can refer to brother Cai's article ：

《​ ​ use Python Shake it X No watermark short video download ​​》

link ：https://mp.weixin.qq.com/s/NNVT6IH6dpT0rTeu1-oD6w

UI The core code of interface design is as follows ：

Log in and copy

      
      

       
       layout = [
       
       
    [sg.Text(' Tiktok video address ：', font=(" Regular script ", 12)),
       
       
     sg.In(key='url', size=(70, 1), text_color="#bb8b59",
       
       
           default_text="https://www.douyin.com/video/6803929443069988103")],
       
       
    [sg.Checkbox(' If it is a collection, download the whole collection ', key="download_collection", default=False),
       
       
     sg.Button(' Start the download '),
       
       
     sg.Button(' Clear output '),
       
       
     sg.Button(' Visit Tiktok Homepage '),
       
       
     sg.Button(' Visit the current address '),
       
       
     ],
       
       
    [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\n00:00<00:00', key="message_video"),
       
       
        sg.ProgressBar(1000, size=(20, 20), key='progressbar', bar_color=("#15d36a", "#295273")),
       
       
        sg.Text('00.00MB/00.00MB\n00.00MB/s', key="message")
       
       
    ],
       
       
    [sg.Text(' The output directory ：', font=(" Regular script ", 12)),
       
       
     sg.In(size=(35, 1), key="save_dir"),
       
       
     sg.FolderBrowse('...', target='save_dir', initial_folder="."),
       
       
     sg.Checkbox('  After downloading  \n Open the directory ', key="open_folder", default=True),
       
       
     sg.Button(' Open the output directory '),
       
       
     ],
       
       
    [sg.Text("@ Xiaoming ：https://blog.csdn.net/as604049322"), ],
       
       
]
      
      
      
      

       
       
1.
       
       
2.
       
       
3.
       
       
4.
       
       
5.
       
       
6.
       
       
7.
       
       
8.
       
       
9.
       
       
10.
       
       
11.
       
       
12.
       
       
13.
       
       
14.
       
       
15.
       
       
16.
       
       
17.
       
       
18.
       
       
19.
       
       
20.
       
       
21.
       
       
22.
       
       
23.
       
       
24.
       
       
25.
      
      

Program download

The complete code of the tool and the download address of the packaged tool ：

Log in and copy

      
      

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

       
       
1.
      
      

friends , Practice it quickly ！ If in the process of learning , Any problems encountered , Welcome to add my friend , I'll pull you in Python The learning exchange group discusses learning together .