diff --git a/config.ini b/config.ini new file mode 100644 index 0000000..6eca94f --- /dev/null +++ b/config.ini @@ -0,0 +1,33 @@ +[Web_API] +# API默认运行端口 +Port = 2333 +# 是否启用API的/video功能 +Video_Download = True +# 是否启用API的/music功能 +Music_Download = True +# 是否记录API调用日志 +Allow_Logs = True +# 快捷指令版本 +iOS_Shortcut_Version = 3.0 +# 快捷指令Link +iOS_Shortcut_Link = https://www.icloud.com/shortcuts/126820d2783748d1bdec95a223a02639 +# 快捷指令更新时间 +iOS_Shortcut_Update_Time = 2022/04/15 +# 快捷指令更新记录 +iOS_Shortcut_Update_Note = 为快捷指令增加了自动检查更新功能 + +[Web_ZH] +# 网页默认运行端口 +Port = 5000 +# 是否启用解析结果页面视频批量下载功能 +Allow_Batch_Download = True +# 最大接受提交URL的数量 +Max_Take_URLs = 50 +# 是否记录错误日志 +Allow_Logs = True +# 网页标题 +Web_Title = 抖音/TikTok无水印在线解析 +# 网页描述 +Web_Description = 支持在线批量解析下载无水印抖音/TikTok的无水印视频/图集。支持API调用，开源，免费，无广告。 + + diff --git a/scraper.py b/scraper.py new file mode 100644 index 0000000..58d3157 --- /dev/null +++ b/scraper.py @@ -0,0 +1,406 @@ +#!/usr/bin/env python +# -*- encoding: utf-8 -*- +# @Author: https://github.com/Evil0ctal/ +# @Time: 2021/11/06 +# @Update: 2022/04/21 +# @Function: +# 核心代码，估值1块(๑•̀ㅂ•́)و✧ +# 用于爬取Douyin/TikTok数据并以字典形式返回。 + + +import re +import json +import time +import requests +from retrying import retry + + +class Scraper: + """ + Scraper.douyin():抖音视频/图集解析，返回字典。 + Scraper.tiktok():TikTok视频解析，返回字典。 + """ + + def __init__(self): + self.headers = { + 'user-agent': 'Mozilla/5.0 (Linux; Android 8.0; Pixel 2 Build/OPD3.170816.012) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Mobile Safari/537.36 Edg/87.0.664.66' + } + self.tiktok_headers = { + "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9", + "authority": "www.tiktok.com", + "Accept-Encoding": "gzip, deflate", + "Connection": "keep-alive", + "Host": "www.tiktok.com", + "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) coc_coc_browser/86.0.170 Chrome/80.0.3987.170 Safari/537.36", + } + + @retry(stop_max_attempt_number=6) + def douyin(self, original_url): + """ + 利用官方接口解析抖音链接信息 + :param original_url: 抖音/TikTok链接(支持长/短链接) + :return:包含信息的字典 + """ + headers = self.headers + try: + # 开始时间 + start = time.time() + # 原视频链接 + r = requests.get(url=original_url, headers=headers, allow_redirects=False) + try: + # 2021/12/11 发现抖音做了限制，会自动重定向网址，但是可以从回执头中获取 + long_url = r.headers['Location'] + except: + # 报错后判断为长链接，直接截取视频id + long_url = original_url + # 正则匹配出视频ID + key = re.findall('video/(\d+)?', long_url)[0] + # 构造抖音API链接 + api_url = f'https://www.iesdouyin.com/web/api/v2/aweme/iteminfo/?item_ids={key}' + print("正在请求抖音API链接: " + '\n' + api_url) + # 将回执以JSON格式处理 + js = json.loads(requests.get(url=api_url, headers=headers).text) + # 判断是否为图集 + if js['item_list'][0]['images'] is not None: + print("类型 = 图集") + # 类型为图集 + url_type = 'album' + # 图集标题 + album_title = str(js['item_list'][0]['desc']) + # 图集作者昵称 + album_author = str(js['item_list'][0]['author']['nickname']) + # 图集作者签名 + album_author_signature = str(js['item_list'][0]['author']['signature']) + # 图集作者UID + album_author_uid = str(js['item_list'][0]['author']['uid']) + # 图集作者抖音号 + album_author_id = str(js['item_list'][0]['author']['unique_id']) + if album_author_id == "": + # 如果作者未修改过抖音号，应使用此值以避免无法获取其抖音ID + album_author_id = str(js['item_list'][0]['author']['short_id']) + # 尝试获取图集BGM信息 + try: + # 图集BGM链接 + album_music = str(js['item_list'][0]['music']['play_url']['url_list'][0]) + # 图集BGM标题 + album_music_title = str(js['item_list'][0]['music']['title']) + # 图集BGM作者 + album_music_author = str(js['item_list'][0]['music']['author']) + # 图集BGM ID + album_music_id = str(js['item_list'][0]['music']['id']) + # 图集BGM MID + album_music_mid = str(js['item_list'][0]['music']['mid']) + except: + # 报错后代表无背景音乐 + # 图集BGM链接 + album_music = 'No BGM found' + # 图集BGM标题 + album_music_title = 'No BGM found' + # 图集BGM作者 + album_music_author = 'No BGM found' + # 图集BGM ID + album_music_id = 'No BGM found' + # 图集BGM MID + album_music_mid = 'No BGM found' + # 图集ID + album_aweme_id = str(js['item_list'][0]['statistics']['aweme_id']) + # 评论数量 + album_comment_count = str(js['item_list'][0]['statistics']['comment_count']) + # 获赞数量 + album_digg_count = str(js['item_list'][0]['statistics']['digg_count']) + # 播放次数 + album_play_count = str(js['item_list'][0]['statistics']['play_count']) + # 分享次数 + album_share_count = str(js['item_list'][0]['statistics']['share_count']) + # 上传时间戳 + album_create_time = str(js['item_list'][0]['create_time']) + # 将话题保存在列表中 + album_hashtags = [] + for tag in js['item_list'][0]['text_extra']: + album_hashtags.append(tag['hashtag_name']) + # 将无水印图片链接保存在列表中 + images_list = [] + for data in js['item_list'][0]['images']: + images_list.append(data['url_list'][0]) + # 结束时间 + end = time.time() + # 解析时间 + analyze_time = format((end - start), '.4f') + # 将信息储存在字典中 + album_data = {'status': 'success', + 'analyze_time': (analyze_time + 's'), + 'url_type': url_type, + 'platform': 'douyin', + 'original_url': original_url, + 'api_url': api_url, + 'album_aweme_id': album_aweme_id, + 'album_title': album_title, + 'album_author': album_author, + 'album_author_signature': album_author_signature, + 'album_author_uid': album_author_uid, + 'album_author_id': album_author_id, + 'album_music': album_music, + 'album_music_title': album_music_title, + 'album_music_author': album_music_author, + 'album_music_id': album_music_id, + 'album_music_mid': album_music_mid, + 'album_comment_count': album_comment_count, + 'album_digg_count': album_digg_count, + 'album_play_count': album_play_count, + 'album_share_count': album_share_count, + 'album_create_time': album_create_time, + 'album_list': images_list, + 'album_hashtags': album_hashtags} + return album_data + else: + print("类型 = 视频") + # 类型为视频 + url_type = 'video' + # 视频标题 + video_title = str(js['item_list'][0]['desc']) + # 视频作者昵称 + video_author = str(js['item_list'][0]['author']['nickname']) + # 视频作者抖音号 + video_author_id = str(js['item_list'][0]['author']['unique_id']) + if video_author_id == "": + # 如果作者未修改过抖音号，应使用此值以避免无法获取其抖音ID + video_author_id = str(js['item_list'][0]['author']['short_id']) + # 有水印视频链接 + wm_video_url = str(js['item_list'][0]['video']['play_addr']['url_list'][0]) + # 无水印视频链接 (在回执JSON中将关键字'playwm'替换为'play'即可获得无水印地址) + nwm_video_url = str(js['item_list'][0]['video']['play_addr']['url_list'][0]).replace('playwm', 'play') + # 去水印后视频链接(2022年1月1日抖音APi获取到的URL会进行跳转，需要在Location中获取直链) + r = requests.get(url=nwm_video_url, headers=headers, allow_redirects=False) + video_url = r.headers['Location'] + # 视频作者签名 + video_author_signature = str(js['item_list'][0]['author']['signature']) + # 视频作者UID + video_author_uid = str(js['item_list'][0]['author']['uid']) + # 尝试获取视频背景音乐 + try: + # 视频BGM链接 + video_music = str(js['item_list'][0]['music']['play_url']['url_list'][0]) + # 视频BGM标题 + video_music_title = str(js['item_list'][0]['music']['title']) + # 视频BGM作者 + video_music_author = str(js['item_list'][0]['music']['author']) + # 视频BGM ID + video_music_id = str(js['item_list'][0]['music']['id']) + # 视频BGM MID + video_music_mid = str(js['item_list'][0]['music']['mid']) + except: + # 出错代表无背景音乐 + # 视频BGM链接 + video_music = 'No BGM found' + # 视频BGM标题 + video_music_title = 'No BGM found' + # 视频BGM作者 + video_music_author = 'No BGM found' + # 视频BGM ID + video_music_id = 'No BGM found' + # 视频BGM MID + video_music_mid = 'No BGM found' + # 视频ID + video_aweme_id = str(js['item_list'][0]['statistics']['aweme_id']) + # 评论数量 + video_comment_count = str(js['item_list'][0]['statistics']['comment_count']) + # 获赞数量 + video_digg_count = str(js['item_list'][0]['statistics']['digg_count']) + # 播放次数 + video_play_count = str(js['item_list'][0]['statistics']['play_count']) + # 分享次数 + video_share_count = str(js['item_list'][0]['statistics']['share_count']) + # 上传时间戳 + video_create_time = str(js['item_list'][0]['create_time']) + # 将话题保存在列表中 + video_hashtags = [] + for tag in js['item_list'][0]['text_extra']: + video_hashtags.append(tag['hashtag_name']) + # 结束时间 + end = time.time() + # 解析时间 + analyze_time = format((end - start), '.4f') + # 返回包含数据的字典 + video_data = {'status': 'success', + 'analyze_time': (analyze_time + 's'), + 'url_type': url_type, + 'platform': 'douyin', + 'original_url': original_url, + 'api_url': api_url, + 'video_title': video_title, + 'nwm_video_url': video_url, + 'wm_video_url': wm_video_url, + 'video_aweme_id': video_aweme_id, + 'video_author': video_author, + 'video_author_signature': video_author_signature, + 'video_author_uid': video_author_uid, + 'video_author_id': video_author_id, + 'video_music': video_music, + 'video_music_title': video_music_title, + 'video_music_author': video_music_author, + 'video_music_id': video_music_id, + 'video_music_mid': video_music_mid, + 'video_comment_count': video_comment_count, + 'video_digg_count': video_digg_count, + 'video_play_count': video_play_count, + 'video_share_count': video_share_count, + 'video_create_time': video_create_time, + 'video_hashtags': video_hashtags} + return video_data + except Exception as e: + # 返回异常 + return {'status': 'failed', 'reason': e, 'function': 'Scraper.douyin()', 'value': original_url} + + @retry(stop_max_attempt_number=6) + def tiktok(self, original_url): + """ + 解析TikTok链接 + :param original_url:TikTok链接 + :return:包含信息的字典 + """ + headers = self.headers + # 开始时间 + start = time.time() + # 校验TikTok链接 + if original_url[:12] == "https://www.": + original_url = original_url + print("目标链接: ", original_url) + else: + # 从请求头中获取原始链接 + response = requests.get(url=original_url, headers=headers, allow_redirects=False) + true_link = response.headers['Location'].split("?")[0] + original_url = true_link + # TikTok请求头返回的第二种链接类型 + if '.html' in true_link: + response = requests.get(url=true_link, headers=headers, allow_redirects=False) + original_url = response.headers['Location'].split("?")[0] + print("目标链接: ", original_url) + try: + # 获取视频ID + video_id = re.findall('video/(\d+)?', original_url)[0] + print('获取到的TikTok视频ID是{}'.format(video_id)) + # 从TikTok网页获取部分视频数据 + tiktok_headers = self.tiktok_headers + html = requests.get(url=original_url, headers=tiktok_headers) + res = re.search(' |') + rstr = r"[\/\\\:\*\?\"\<\>\|]" + # 将上述字符替换为下划线 + new_title = re.sub(rstr, "_", string) + # 新文件名 + filename = ('douyin.wtf_' + new_title + '_' + author_name).replace('\n', '') + return filename + + +@app.route("/", methods=["POST", "GET"]) +def index(): + # 显示基础信息 + index_info = {'API status': 'Running', + 'GitHub': 'https://github.com/Evil0ctal/Douyin_TikTok_Download_API', + 'Introduction': 'Free and open source Douyin/TikTok watermark-free video download tool, supports API calls.', + 'Web interface': 'https://douyin.wtf/', + 'iOS Shortcuts': 'https://api.douyin.wtf/ios', + 'Parsing Douyin/TikTok videos': 'https://api.douyin.wtf/api?url=[Douyin/TikTok url]', + 'Return Video MP4 File Download': 'https://api.douyin.wtf/video?url=[Douyin/TikTok url]', + 'Return Video MP3 File Download': 'https://api.douyin.wtf/music?url=[Douyin/TikTok url]'} + return jsonify(index_info) + + +@app.route("/api", methods=["POST", "GET"]) +def webapi(): + # 创建一个Flask应用获取POST参数并返回结果 + api = Scraper() + content = request.args.get("url") + if content != '': + post_content = find_url(content)[0] + if api_config['Allow_Logs']: + # 将API记录在API_logs.txt中 + date = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) + with open('API_logs.txt', 'a') as f: + f.write(date + " : " + post_content + '\n') + try: + # 开始时间 + start = time.time() + # 校验是否为TikTok链接 + if 'tiktok.com' in post_content: + result = api.tiktok(post_content) + # 以JSON格式返回TikTok信息 + return jsonify(result) + # 如果关键字不存在则判断为抖音链接 + elif 'douyin.com' in post_content: + result = api.douyin(post_content) + # 以JSON格式返回返回Douyin信息 + return jsonify(result) + except Exception as e: + # 结束时间 + end = time.time() + # 解析时间 + analyze_time = (format((end - start), '.4f') + 's') + # 返回错误信息 + return jsonify(status='failed', reason=str(e), time=analyze_time, function='webapi()', value=content) + else: + # 返回错误信息 + return jsonify(status='failed', reason='url value cannot be empty', function='api()', value=content) + + +@app.route("/ios", methods=["POST", "GET"]) +def ios_shortcut(): + # 用于检查快捷指令更新 + return jsonify(version=api_config['iOS_Shortcut_Version'], + update=api_config['iOS_Shortcut_Update_Time'], + link=api_config['iOS_Shortcut_Link'], + note=api_config['iOS_Shortcut_Update_Note']) + + +@app.route("/video", methods=["POST", "GET"]) +def download_video(): + # 用于返回视频下载请求(返回MP4文件下载请求，面对大量请求时非常吃服务器内存，容易崩，慎用。) + # 将api_switch的值设定为False可关闭该API + api_switch = api_config['Video_Download'] + if api_switch: + api = Scraper() + content = request.args.get("url") + if content == '': + return jsonify(status='failed', reason='url value cannot be empty', function='download_music()', + value=content) + else: + post_content = find_url(content)[0] + try: + if 'douyin.com' in post_content: + # 获取视频信息 + result = api.douyin(post_content) + # 视频链接 + video_url = result['nwm_video_url'] + # 视频标题 + video_title = result['video_title'] + # 作者昵称 + video_author = result['video_author'] + # 清理文件名 + file_name = clean_filename(video_title, video_author) + elif 'tiktok.com' in post_content: + # 获取视频信息 + result = api.tiktok(post_content) + # 无水印地址 + video_url = result['nwm_video_url'] + # 视频标题 + video_title = result['video_title'] + # 作者昵称 + video_author = result['video_author'] + # 清理文件名 + file_name = clean_filename(video_title, video_author) + else: + return jsonify(Status='Failed', Reason='Check submitted parameters!') + # 获取视频文件字节流 + video_mp4 = requests.get(video_url, headers).content + # 将字节流封装成返回对象 + response = make_response(video_mp4) + # 添加响应头部信息 + response.headers['Content-Type'] = "video/mp4" + # 他妈的,费了我老大劲才解决文件中文名的问题 + try: + filename = file_name.encode('latin-1') + except UnicodeEncodeError: + filenames = { + 'filename': unicodedata.normalize('NFKD', file_name).encode('latin-1', 'ignore'), + 'filename*': "UTF-8''{}".format(url_quote(file_name) + '.mp4'), + } + else: + filenames = {'filename': file_name + '.mp4'} + # attachment表示以附件形式下载 + response.headers.set('Content-Disposition', 'attachment', **filenames) + return response + except Exception as e: + return jsonify(status='failed', reason=str(e), function='download_video()', value=content) + else: + return jsonify(Status='Failed', Reason='This API is disabled. To enable it, set the value of "api_switch" to True.') + + +@app.route("/music", methods=["POST", "GET"]) +def download_music(): + # 用于返回视频下载请求(返回MP3文件下载请求，面对大量请求时非常吃服务器内存，容易崩，慎用。) + # 将api_switch的值设定为False可关闭该API + api_switch = api_config['Music_Download'] + if api_switch: + api = Scraper() + content = request.args.get("url") + if content == '': + return jsonify(status='failed', reason='url value cannot be empty', function='download_music()', + value=content) + else: + post_content = find_url(content)[0] + try: + if 'douyin.com' in post_content: + # 获取视频信息 + result = api.douyin(post_content) + bgm_url = result['video_music'] + if bgm_url == "None": + return jsonify(Status='Failed', Reason='This link has no music to get!') + else: + # 视频标题 + bgm_title = result['video_music_title'] + # 作者昵称 + author_name = result['video_music_author'] + # 清理文件名 + file_name = clean_filename(bgm_title, author_name) + elif 'tiktok.com' in post_content: + # 获取视频信息 + result = api.douyin(post_content) + # BGM链接 + bgm_url = result['video_music'] + # 视频标题 + bgm_title = result['video_music_title'] + # 作者昵称 + author_name = result['video_music_author'] + # 清理文件名 + file_name = clean_filename(bgm_title, author_name) + else: + return jsonify(Status='Failed', Reason='This link has no music to get!') + video_bgm = requests.get(bgm_url, headers).content + # 将bgm字节流封装成response对象 + response = make_response(video_bgm) + # 添加响应头部信息 + response.headers['Content-Type'] = "video/mp3" + # 他妈的,费了我老大劲才解决文件中文名的问题 + try: + filename = file_name.encode('latin-1') + except UnicodeEncodeError: + filenames = { + 'filename': unicodedata.normalize('NFKD', file_name).encode('latin-1', 'ignore'), + 'filename*': "UTF-8''{}".format(url_quote(file_name) + '.mp3'), + } + else: + filenames = {'filename': file_name + '.mp3'} + # attachment表示以附件形式下载 + response.headers.set('Content-Disposition', 'attachment', **filenames) + return response + except Exception as e: + return jsonify(status='failed', reason=str(e), function='download_music()', value=content) + else: + return jsonify(Status='Failed', Reason='This API is disabled. To enable it, set the value of "api_switch" to True.') + + +if __name__ == '__main__': + # 开启WebAPI + if os.environ.get('PORT'): + port = int(os.environ.get('PORT')) + else: + # 默认端口 + port = api_config['Port'] + app.run(host='0.0.0.0', port=port) diff --git a/web_zh.py b/web_zh.py new file mode 100644 index 0000000..515c2c9 --- /dev/null +++ b/web_zh.py @@ -0,0 +1,486 @@ +#!/usr/bin/env python +# -*- encoding: utf-8 -*- +# @Author: https://github.com/Evil0ctal/ +# @Time: 2021/11/06 +# @Update: 2022/04/21 +# @Function: +# 用于在线批量解析Douyin/TikTok的无水印视频/图集。 +# 基于 PyWebIO、Flask, 将scraper.py返回的内容显示在网页上。 +# 默认运行端口5000, 请自行在config.ini中修改。 + + +import os +import re +import time +import json +import tarfile +import requests +import configparser +from scraper import Scraper +from pywebio import config, session +from pywebio.input import * +from pywebio.output import * +from pywebio.platform.flask import webio_view +from flask import Flask + +app = Flask(__name__) +app_config = configparser.ConfigParser() +app_config.read('config.ini', encoding='utf-8') +web_config = app_config['Web_ZH'] +title = web_config['Web_Title'] +description = web_config['Web_Description'] +headers = { + 'user-agent': 'Mozilla/5.0 (Linux; Android 8.0; Pixel 2 Build/OPD3.170816.012) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Mobile Safari/537.36 Edg/87.0.664.66' +} + + +def loading(): + # 写一个进度条装装样子吧 :) + set_scope('bar', position=3) + with use_scope('bar'): + put_processbar('bar') + for i in range(1, 4): + set_processbar('bar', i / 3) + time.sleep(0.1) + + +def find_url(string): + # 解析抖音分享口令中的链接并返回列表 + url = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', string) + return url + + +def valid_check(kou_ling): + # 校验输入的内容 + url_list = find_url(kou_ling) + # 对每一个链接进行校验 + if url_list: + total_urls = len(url_list) + # 最大接受提交URL的数量 + max_urls = web_config['Max_Take_URLs'] + if total_urls > int(max_urls): + return '为了避免资源占用过多请确保每次提交的链接少于10个，如需大量解析请自行部署。' + else: + for i in url_list: + if 'douyin.com' in i[:31]: + if i == url_list[-1]: + return None + elif 'tiktok.com' in i[:31]: + if i == url_list[-1]: + return None + else: + return '请确保输入链接均为有效的抖音/TikTok链接!' + elif kou_ling == 'wyn': + return None + else: + return '抖音分享口令有误!' + + +def error_do(reason, function, value): + # 输出一个毫无用处的信息 + put_html("
") + put_error("发生了了意料之外的错误，输入值已被记录。") + put_html('

⚠详情

') + put_table([ + ['函数名', '原因', '输入值'], + [function, str(reason), value]]) + put_markdown('可能的原因:') + put_markdown('服务器可能被目标主机的防火墙限流(稍等片刻后再次尝试)') + put_markdown('输入了错误的链接(暂不支持主页链接解析)') + put_markdown('该视频已经被删除或屏蔽(你看的都是些啥(⊙_⊙)?)') + put_markdown('你可以在右上角的关于菜单中查看本站错误日志。') + put_markdown('[点击此处在GayHub上进行反馈](https://github.com/Evil0ctal/Douyin_TikTok_Download_API/issues)') + put_html("
") + if web_config['Allow_Logs']: + # 将错误记录在logs.txt中 + error_date = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) + with open('logs.txt', 'a') as f: + f.write(error_date + ":\n" + function + ': ' + str(reason) + '\n' + "Input value: " + value + '\n') + + +def clean_filename(string, author_name): + # 替换不能用于文件名的字符('/ \ : * ? " < > |') + rstr = r"[\/\\\:\*\?\"\<\>\|]" + # 将上述字符替换为下划线 + new_title = re.sub(rstr, "_", string) + # 新文件名 + filename = (author_name + '_' + new_title).replace('\n', '') + return filename + + +def compress_file(tar_file, target_file): + # tar_file是输出压缩包名字以及目录("./output/mp4.tar")，target_file是要打包的目录或文件名("./files") + if os.path.isfile(target_file): + with tarfile.open(tar_file, 'w') as tar: + tar.add(target_file) + return 'finished' + else: + with tarfile.open(tar_file, 'w') as tar: + for root, dirs, files in os.walk(target_file): + for single_file in files: + filepath = os.path.join(root, single_file) + tar.add(filepath) + return 'finished' + + +def clean_file(path): + # 清理下载文件夹 + while True: + for root, dirs, files in os.walk(path, topdown=False): + for name in files: + os.remove(os.path.join(root, name)) + # print("%s文件删除成功 %s" % (name, (time.strftime("%d/%m/%Y%H:%M:%S")))) + for name in dirs: + os.rmdir(os.path.join(root, name)) + # print("%s子文件夹下文件删除成功 %s" % (name, (time.strftime("%d/%m/%Y%H:%M:%S")))) + # 每30分钟(1800秒)清理一次 + time.sleep(1800) + + +def video_download_window(result_dict): + try: + # result_dict = {'文件名': '链接'} + total_amount = len(result_dict) + download_time = (time.strftime("%Y_%m_%d_%H_%M_%S", time.localtime())) + # 存储根目录 + save_path = './web/saved_videos/' + (download_time + '_total_' + str(total_amount) + '_videos') + # 判断目录是否存在 + if not os.path.exists(save_path): + os.makedirs(save_path) + # 弹出窗口 + with popup("正在服务器后台下载视频(共{}个下载任务)".format(str(len(result_dict)))): + # 下载索引计数 + download_count = 0 + # 遍历字典的键和值 + for file_name, url in result_dict.items(): + try: + download_count += 1 + put_info('正在下载第{}个视频:\n{}'.format(download_count, file_name)) + response = requests.get(url, headers=headers) + data = response.content + if data: + file_path = '{}/{}.{}'.format(save_path, file_name, 'mp4') + if not os.path.exists(file_path): + with open(file_path, 'wb') as f: + f.write(data) + f.close() + put_success('{}下载成功'.format(file_name)) + except Exception as e: + download_count += 1 + put_error('视频下载失败，将跳过该视频。') + continue + if download_count == total_amount: + put_html('
') + put_html('

💾结果页视频合集下载完成

') + output_path = save_path + '/output' + tarfile_name = download_time + '_total_' + str(total_amount) + '_videos.tar' + output_file = output_path + '/' + tarfile_name + put_info('正在压缩视频文件，请勿关闭当前弹窗，完成后会在下方显示按钮...') + # 判断目录是否存在 + if not os.path.exists(output_path): + os.mkdir(output_path) + if compress_file(tar_file=output_file, target_file=save_path) == 'finished': + tar = open(output_file, "rb").read() + put_file(tarfile_name, tar, '点击下载视频合集压缩包') + except Exception as e: + print(str(e)) + + +def put_douyin_result(item): + # 向前端输出表格 + api = Scraper() + # 抖音数据 + douyin_date = api.douyin(item) + # API链接 + short_api_url = 'https://api.douyin.wtf/api?url=' + item + download_video = 'https://api.douyin.wtf/video?url=' + item + download_bgm = 'https://api.douyin.wtf/music?url=' + item + if douyin_date['status'] == 'success': + if douyin_date['url_type'] == 'video': + put_table([ + ['类型', '内容'], + ['格式:', douyin_date['url_type']], + ['视频直链: ', put_link('点击打开视频', douyin_date['nwm_video_url'], new_window=True)], + ['视频下载：', put_link('点击下载', download_video, new_window=True)], + ['背景音乐直链: ', put_link('点击打开音频', douyin_date['video_music'], new_window=True)], + ['背景音乐下载：', put_link('点击下载', download_bgm, new_window=True)], + ['视频标题: ', douyin_date['video_title']], + ['作者昵称: ', douyin_date['video_author']], + ['作者抖音ID: ', douyin_date['video_author_id']], + ['原视频链接: ', put_link('点击打开原视频', item, new_window=True)], + ['当前视频API链接: ', put_link('点击浏览API数据', douyin_date['api_url'], new_window=True)], + ['当前视频精简API链接: ', put_link('点击浏览API数据', short_api_url, new_window=True)] + ]) + return {'status': 'success', + 'type': 'video', + 'video_title': douyin_date['video_title'], + 'video_author': douyin_date['video_author'], + 'nwm_video_url': douyin_date['nwm_video_url'], + 'video_music': douyin_date['video_music'], + 'original_url': douyin_date['original_url']} + else: + put_table([ + ['类型', '内容'], + ['格式:', douyin_date['url_type']], + ['背景音乐直链: ', put_link('点击打开音频', douyin_date['album_music'], new_window=True)], + ['背景音乐下载：', put_link('点击下载', download_bgm, new_window=True)], + ['视频标题: ', douyin_date['album_title']], + ['作者昵称: ', douyin_date['album_author']], + ['作者抖音ID: ', douyin_date['album_author_id']], + ['原视频链接: ', put_link('点击打开原视频', douyin_date['original_url'], new_window=True)], + ['当前视频API链接: ', put_link('点击浏览API数据', douyin_date['api_url'], new_window=True)], + ['当前视频精简API链接: ', put_link('点击浏览API数据', 'short_api_url', new_window=True)] + ]) + for i in douyin_date['album_list']: + put_table([ + ['图片直链: ', put_link('点击打开图片', i, new_window=True), put_image(i)] + ]) + return {'status': 'success', + 'type': 'album', + 'album_title': douyin_date['album_title'], + 'video_author': douyin_date['video_author'], + 'album_list': douyin_date['album_list'], + 'album_music': douyin_date['album_music'], + 'original_url': douyin_date['original_url']} + else: + # {'status': 'failed', 'reason': e, 'function': 'API.tiktok()', 'value': original_url} + reason = douyin_date['reason'] + function = douyin_date['function'] + value = douyin_date['value'] + error_do(reason, function, value) + return 'failed' + + +def put_tiktok_result(item): + # 将TikTok结果显示在前端 + api = Scraper() + # TikTok数据 + tiktok_date = api.tiktok(item) + if tiktok_date['status'] == 'success': + # API链接 + short_api_url = 'https://api.douyin.wtf/api?url=' + item + download_video = 'https://api.douyin.wtf/video?url=' + item + download_bgm = 'https://api.douyin.wtf/music?url=' + item + put_table([ + ['类型', '内容'], + ['视频标题: ', tiktok_date['video_title']], + ['视频直链(有水印): ', put_link('点击打开视频', tiktok_date['wm_video_url'], new_window=True)], + ['视频直链(无水印): ', put_link('点击打开视频', tiktok_date['nwm_video_url'], new_window=True)], + ['视频下载(无水印)：', put_link('点击下载', download_video, new_window=True)], + ['音频(名称-作者)：', tiktok_date['video_music_title'] + " - " + tiktok_date['video_music_author']], + ['音频播放：', put_link('点击播放', tiktok_date['video_music_url'], new_window=True)], + ['音频下载：', put_link('点击下载', download_bgm, new_window=True)], + ['作者昵称: ', tiktok_date['video_author_nickname']], + ['作者ID: ', tiktok_date['video_author_id']], + ['粉丝数量: ', tiktok_date['video_author_followerCount']], + ['关注他人数量: ', tiktok_date['video_author_followingCount']], + ['获赞总量: ', tiktok_date['video_author_heartCount']], + ['视频总量: ', tiktok_date['video_author_videoCount']], + ['原视频链接: ', put_link('点击打开原视频', item, new_window=True)], + ['当前视频API链接: ', put_link('点击浏览API数据', short_api_url, new_window=True)] + ]) + return {'status': 'success', + 'type': 'video', + 'video_title': tiktok_date['video_title'], + 'video_author': tiktok_date['video_author_nickname'], + 'nwm_video_url': tiktok_date['nwm_video_url'], + 'video_music_url': tiktok_date['video_music_url'], + 'original_url': item} + else: + # {'status': 'failed', 'reason': e, 'function': 'API.tiktok()', 'value': original_url} + reason = tiktok_date['reason'] + function = tiktok_date['function'] + value = tiktok_date['value'] + error_do(reason, function, value) + return 'failed' + + +def ios_pop_window(): + with popup("iOS快捷指令"): + try: + shortcut = json.loads(requests.get(url='https://api.douyin.wtf/ios', headers=headers).text) + shortcut_link = shortcut['link'] + shortcut_note = shortcut['note'] + shortcut_update = shortcut['update'] + shortcut_version = shortcut['version'] + except Exception as e: + shortcut_link = '无法获取快捷指令信息,请到Github上进行反馈。' + shortcut_note = '无法获取快捷指令信息,请到Github上进行反馈。' + shortcut_update = '无法获取快捷指令信息,请到Github上进行反馈。' + shortcut_version = '无法获取快捷指令信息,请到Github上进行反馈。' + put_text('快捷指令需要在抖音或TikTok的APP内，浏览你想要无水印保存的视频或图集。') + put_text('然后点击右下角分享按钮，选择更多，然后下拉找到 "抖音TikTok无水印下载" 这个选项。') + put_text('如遇到通知询问是否允许快捷指令访问xxxx (域名或服务器)，需要点击允许才可以正常使用。') + put_text('该快捷指令会在你相册创建一个新的相薄方便你浏览保存的内容。') + put_html('
') + put_text('最新快捷指令版本: {}'.format(shortcut_version)) + put_text('快捷指令更新时间: {}'.format(shortcut_update)) + put_text('快捷指令更新内容: {}'.format(shortcut_note)) + put_link('[点击获取快捷指令]', shortcut_link, new_window=True) + + +def api_document_pop_window(): + with popup("API文档"): + put_markdown("💽API文档") + put_markdown("API可将请求参数转换为需要提取的无水印视频/图片直链，配合IOS捷径可实现应用内下载。") + put_link('[中文文档]', 'https://github.com/Evil0ctal/Douyin_TikTok_Download_API#%EF%B8%8Fapi%E4%BD%BF%E7%94%A8', + new_window=True) + put_html('
') + put_link('[English doc]', + 'https://github.com/Evil0ctal/Douyin_TikTok_Download_API/blob/main/README.en.md#%EF%B8%8Fapi-usage', + new_window=True) + put_html('
') + put_markdown("🛰️API参考") + put_markdown('抖音/TikTok解析请求参数') + put_code('https://api.douyin.wtf/api?url="复制的(抖音/TikTok)的(分享文本/链接)"\n#返回JSON') + put_markdown('抖音/TikTok视频下载请求参数') + put_code('https://api.douyin.wtf/video?url="复制的抖音/TikTok链接"\n' + '# 返回mp4文件下载请求\n' + '# 大量请求时很吃服务器内存，容易崩，慎用。') + put_markdown('抖音视频/图集音频下载请求参数') + put_code('https://api.douyin.wtf/music?url="复制的抖音/TikTok链接"\n' + '# 返回mp3文件下载请求\n' + '# 大量请求时很吃服务器内存，容易崩，慎用。') + + +def log_popup_window(): + with popup('错误日志'): + put_html('

⚠️关于解析失败可能的原因

') + put_markdown('服务器可能被目标主机的防火墙限流(稍等片刻后再次尝试)') + put_markdown('输入了错误的链接(暂不支持主页链接解析)') + put_markdown('该视频已经被删除或屏蔽(你看的都是些啥(⊙_⊙)?)') + put_markdown('[点击此处在GayHub上进行反馈](https://github.com/Evil0ctal/Douyin_TikTok_Download_API/issues)') + put_html('
') + put_text('点击logs.txt可下载日志:') + content = open(r'./logs.txt', 'rb').read() + put_file('logs.txt', content=content) + with open('./logs.txt', 'r') as f: + content = f.read() + put_text(str(content)) + + +def about_popup_window(): + with popup('更多信息'): + put_html('

👀访问记录

') + put_image('https://views.whatilearened.today/views/github/evil0ctal/TikTokDownload_PyWebIO.svg', + title='访问记录') + put_html('
') + put_html('

⭐Github

') + put_markdown('[Douyin_TikTok_Download_API](https://github.com/Evil0ctal/Douyin_TikTok_Download_API)') + put_html('
') + put_html('

🎯反馈

') + put_markdown('提交：[issues](https://github.com/Evil0ctal/Douyin_TikTok_Download_API/issues)') + put_html('
') + put_html('

🌐视频/图集批量下载

') + put_markdown('可以使用[IDM](https://www.zhihu.com/topic/19746283/hot)之类的工具对结果页面的链接进行嗅探。') + put_markdown('如果你有更好的想法欢迎PR') + put_html('
') + put_html('

💖WeChat

') + put_markdown('微信：[Evil0ctal](https://mycyberpunk.com/)') + put_html('
') + + +@config(title=title, description=description) +def main(): + # 设置favicon + favicon_url = "https://raw.githubusercontent.com/Evil0ctal/Douyin_TikTok_Download_API/main/favicon/android-chrome-512x512.png" + session.run_js(""" + $('#favicon32,#favicon16').remove(); + $('head').append('') + """ % favicon_url) + # 修改footer + session.run_js("""$('footer').remove()""") + # 访问记录 + view_amount = requests.get("https://views.whatilearened.today/views/github/evil0ctal/TikTokDownload_PyWebIO.svg") + put_markdown("""
😼抖音/TikTok无水印在线解析
""") + put_html('
') + put_row([put_button("快捷指令", onclick=lambda: ios_pop_window(), link_style=True, small=True), + put_button("API", onclick=lambda: api_document_pop_window(), link_style=True, small=True), + put_button("日志", onclick=lambda: log_popup_window(), link_style=True, small=True), + put_button("关于", onclick=lambda: about_popup_window(), link_style=True, small=True) + ]) + placeholder = "批量解析请直接粘贴多个口令或链接，无需使用符号分开，支持抖音和TikTok链接混合，暂时不支持作者主页链接批量解析。" + kou_ling = textarea('请将抖音或TikTok的分享口令或网址粘贴于此', type=TEXT, validate=valid_check, required=True, + placeholder=placeholder, + position=0) + if kou_ling: + if kou_ling == 'wyn': + # 好想你(小彩蛋) + with popup('给 WYN💖'): + put_text('我大约真的没有什么才华，只是因为有幸见着了你，于是这颗庸常的心中才凭空生出好些浪漫。') + put_text('真的好爱你呀！') + put_link('WYN&THB', 'https://www.wynthb.com/') + else: + url_lists = find_url(kou_ling) + total_urls = len(url_lists) + # 解析开始时间 + start = time.time() + # 放一个毫无意义的进度条 + loading() + # 成功/失败统计 + success_count = 0 + failed_count = 0 + # 解析成功的url + success_list = [] + # 解析失败的url + failed_list = [] + # 成功解析的视频标题/视频直链 + nwm_success_list = {} + # 遍历链接 + for url in url_lists: + if 'douyin.com' in url: + result = put_douyin_result(url) + if result == 'failed': + failed_count += 1 + # 将url添加到失败列表内 + failed_list.append(url) + continue + else: + success_count += 1 + # 将url添加到成功列表内 + success_list.append(url) + if result['type'] == 'video': + filename = clean_filename(string=result['video_title'], author_name=result['video_author']) + nwm_success_list.update({filename: result['nwm_video_url']}) + else: + result = put_tiktok_result(url) + if result == 'failed': + failed_count += 1 + # 将url添加到失败列表内 + failed_list.append(url) + continue + else: + success_count += 1 + # 将url添加到成功列表内 + success_list.append(url) + if result['type'] == 'video': + filename = clean_filename(string=result['video_title'], author_name=result['video_author']) + nwm_success_list.update({filename: result['nwm_video_url']}) + clear('bar') + # 解析结束时间 + end = time.time() + put_html("
") + put_text('总共收到' + str(total_urls) + '个链接') + put_text('成功: ' + str(success_count) + ' ' + '失败: ' + str(failed_count)) + put_text('解析共耗时: %.4f秒' % (end - start)) + if web_config['Allow_Batch_Download']: + put_button("下载结果页中的所有视频", onclick=lambda: video_download_window(nwm_success_list)) + put_link('返回主页', '/') + time.sleep(300) + # 清理文件夹 + clean_file('./web/saved_videos') + + +if __name__ == "__main__": + # 初始化logs.txt + date = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) + with open('logs.txt', 'a') as f: + f.write("时间: " + date + " " + "程序重载完毕!" + '\n') + app.add_url_rule('/', 'webio_view', webio_view(main), methods=['GET', 'POST', 'OPTIONS']) + # 获取空闲端口 + if os.environ.get('PORT'): + port = int(os.environ.get('PORT')) + else: + # 在这里修改默认端口(记得在防火墙放行该端口) + port = web_config['Port'] + app.run(host='0.0.0.0', port=port)