🐛 Fix Douyin TikTok API

This commit is contained in:
Evil0ctal 2024-03-25 15:11:18 -07:00
parent ac6c4fad5f
commit 1db94fc8ad
9 changed files with 239 additions and 194 deletions

View File

@ -30,7 +30,7 @@ cd Douyin_TikTok_Download_API/ || exit
pip install -r requirements.txt pip install -r requirements.txt
echo 'Please edit config.ini, all input must be numbers!' echo 'Please edit config.yml, all input must be numbers!'
python3 config.py python3 config.py

View File

@ -1,107 +0,0 @@
# -*- encoding: utf-8 -*-
# @Author: https://github.com/Evil0ctal/
# @Time: 2021/11/06
# @Update: 2022/11/09
# @Function:
# 项目的配置文件/Config file of the project
[Scraper] # scraper.py
# 是否使用代理(如果部署在IP受限国家需要开启默认为False关闭请自行收集代理下面代理仅作为示例不保证可用性)
# Whether to use proxy (if deployed in a country with IP restrictions, it needs to be turned on by default, False is closed. Please collect proxies yourself. The following proxies are only for reference and do not guarantee availability)
Proxy_switch = False
# 是否根据不同协议(http/https)使用不同代理设置为True时修改Http_proxy/Https_proxy这两个变量的值
# Whether to use different proxies for different protocols (http/https). When set to True, modify the values of the two variables Http_proxy/Https_proxy
Use_different_protocols = False
# http/https协议都使用以下代理(Use_different_protocols为False时生效)
# Both http/https protocols use the following proxy (effective when Use_different_protocols is False)
All = 45.167.124.5:9992
# http协议使用以下代理(Use_different_protocols为True时生效)
# The http protocol uses the following proxy (effective when Use_different_protocols is True)
Http_proxy = http://45.167.124.5:9992
# https协议使用以下代理(Use_different_protocols为True时生效)
# The https protocol uses the following proxy (effective when Use_different_protocols is True)
Https_proxy = https://45.167.124.5:9992
# 抖音cookies配置项
# odin_tt=xxx;sessionid_ss=xxx;ttwid=xxx;passport_csrf_token=xxx;msToken=xxx;
DouYinCookies =
[Web_API] # web_api.py
# API链接 如http://127.0.0.1:2333 或 http://api.douyin.wtf (末尾不要留斜杠)
# API link, such as: http://127.0.0.1:2333 or http://api.douyin.wtf (no slash at the end)
Domain = http://api.douyin.wtf
# 限制API的请求次数/Limited API requests
Rate_Limit = 10/minute
# API默认运行端口/Default port of API
Port = 8000
# 默认下载目录/Default download directory
Download_Path = ./download
# 是否开启下载[tag = Download]功能(默认开启,关闭后无法下载)/Whether to enable the download [tag = Download] function (default open, closed after download)
Download_Switch = True
# 是否自动清理下载目录/Whether to automatically clean up the download directory
Download_Path_Clean_Switch = True
# 下载文件夹自动删除时间(单位:秒)/Download folder automatic deletion time (unit: seconds)
Download_Path_Clean_Timer = 3600
# 默认下载文件名前缀/Default download file name prefix
File_Name_Prefix = api.douyin.wtf_
# 是否记录API调用日志/Whether to record API call logs
Allow_Logs = True
# 快捷指令版本/Shortcut version
iOS_Shortcut_Version = 6.0
# 快捷指令Link(Chinese_Language)
iOS_Shortcut_Link = https://www.icloud.com/shortcuts/4465d514869e4ca585074d40328f3e0e
# Shortcut Link(English_Language)
iOS_Shortcut_Link_EN = https://www.icloud.com/shortcuts/58e3a2cbac784a6782f1031c6b1dd9f8
# 快捷指令更新时间/Shortcut update time
iOS_Shortcut_Update_Time = 2022/11/06
# 快捷指令更新记录/Shortcut update log
iOS_Shortcut_Update_Note = 重新适配https://api.douyin.wtf(API-V1 3.0.0版本)
# iOS shortcut update note
iOS_Shortcut_Update_Note_EN = Re-adapt https://api.douyin.wtf (API-V1 3.0.0 version)
[Web_APP] # web_app.py
# 网页默认运行端口/Web default running port
Port = 80
# PyWebIO是否使用CDN来获取前端的静态资源(防止CDN被墙导致无法正常显示)
# Whether PyWebIO uses CDN to obtain static resources of the front end (to prevent CDN from being blocked and displayed normally)
PyWebIO_CDN = True
# 最大接受提交URL的数量/Maximum number of URLs accepted for submission
Max_Take_URLs = 200
# 是否记录错误日志/Whether to record error logs
Allow_Logs = True
# 网页标题
Web_Title = TikTok/抖音无水印在线解析下载
# Web Title English
Web_Title_English = Douyin/TikTok online parsing and download without watermark
# 网页描述
Web_Description = 在线批量解析TikTok/抖音视频和图片,支持无水印下载,官方数据接口,稳定,开源,免费,无广告。
# Web Description English
Web_Description_English = Online batch parsing of TikTok/Douyin videos and pictures, support for no watermark download, official data interface, stable, open source, free, no ads.
# 网页关键词/Keywords of the web page
Keywords = 抖音,tiktok,水印,无水印,no-watermark,抖音去水印,tiktok no watermark,在线,online,api,快捷指令,shortcut,下载,解析,parsing,tiktok api,抖音api,抖音去水印在线,tiktok去水印在线,downloader,下载器,free api,免费api

View File

@ -1,46 +1,56 @@
import configparser import yaml
config = configparser.ConfigParser() config_path = 'config.yml'
config_path = 'config.ini'
config.read(config_path, encoding='utf-8') with open(config_path, 'r', encoding='utf-8') as file:
config = yaml.safe_load(file)
def api_config(): def api_config():
api_default_port = config.get('Web_API', 'Port') api_default_port = config['Web_API']['Port']
api_new_port = input(f'Default API port: {api_default_port}\nIf you want use different port input new API port here: ') api_new_port = input(
f'Default API port: {api_default_port}\nIf you want use different port input new API port here: ')
if api_new_port.isdigit(): if api_new_port.isdigit():
if int(api_new_port) == int(api_default_port): if int(api_new_port) == int(api_default_port):
print(f'Use default port for web_app.py: {api_default_port}') print(f'Use default port for web_app.py: {api_default_port}')
else: else:
print(f'Use new port for web_api.py: {api_new_port}') print(f'Use new port for web_api.py: {api_new_port}')
config.set('Web_API', 'Port', api_new_port) config['Web_API']['Port'] = int(api_new_port)
config.write(open(config_path, "w", encoding="utf-8")) with open(config_path, "w", encoding="utf-8") as file:
yaml.dump(config, file, allow_unicode=True)
else: else:
print(f'Use default port for web_app.py: {api_default_port}') print(f'Use default port for web_app.py: {api_default_port}')
req_limit = config.get('Web_API', 'Rate_Limit') req_limit = config['Web_API']['Rate_Limit']
new_req_limit = input(f'Default API rate limit: {req_limit}\nIf you want use different rate limit input new rate limit here: ') new_req_limit = input(
f'Default API rate limit: {req_limit}\nIf you want use different rate limit input new rate limit here: ')
if new_req_limit.isdigit(): if new_req_limit.isdigit():
if int(new_req_limit) == int(req_limit.split('/')[0]): if int(new_req_limit) == int(req_limit.split('/')[0]):
print(f'Use default rate limit for web_api.py : {req_limit}') print(f'Use default rate limit for web_api.py : {req_limit}')
else: else:
print(f'Use new rate limit: {new_req_limit}/minute') print(f'Use new rate limit: {new_req_limit}/minute')
config.set('Web_API', 'Rate_Limit', f'{new_req_limit}/minute') config['Web_API']['Rate_Limit'] = f'{new_req_limit}/minute'
config.write(open(config_path, "w", encoding="utf-8")) with open(config_path, "w", encoding="utf-8") as file:
yaml.dump(config, file, allow_unicode=True)
else: else:
print(f'Use default rate limit for web_api.py: {req_limit}') print(f'Use default rate limit for web_api.py: {req_limit}')
def app_config(): def app_config():
app_default_port = config.get('Web_APP', 'Port') app_default_port = config['Web_APP']['Port']
app_new_port = input(f'Default App port: {app_default_port}\nIf you want use different port input new App port here: ') app_new_port = input(
f'Default App port: {app_default_port}\nIf you want use different port input new App port here: ')
if app_new_port.isdigit(): if app_new_port.isdigit():
if int(app_new_port) == int(app_default_port): if int(app_new_port) == int(app_default_port):
print(f'Use default port for web_app.py: {app_default_port}') print(f'Use default port for web_app.py: {app_default_port}')
else: else:
print(f'Use new port: {app_new_port}') print(f'Use new port: {app_new_port}')
config.set('Web_APP', 'Port', app_new_port) config['Web_APP']['Port'] = int(app_new_port)
config.write(open(config_path, "w", encoding="utf-8")) with open(config_path, "w", encoding="utf-8") as file:
yaml.dump(config, file, allow_unicode=True)
else: else:
print(f'Use default port for web_app.py : {app_default_port}') print(f'Use default port for web_app.py : {app_default_port}')
@ -48,4 +58,3 @@ def app_config():
if __name__ == '__main__': if __name__ == '__main__':
api_config() api_config()
app_config() app_config()

109
config.yml Normal file
View File

@ -0,0 +1,109 @@
# -*- encoding: utf-8 -*-
# @Author: https://github.com/Evil0ctal/
# @Time: 2021/11/06
# @Update: 2024/03/25
# @Function:
# 项目的配置文件/Config file of the project
# 去看看我们的另外一个项目吧一个YAML文件的多态键值路径映射解析器https://github.com/PKVPM/PKVPM
# Check out our other project, a polymorphic key-value path mapping parser for YAML files:
Scraper: # scraper.py
# 是否使用代理(如果部署在IP受限国家需要开启默认为False关闭请自行收集代理下面代理仅作为示例不保证可用性)
# Whether to use proxy (if deployed in a country with IP restrictions, it needs to be turned on by default, False is closed. Please collect proxies yourself. The following proxies are only for reference and do not guarantee availability)
Proxy_switch: false
# 是否根据不同协议(http/https)使用不同代理设置为True时修改Http_proxy/Https_proxy这两个变量的值
# Whether to use different proxies for different protocols (http/https). When set to True, modify the values of the two variables Http_proxy/Https_proxy
Use_different_protocols: false
# http/https协议都使用以下代理(Use_different_protocols为False时生效)
# Both http/https protocols use the following proxy (effective when Use_different_protocols is False)
All: "45.167.124.5:9992"
# http协议使用以下代理(Use_different_protocols为True时生效)
# The http protocol uses the following proxy (effective when Use_different_protocols is True)
Http_proxy: "http://45.167.124.5:9992"
# https协议使用以下代理(Use_different_protocols为True时生效)
# The https protocol uses the following proxy (effective when Use_different_protocols is True)
Https_proxy: "https://45.167.124.5:9992"
# 抖音cookies配置项
# odin_tt=xxx;sessionid_ss=xxx;ttwid=xxx;passport_csrf_token=xxx;msToken=xxx;
DouYinCookies: __ac_nonce=06601efc9000687edabfb; __ac_signature=_02B4Z6wo00f01DY5d.gAAIDCmbcjj5Gs2Wg2CXNAAGuWde; ttwid=1%7CE0Fz_BrMgjzSm3__CbFk_z_YxJTZvuoIynWz56Jr2gw%7C1711402953%7C0bae07e4ed08cc7062e5025b43028917c0f101ce950429d713bdfc98ce8900e4; douyin.com; device_web_cpu_core=16; device_web_memory_size=-1; architecture=amd64; IsDouyinActive=true; home_can_add_dy_2_desktop=%220%22; dy_swidth=1344; dy_sheight=756; stream_recommend_feed_params=%22%7B%5C%22cookie_enabled%5C%22%3Atrue%2C%5C%22screen_width%5C%22%3A1344%2C%5C%22screen_height%5C%22%3A756%2C%5C%22browser_online%5C%22%3Atrue%2C%5C%22cpu_core_num%5C%22%3A16%2C%5C%22device_memory%5C%22%3A0%2C%5C%22downlink%5C%22%3A%5C%22%5C%22%2C%5C%22effective_type%5C%22%3A%5C%22%5C%22%2C%5C%22round_trip_time%5C%22%3A0%7D%22; strategyABtestKey=%221711402955.353%22; volume_info=%7B%22isUserMute%22%3Afalse%2C%22isMute%22%3Atrue%2C%22volume%22%3A0.5%7D; stream_player_status_params=%22%7B%5C%22is_auto_play%5C%22%3A0%2C%5C%22is_full_screen%5C%22%3A0%2C%5C%22is_full_webscreen%5C%22%3A0%2C%5C%22is_mute%5C%22%3A1%2C%5C%22is_speed%5C%22%3A1%2C%5C%22is_visible%5C%22%3A1%7D%22; passport_csrf_token=6cbad4aeddb5063d2da49dba0f0001a4; passport_csrf_token_default=6cbad4aeddb5063d2da49dba0f0001a4; msToken=Vnmw2WIIMakoPHjKeN_pdZQUaL3Pqe2Bkc5voIdZJlfpQQTmmYIi2Oy8V8VhGn9VoYyx9G2EoNLUubHK_OSaTL3-W4LTM7DTTwkNhZVAMJ7BVBWW85jPHqXCAjFn; FORCE_LOGIN=%7B%22videoConsumedRemainSeconds%22%3A180%7D; odin_tt=fff2328d744fdd887dfe8236d1343072c7d667d877a05e9fbf0c4dea2cf6cd0fb24cc994eb844d91502053a9fb48b5cf1f37be4285cfeab319cac618493b1cc78a21c68b7e2b6af04f08d1f3417b5617; csrf_session_id=120d8aacffb06addd01cb40859003c8e; bd_ticket_guard_client_data=eyJiZC10aWNrZXQtZ3VhcmQtdmVyc2lvbiI6MiwiYmQtdGlja2V0LWd1YXJkLWl0ZXJhdGlvbi12ZXJzaW9uIjoxLCJiZC10aWNrZXQtZ3VhcmQtcmVlLXB1YmxpYy1rZXkiOiJCUE8vYUdEdlNsRE1ZYTBpRXVrQTk0aVppQ2t0Y2NwcWs3NGh2aitjN2NFZ1I5alZTQXdRTFNvL2tza3U3R1JJMUtLc0xJakROam91WDBZcm9XdytVTDQ9IiwiYmQtdGlja2V0LWd1YXJkLXdlYi12ZXJzaW9uIjoxfQ%3D%3D; bd_ticket_guard_client_web_domain=2; msToken=O6EKBamnejH7dsEfHq4JRyU3rYJv__HW7Bz7OPeOD-AjZMtNe31tPGkhM0Ez06aM_J0uy0OjAGvflkpOukOAYUerarzl5OSuwKFddmm6JL40dUcahW_TBmSgNOOJ
Web_API: # web_api.py
# API链接 如http://127.0.0.1:2333 或 http://api.douyin.wtf (末尾不要留斜杠)
# API link, such as: http://127.0.0.1:2333 or http://api.douyin.wtf (no slash at the end)
Domain: "http://api.douyin.wtf"
# 限制API的请求次数/Limited API requests
Rate_Limit: "10/minute"
# API默认运行端口/Default port of API
Port: 8000
# 默认下载目录/Default download directory
Download_Path: "./download"
# 是否开启下载[tag = Download]功能(默认开启,关闭后无法下载)/Whether to enable the download [tag = Download] function (default open, closed after download)
Download_Switch: true
# 是否自动清理下载目录/Whether to automatically clean up the download directory
Download_Path_Clean_Switch: true
# 下载文件夹自动删除时间(单位:秒)/Download folder automatic deletion time (unit: seconds)
Download_Path_Clean_Timer: 3600
# 默认下载文件名前缀/Default download file name prefix
File_Name_Prefix: "api.douyin.wtf_"
# 是否记录API调用日志/Whether to record API call logs
Allow_Logs: true
# 快捷指令版本/Shortcut version
iOS_Shortcut_Version: "6.0"
# 快捷指令Link(Chinese_Language)
iOS_Shortcut_Link: "https://www.icloud.com/shortcuts/4465d514869e4ca585074d40328f3e0e"
# Shortcut Link(English_Language)
iOS_Shortcut_Link_EN: "https://www.icloud.com/shortcuts/58e3a2cbac784a6782f1031c6b1dd9f8"
# 快捷指令更新时间/Shortcut update time
iOS_Shortcut_Update_Time: "2022/11/06"
# 快捷指令更新记录/Shortcut update log
iOS_Shortcut_Update_Note: "重新适配https://api.douyin.wtf(API-V1 3.0.0版本)"
# iOS shortcut update note
iOS_Shortcut_Update_Note_EN: "Re-adapt https://api.douyin.wtf (API-V1 3.0.0 version)"
Web_APP: # web_app.py
# 网页默认运行端口/Web default running port
Port: 80
# PyWebIO是否使用CDN来获取前端的静态资源(防止CDN被墙导致无法正常显示)
# Whether PyWebIO uses CDN to obtain static resources of the front end (to prevent CDN from being blocked and displayed normally)
PyWebIO_CDN: true
# 最大接受提交URL的数量/Maximum number of URLs accepted for submission
Max_Take_URLs: 200
# 是否记录错误日志/Whether to record error logs
Allow_Logs: true
# 网页标题
Web_Title: "TikTok/抖音无水印在线解析下载"
# Web Title English
Web_Title_English: "Douyin/TikTok online parsing and download without watermark"
# 网页描述
Web_Description: "在线批量解析TikTok/抖音视频和图片,支持无水印下载,官方数据接口,稳定,开源,免费,无广告。"
# Web Description English
Web_Description_English: "Online batch parsing of TikTok/Douyin videos and pictures, support for no watermark download, official data interface, stable, open source, free, no ads."
# 网页关键词/Keywords of the web page
Keywords: "抖音,tiktok,水印,无水印,no-watermark,抖音去水印,tiktok no watermark,在线,online,api,快捷指令,shortcut,下载,解析,parsing,tiktok api,抖音api,抖音去水印在线,tiktok去水印在线,downloader,下载器,free api,免费api"

View File

@ -9,7 +9,7 @@ services:
container_name: douyin_tiktok_download_api container_name: douyin_tiktok_download_api
restart: always restart: always
volumes: volumes:
- ./config.ini:/app/config.ini - ./config.yml:/app/config.yml
environment: environment:
TZ: Asia/Shanghai TZ: Asia/Shanghai
deploy: deploy:

View File

@ -1,4 +1,4 @@
aiohttp==3.8.4 aiohttp~=3.8.4
aiosignal==1.3.1 aiosignal==1.3.1
anyio==3.6.2 anyio==3.6.2
async-timeout==4.0.2 async-timeout==4.0.2
@ -8,24 +8,24 @@ charset-normalizer==3.0.1
click==8.1.3 click==8.1.3
colorama==0.4.6 colorama==0.4.6
Deprecated==1.2.13 Deprecated==1.2.13
fastapi==0.92.0 fastapi~=0.92.0
frozenlist==1.3.3 frozenlist==1.3.3
h11==0.14.0 h11==0.14.0
idna==3.4 idna==3.4
limits==2.8.0 limits==2.8.0
multidict==6.0.4 multidict==6.0.4
orjson==3.8.6 orjson==3.9.15
packaging==22.0 packaging==22.0
pydantic==1.10.5 pydantic~=1.10.12
PyExecJS==1.5.1 PyExecJS==1.5.1
pywebio==1.7.1 pywebio==1.7.1
six==1.16.0 six==1.16.0
slowapi==0.1.7 slowapi==0.1.7
sniffio==1.3.0 sniffio==1.3.0
starlette==0.25.0 starlette~=0.25.0
tenacity==8.2.1 tenacity==8.2.1
tornado==6.2 tornado==6.3.3
typing_extensions==4.5.0 typing_extensions==4.8.0
ua-parser==0.16.1 ua-parser==0.16.1
user-agents==2.2.0 user-agents==2.2.0
uvicorn==0.20.0 uvicorn==0.20.0
@ -33,3 +33,4 @@ wrapt==1.15.0
yarl==1.8.2 yarl==1.8.2
httpx~=0.25.0 httpx~=0.25.0
requests~=2.28.2 requests~=2.28.2
PyYAML~=6.0.1

View File

@ -2,7 +2,7 @@
# -*- encoding: utf-8 -*- # -*- encoding: utf-8 -*-
# @Author: https://github.com/Evil0ctal/ # @Author: https://github.com/Evil0ctal/
# @Time: 2021/11/06 # @Time: 2021/11/06
# @Update: 2024/03/14 # @Update: 2024/03/25
# @Version: 3.1.8 # @Version: 3.1.8
# @Note: # @Note:
# Core code, valued at 1 bucks (๑•̀ㅂ•́)و✧ # Core code, valued at 1 bucks (๑•̀ㅂ•́)و✧
@ -12,7 +12,6 @@
# 核心代码估值1块(๑•̀ㅂ•́)و✧ # 核心代码估值1块(๑•̀ㅂ•́)و✧
# 用于爬取Douyin/TikTok/Bilibili/xigua的数据并以字典形式返回。 # 用于爬取Douyin/TikTok/Bilibili/xigua的数据并以字典形式返回。
# 如果本项目对您有帮助请给我一个star谢谢 # 如果本项目对您有帮助请给我一个star谢谢
import random
import re import re
import os import os
import time import time
@ -22,15 +21,18 @@ import httpx
import platform import platform
import asyncio import asyncio
import traceback import traceback
import configparser import yaml
import urllib.parse import urllib.parse
import random import random
import json
from zlib import crc32 from zlib import crc32
from typing import Union from typing import Union
from tenacity import * from tenacity import *
# 读取配置文件
with open('config.yml', 'r', encoding='utf-8') as yaml_file:
config = yaml.safe_load(yaml_file)
class Scraper: class Scraper:
"""__________________________________________⬇initialization(初始化)⬇______________________________________""" """__________________________________________⬇initialization(初始化)⬇______________________________________"""
@ -44,10 +46,11 @@ class Scraper:
'accept-encoding': 'gzip, deflate, br', 'accept-encoding': 'gzip, deflate, br',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36',
'Referer': 'https://www.douyin.com/', 'Referer': 'https://www.douyin.com/',
'cookie': '' # 如果抖音接口不返回数据可能是因为cookie过期需要更新cookie/If the Douyin interface does not return data, it may be because the cookie has expired and needs to be updated
'cookie': config['Scraper']['DouYinCookies']
} }
self.tiktok_api_headers = { self.tiktok_api_headers = {
'User-Agent': 'com.ss.android.ugc.trill/494+Mozilla/5.0+(Linux;+Android+12;+2112123G+Build/SKQ1.211006.001;+wv)+AppleWebKit/537.36+(KHTML,+like+Gecko)+Version/4.0+Chrome/107.0.5304.105+Mobile+Safari/537.36' 'User-Agent': "Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Mobile Safari/537.36"
} }
self.bilibili_api_headers = { self.bilibili_api_headers = {
'User-Agent': 'com.ss.android.ugc.trill/494+Mozilla/5.0+(Linux;+Android+12;+2112123G+Build/SKQ1.211006.001;+wv)+AppleWebKit/537.36+(KHTML,+like+Gecko)+Version/4.0+Chrome/107.0.5304.105+Mobile+Safari/537.36' 'User-Agent': 'com.ss.android.ugc.trill/494+Mozilla/5.0+(Linux;+Android+12;+2112123G+Build/SKQ1.211006.001;+wv)+AppleWebKit/537.36+(KHTML,+like+Gecko)+Version/4.0+Chrome/107.0.5304.105+Mobile+Safari/537.36'
@ -86,9 +89,8 @@ class Scraper:
'sec-ch-ua-platform': '"macOS"', 'sec-ch-ua-platform': '"macOS"',
} }
# 判断配置文件是否存在/Check if the configuration file exists # 判断配置文件是否存在/Check if the configuration file exists
if os.path.exists('config.ini'): if os.path.exists('config.yml'):
self.config = configparser.RawConfigParser() self.config = config
self.config.read('config.ini', encoding='utf-8')
if not self.config['Scraper']['DouYinCookies'] is None: if not self.config['Scraper']['DouYinCookies'] is None:
self.douyin_api_headers['Cookie'] = str(self.config['Scraper']['DouYinCookies']) self.douyin_api_headers['Cookie'] = str(self.config['Scraper']['DouYinCookies'])
# 判断是否使用代理 # 判断是否使用代理
@ -319,22 +321,6 @@ class Scraper:
"""__________________________________________⬇Douyin methods(抖音方法)⬇______________________________________""" """__________________________________________⬇Douyin methods(抖音方法)⬇______________________________________"""
# 生成抖音X-Bogus签名/Generate Douyin X-Bogus signature
# 下面的代码不能保证稳定性,随时可能失效/ The code below cannot guarantee stability and may fail at any time
def generate_x_bogus_url(self, url: str) -> str:
"""
生成抖音X-Bogus签名
:param url: 视频链接
:return: 包含X-Bogus签名的URL
"""
# 调用JavaScript函数
query = urllib.parse.urlparse(url).query
xbogus = execjs.compile(open(self.relpath('./X-Bogus.js')).read()).call('sign', query,
self.headers['User-Agent'])
# print('生成的X-Bogus签名为: {}'.format(xbogus))
new_url = url + "&X-Bogus=" + xbogus
return new_url
# 获取抖音视频ID/Get Douyin video ID # 获取抖音视频ID/Get Douyin video ID
async def get_douyin_video_id(self, original_url: str) -> Union[str, None]: async def get_douyin_video_id(self, original_url: str) -> Union[str, None]:
""" """
@ -382,19 +368,50 @@ class Scraper:
""" """
try: try:
# 构造访问链接/Construct the access link # 构造访问链接/Construct the access link
api_url = f"https://www.douyin.com/aweme/v1/web/aweme/detail/?device_platform=webapp&aid=6383&channel=channel_pc_web&aweme_id={video_id}&pc_client_type=1&version_code=190500&version_name=19.5.0&cookie_enabled=true&screen_width=1344&screen_height=756&browser_language=zh-CN&browser_platform=Win32&browser_name=Firefox&browser_version=118.0&browser_online=true&engine_name=Gecko&engine_version=109.0&os_name=Windows&os_version=10&cpu_core_num=16&device_memory=&platform=PC&webid=7284189800734082615&msToken=B1N9FM825TkvFbayDsDvZxM8r5suLrsfQbC93TciS0O9Iii8iJpAPd__FM2rpLUJi5xtMencSXLeNn8xmOS9q7bP0CUsrt9oVTL08YXLPRzZm0dHKLc9PGRlyEk=" # parameters provided by https://github.com/Johnserf-Seed
api_url = self.generate_x_bogus_url(api_url) domain = "https://www.douyin.com"
endpoint = "/aweme/v1/web/aweme/detail/"
query_body = {
"aweme_id": video_id,
"device_platform": "webapp",
"aid": "6383",
"channel": "channel_pc_web",
"pc_client_type": 1,
"version_code": "170400",
"version_name": "17.4.0",
"cookie_enabled": "true",
"screen_width": 1920,
"screen_height": 1080,
"browser_language": "zh-CN",
"browser_platform": "Win32",
"browser_name": "Edge",
"browser_version": "117.0.2045.47",
"browser_online": "true",
"engine_name": "Blink",
"engine_version": "117.0.0.0",
"os_name": "Windows",
"os_version": "10",
"cpu_core_num": 12,
"device_memory": 8,
"platform": "PC",
"downlink": 10,
"effective_type": "4g",
"round_trip_time": 100,
"msToken": "Hello From Evil0ctal!"
}
# 将参数编码为 URL 查询字符串
query_string = urllib.parse.urlencode(query_body, quote_via=urllib.parse.quote)
api_url = urllib.parse.urljoin(domain, endpoint) + "?" + query_string
api_url = self.generate_x_bogus_url(api_url, self.douyin_api_headers)
# 访问API/Access API # 访问API/Access API
print("正在请求抖音视频API: {}".format(api_url)) print("正在请求抖音视频API: {}".format(api_url))
async with aiohttp.ClientSession() as session: # 使用httpx请求
self.douyin_api_headers['Referer'] = f'https://www.douyin.com/video/{video_id}' async with httpx.AsyncClient() as client:
async with session.get(api_url, headers=self.douyin_api_headers, proxy=self.proxies, response = await client.get(api_url, headers=self.douyin_api_headers, timeout=10)
timeout=10) as response: response = response.json()
response = await response.json() print(response)
# 获取视频数据/Get video data # 获取视频数据/Get video data
video_data = response['aweme_detail'] video_data = response["aweme_detail"]
# print('获取视频数据成功!')
print("抖音API返回数据: {}".format(video_data))
return video_data return video_data
except Exception as e: except Exception as e:
raise ValueError(f"获取抖音视频数据出错了: {e}") raise ValueError(f"获取抖音视频数据出错了: {e}")
@ -456,19 +473,28 @@ class Scraper:
# print('正在获取TikTok视频数据...') # print('正在获取TikTok视频数据...')
try: try:
# 构造访问链接/Construct the access link # 构造访问链接/Construct the access link
api_url = f'https://api22-normal-c-useast2a.tiktokv.com/aweme/v1/feed/?aweme_id={video_id}' # params provided by https://github.com/sheldygg
print("正在获取视频数据API: {}".format(api_url)) params = {
async with aiohttp.ClientSession() as session: "iid": "7318518857994389254",
async with session.get(api_url, headers=self.tiktok_api_headers, proxy=self.proxies, "device_id": "7318517321748022790",
timeout=10) as response: "channel": "googleplay",
response = await response.json() "app_name": "musical_ly",
video_data = response['aweme_list'][0] "version_code": "300904",
# print('获取视频信息成功!') "device_platform": "android",
"device_type": "ASUS_Z01QD",
"os_version": "9",
"aweme_id": video_id
}
api_url = f"https://api22-normal-c-alisg.tiktokv.com/aweme/v1/feed/"
# 使用httpx请求
async with httpx.AsyncClient() as client:
response = await client.get(api_url, params=params, headers=self.tiktok_api_headers, timeout=10)
response = response.json()
# 获取视频数据/Get video data
video_data = response["aweme_list"][0]
return video_data return video_data
except Exception as e: except Exception as e:
print('获取视频信息失败!原因:{}'.format(e)) raise ValueError(f"获取TikTok视频数据出错了: {e}")
# return None
raise e
"""__________________________________________⬇bilibili methods(Bilibili方法)⬇______________________________________""" """__________________________________________⬇bilibili methods(Bilibili方法)⬇______________________________________"""
@ -978,8 +1004,14 @@ if __name__ == '__main__':
# async_test(_douyin_url=douyin_url, _tiktok_url=tiktok_url, _bilibili_url=bilibili_url, _ixigua_url=ixigua_url, # async_test(_douyin_url=douyin_url, _tiktok_url=tiktok_url, _bilibili_url=bilibili_url, _ixigua_url=ixigua_url,
# _kuaishou_url=kuaishou_url)) # _kuaishou_url=kuaishou_url))
tiktok_id = asyncio.run(api.get_tiktok_video_id(tiktok_url)) # tiktok_id = asyncio.run(api.get_tiktok_video_id(tiktok_url))
#
# tiktok_data = asyncio.run(api.get_tiktok_video_data(tiktok_id))
#
# print(tiktok_data)
tiktok_data = asyncio.run(api.get_tiktok_video_data(tiktok_id)) douyin_id = asyncio.run(api.get_douyin_video_id(douyin_url))
print(tiktok_data) douyin_data = asyncio.run(api.get_douyin_video_data(douyin_id))
print(douyin_data)

View File

@ -2,7 +2,7 @@
# -*- encoding: utf-8 -*- # -*- encoding: utf-8 -*-
# @Author: https://github.com/Evil0ctal/ # @Author: https://github.com/Evil0ctal/
# @Time: 2021/11/06 # @Time: 2021/11/06
# @Update: 2023/09/25 # @Update: 2024/03/25
# @Version: 3.1.8 # @Version: 3.1.8
# @Function: # @Function:
# 创建一个接受提交参数的FastAPi应用程序。 # 创建一个接受提交参数的FastAPi应用程序。
@ -16,7 +16,7 @@ import aiohttp
import uvicorn import uvicorn
import zipfile import zipfile
import threading import threading
import configparser import yaml
from fastapi import FastAPI, Request from fastapi import FastAPI, Request
from fastapi.responses import ORJSONResponse, FileResponse from fastapi.responses import ORJSONResponse, FileResponse
@ -29,8 +29,8 @@ from starlette.responses import RedirectResponse
from scraper import Scraper from scraper import Scraper
# 读取配置文件 # 读取配置文件
config = configparser.ConfigParser() with open('config.yml', 'r', encoding='utf-8') as yaml_file:
config.read('config.ini', encoding='utf-8') config = yaml.safe_load(yaml_file)
# 运行端口 # 运行端口
port = int(config["Web_API"]["Port"]) port = int(config["Web_API"]["Port"])
# 域名 # 域名

View File

@ -2,13 +2,13 @@
# -*- encoding: utf-8 -*- # -*- encoding: utf-8 -*-
# @Author: https://github.com/Evil0ctal/ # @Author: https://github.com/Evil0ctal/
# @Time: 2021/11/06 # @Time: 2021/11/06
# @Update: 2023/09/25 # @Update: 2024/03/25
# @Version: 3.1.8 # @Version: 3.1.8
# @Function: # @Function:
# 用于在线批量解析Douyin/TikTok的无水印视频/图集。 # 用于在线批量解析Douyin/TikTok的无水印视频/图集。
# 基于 PyWebIO将scraper.py返回的内容显示在网页上。 # 基于 PyWebIO将scraper.py返回的内容显示在网页上。
import configparser import yaml
import os import os
import re import re
import time import time
@ -20,8 +20,9 @@ from pywebio.input import *
from pywebio.output import * from pywebio.output import *
from pywebio.session import info as session_info, run_asyncio_coroutine from pywebio.session import info as session_info, run_asyncio_coroutine
config = configparser.ConfigParser() # 读取配置文件
config.read('config.ini', encoding='utf-8') with open('config.yml', 'r', encoding='utf-8') as yaml_file:
config = yaml.safe_load(yaml_file)
# 创建一个Scraper类的实例/Create an instance of the Scraper class # 创建一个Scraper类的实例/Create an instance of the Scraper class
api = Scraper() api = Scraper()