mirror of
https://github.com/Evil0ctal/Douyin_TikTok_Download_API.git
synced 2025-04-22 21:45:58 +08:00
🚀重构代码
This commit is contained in:
Evil0ctal
GitHub
parent
ffe0674e2c
commit
3fccb527f1
387
scraper.py
Normal file
387
scraper.py
Normal file
@ -0,0 +1,387 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
# @Author: https://github.com/Evil0ctal/
|
||||
# @Time: 2021/11/06
|
||||
# @Update: 2022/04/05
|
||||
# @Function:
|
||||
# 用于解析抖音/TikTok的无水印视频/图集。
|
||||
|
||||
|
||||
import re
|
||||
import json
|
||||
import time
|
||||
import requests
|
||||
from retrying import retry
|
||||
|
||||
|
||||
class Scraper:
|
||||
"""
|
||||
API.douyin():抖音视频/图集解析
|
||||
API.tiktok():TikTok视频解析
|
||||
"""
|
||||
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'])
|
||||
# 图集BGM链接
|
||||
if len(js['item_list'][0]['music']['play_url']['url_list']) > 0:
|
||||
album_music = str(js['item_list'][0]['music']['play_url']['url_list'][0])
|
||||
else:
|
||||
# 部分视频的API数据中没有BGM链接，返回None
|
||||
album_music = "None"
|
||||
# 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'])
|
||||
# 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']
|
||||
# 视频背景音频
|
||||
if len(js['item_list'][0]['music']['play_url']['url_list']) > 0:
|
||||
video_music = str(js['item_list'][0]['music']['play_url']['url_list'][0])
|
||||
else:
|
||||
# 部分视频的API数据中没有BGM链接，返回None
|
||||
video_music = "None"
|
||||
# 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'])
|
||||
# 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'])
|
||||
# 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]
|
||||
# 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:
|
||||
# 开始获取TikTok数据
|
||||
tiktok_headers = self.tiktok_headers
|
||||
html = requests.get(url=original_url, headers=tiktok_headers)
|
||||
res = re.search('<script id="sigi-persisted-data">(.*)</script><script', html.text).group(1)
|
||||
resp = re.findall(r'^window\[\'SIGI_STATE\']=(.*)?;window', res)[0]
|
||||
result = json.loads(resp)
|
||||
author_id = result["ItemList"]["video"]["list"][0]
|
||||
# 从网页中获得的视频JSON数据
|
||||
video_info = result["ItemModule"][author_id]
|
||||
# print(video_info)
|
||||
# 使用第三方API获取无水印视频链接（不保证稳定）
|
||||
s = requests.Session()
|
||||
api_url = "https://ttdownloader.com/req/"
|
||||
source = s.get("https://ttdownloader.com/")
|
||||
token = re.findall(r'value=\"([0-9a-z]+)\"', source.text)
|
||||
result = s.post(
|
||||
api_url,
|
||||
data={'url': original_url, 'format': '', 'token': token[0]}
|
||||
)
|
||||
nwm, wm, audio = re.findall(
|
||||
r'(https?://.*?.php\?v\=.*?)\"', result.text
|
||||
)
|
||||
r = requests.get(nwm, allow_redirects=False)
|
||||
# 整理数据
|
||||
print("类型 = 视频")
|
||||
# 无水印视频链接
|
||||
nwm_video_url = r.headers['Location']
|
||||
# 有水印视频链接
|
||||
wm_video_url = video_info['video']['playAddr']
|
||||
# 类型为视频
|
||||
url_type = 'video'
|
||||
# 视频标题
|
||||
video_title = video_info['desc']
|
||||
# 视频作者昵称
|
||||
video_author = video_info['author']
|
||||
# 视频作者别名
|
||||
video_author_nickname = video_info['nickname']
|
||||
# 视频作者抖音号
|
||||
video_author_id = video_info['authorId']
|
||||
# 视频作者secid
|
||||
video_author_SecId = video_info['authorSecId']
|
||||
# 视频背景音频
|
||||
video_music = video_info['music']['playUrl']
|
||||
# 上传时间戳
|
||||
video_create_time = video_info['createTime']
|
||||
# 视频ID
|
||||
video_aweme_id = video_info['video']['id']
|
||||
# 视频分辨率
|
||||
video_ratio = video_info['video']['ratio']
|
||||
# 视频BGM标题
|
||||
video_music_title = video_info['music']['title']
|
||||
# 视频BGM作者
|
||||
video_music_author = video_info['music']['authorName']
|
||||
# 视频BGM ID
|
||||
video_music_id = video_info['music']['id']
|
||||
# 视频BGM链接
|
||||
video_music_url = video_info['music']['playUrl']
|
||||
# 评论数量
|
||||
video_comment_count = video_info['stats']['commentCount']
|
||||
# 获赞数量
|
||||
video_digg_count = video_info['stats']['diggCount']
|
||||
# 播放次数
|
||||
video_play_count = video_info['stats']['playCount']
|
||||
# 分享次数
|
||||
video_share_count = video_info['stats']['shareCount']
|
||||
# 作者粉丝数量
|
||||
video_author_followerCount = video_info['authorStats']['followerCount']
|
||||
# 作者关注数量
|
||||
video_author_followingCount = video_info['authorStats']['followingCount']
|
||||
# 作者获赞数量
|
||||
video_author_heartCount = video_info['authorStats']['heartCount']
|
||||
# 作者视频数量
|
||||
video_author_videoCount = video_info['authorStats']['videoCount']
|
||||
# 作者已赞作品数量
|
||||
video_author_diggCount = video_info['authorStats']['diggCount']
|
||||
# 将话题保存在列表中
|
||||
video_hashtags = []
|
||||
for tag in video_info['challenges']:
|
||||
video_hashtags.append(tag['title'])
|
||||
# 结束时间
|
||||
end = time.time()
|
||||
# 解析时间
|
||||
analyze_time = format((end - start), '.4f')
|
||||
# 储存数据
|
||||
video_date = {'status': 'success',
|
||||
'analyze_time': (analyze_time + 's'),
|
||||
'url_type': url_type,
|
||||
'original_url': original_url,
|
||||
'platform': 'tiktok',
|
||||
'video_title': video_title,
|
||||
'nwm_video_url': nwm_video_url,
|
||||
'wm_video_url': wm_video_url,
|
||||
'video_author': video_author,
|
||||
'video_author_nickname': video_author_nickname,
|
||||
'video_author_id': video_author_id,
|
||||
'video_author_SecId': video_author_SecId,
|
||||
'video_music': video_music,
|
||||
'video_create_time': video_create_time,
|
||||
'video_aweme_id': video_aweme_id,
|
||||
'video_ratio': video_ratio,
|
||||
'video_music_title': video_music_title,
|
||||
'video_music_author': video_music_author,
|
||||
'video_music_id': video_music_id,
|
||||
'video_music_url': video_music_url,
|
||||
'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_author_followerCount': video_author_followerCount,
|
||||
'video_author_followingCount': video_author_followingCount,
|
||||
'video_author_heartCount': video_author_heartCount,
|
||||
'video_author_videoCount': video_author_videoCount,
|
||||
'video_author_diggCount': video_author_diggCount,
|
||||
'video_hashtags': video_hashtags
|
||||
}
|
||||
# 返回包含数据的字典
|
||||
return video_date
|
||||
except Exception as e:
|
||||
# 异常捕获
|
||||
return {'status': 'failed', 'reason': e, 'function': 'Scraper.tiktok()', 'value': original_url}
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
# 测试类
|
||||
scraper = Scraper()
|
||||
tiktok_url = "https://www.tiktok.com/@oregonzoo/video/7074995215647477034"
|
||||
tiktok_date = scraper.tiktok(tiktok_url)
|
||||
print(tiktok_date)
|
||||
print('')
|
||||
douyin_url = "https://www.douyin.com/video/7036277592986537252"
|
||||
douyin_date = scraper.douyin(douyin_url)
|
||||
print(douyin_date)
|
||||
195
web_api.py
Normal file
195
web_api.py
Normal file
@ -0,0 +1,195 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
# @Author: https://github.com/Evil0ctal/
|
||||
# @Time: 2021/11/06
|
||||
# @Update: 2022/04/05
|
||||
# @Function:
|
||||
# 基于Requests、Flask，可实现在线批量解析抖音的无水印视频/图集。
|
||||
# 可用于下载作者禁止下载的视频，同时可搭配iOS的快捷指令APP配合本项目API实现应用内下载。
|
||||
|
||||
import os
|
||||
import re
|
||||
import time
|
||||
import requests
|
||||
import unicodedata
|
||||
from scraper import Scraper
|
||||
from werkzeug.urls import url_quote
|
||||
from flask import Flask, request, jsonify, make_response
|
||||
|
||||
|
||||
app = Flask(__name__)
|
||||
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 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 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 = ('douyin.wtf_' + new_title + '_' + author_name).replace('\n', '')
|
||||
return filename
|
||||
|
||||
|
||||
@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]
|
||||
# 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')
|
||||
|
||||
|
||||
|
||||
@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。)
|
||||
api = Scraper()
|
||||
content = request.args.get("url")
|
||||
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)
|
||||
|
||||
|
||||
@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。)
|
||||
api = Scraper()
|
||||
content = request.args.get("url")
|
||||
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)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
# 开启WebAPI
|
||||
if os.environ.get('PORT'):
|
||||
port = int(os.environ.get('PORT'))
|
||||
else:
|
||||
# 默认端口
|
||||
port = 2333
|
||||
app.run(host='0.0.0.0', port=port)
|
||||
334
web_zh.py
Normal file
334
web_zh.py
Normal file
@ -0,0 +1,334 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
# @Author: https://github.com/Evil0ctal/
|
||||
# @Time: 2021/11/06
|
||||
# @Update: 2022/04/05
|
||||
# @Function:
|
||||
# 基于 PyWebIO、Requests、Flask，可实现在线批量解析抖音的无水印视频/图集。
|
||||
# 可用于下载作者禁止下载的视频，同时可搭配iOS的快捷指令APP配合本项目API实现应用内下载。
|
||||
# API请求参考
|
||||
# 抖音/TikTok解析请求参数
|
||||
# http://localhost(服务器IP):80/api?url="复制的(抖音/TikTok)的(分享文本/链接)" - 返回JSON数据
|
||||
# 抖音/TikTok视频下载请求参数
|
||||
# http://localhost(服务器IP):80/video?url="复制的抖音/TikTok链接" - 返回mp4文件下载请求
|
||||
# 抖音视频/图集音频下载请求参数
|
||||
# http://localhost(服务器IP):80/bgm?url="复制的抖音/TikTok链接" - 返回mp3文件下载请求
|
||||
|
||||
|
||||
import os
|
||||
import re
|
||||
import time
|
||||
import requests
|
||||
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, request, jsonify
|
||||
|
||||
app = Flask(__name__)
|
||||
title = "抖音/TikTok无水印在线解析"
|
||||
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。"
|
||||
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:
|
||||
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("<hr>")
|
||||
put_error("发生了了意料之外的错误，输入值已被记录。")
|
||||
put_html('<h3>⚠详情</h3>')
|
||||
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/TikTokDownloader_PyWebIO/issues)')
|
||||
put_html("<hr>")
|
||||
# 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 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 'success'
|
||||
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['url_type'], 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 'success'
|
||||
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)],
|
||||
['作者昵称: ', tiktok_date['video_author_nickname']],
|
||||
['作者ID: ', tiktok_date['video_author']],
|
||||
['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 'success'
|
||||
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"):
|
||||
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('点击分享按钮，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到内容。')
|
||||
put_html('<br>')
|
||||
put_link('[点击获取快捷指令]', 'https://www.icloud.com/shortcuts/e8243369340548efa0d4c1888dd3c170',
|
||||
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/TikTokDownloader_PyWebIO#%EF%B8%8Fapi%E4%BD%BF%E7%94%A8',
|
||||
new_window=True)
|
||||
put_html('<br>')
|
||||
put_link('[English doc]',
|
||||
'https://github.com/Evil0ctal/TikTokDownloader_PyWebIO/blob/main/README.en.md#%EF%B8%8Fapi-usage',
|
||||
new_window=True)
|
||||
put_html('<hr>')
|
||||
put_markdown("🛰️API参考")
|
||||
put_markdown('抖音/TikTok解析请求参数')
|
||||
put_code('http://localhost(服务器IP):2333/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('http://localhost(服务器IP):2333/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('http://localhost(服务器IP):2333/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('<h3>⚠️关于解析失败可能的原因</h3>')
|
||||
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/TikTokDownloader_PyWebIO/issues)')
|
||||
put_html('<hr>')
|
||||
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('<h3>👀访问记录</h3>')
|
||||
put_image('https://views.whatilearened.today/views/github/evil0ctal/TikTokDownload_PyWebIO.svg',
|
||||
title='访问记录')
|
||||
put_html('<hr>')
|
||||
put_html('<h3>⭐Github</h3>')
|
||||
put_markdown('[TikTokDownloader_PyWebIO](https://github.com/Evil0ctal/TikTokDownloader_PyWebIO)')
|
||||
put_html('<hr>')
|
||||
put_html('<h3>🎯反馈</h3>')
|
||||
put_markdown('提交：[issues](https://github.com/Evil0ctal/TikTokDownloader_PyWebIO/issues)')
|
||||
put_html('<hr>')
|
||||
put_html('<h3>🌐视频/图集批量下载</h3>')
|
||||
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('<hr>')
|
||||
put_html('<h3>💖WeChat</h3>')
|
||||
put_markdown('微信：[Evil0ctal](https://mycyberpunk.com/)')
|
||||
put_html('<hr>')
|
||||
|
||||
|
||||
@config(title=title, description=description)
|
||||
def main():
|
||||
# 设置favicon
|
||||
favicon_url = "https://raw.githubusercontent.com/Evil0ctal/TikTokDownloader_PyWebIO/main/favicon/android-chrome-512x512.png"
|
||||
session.run_js("""
|
||||
$('#favicon32,#favicon16').remove();
|
||||
$('head').append('<link rel="icon" type="image/png" href="%s">')
|
||||
""" % favicon_url)
|
||||
# 修改footer
|
||||
session.run_js("""$('footer').remove()""")
|
||||
# 访问记录
|
||||
view_amount = requests.get("https://views.whatilearened.today/views/github/evil0ctal/TikTokDownload_PyWebIO.svg")
|
||||
put_markdown("""<div align='center' ><font size='20'>😼抖音/TikTok无水印在线解析</font></div>""")
|
||||
put_html('<hr>')
|
||||
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
|
||||
# 遍历链接
|
||||
for url in url_lists:
|
||||
if 'douyin.com' in url:
|
||||
if put_douyin_result(url) == 'failed':
|
||||
failed_count += 1
|
||||
continue
|
||||
else:
|
||||
success_count += 1
|
||||
else:
|
||||
if put_tiktok_result(url) == 'failed':
|
||||
failed_count += 1
|
||||
continue
|
||||
else:
|
||||
success_count += 1
|
||||
clear('bar')
|
||||
# 解析结束时间
|
||||
end = time.time()
|
||||
put_html("<br><hr>")
|
||||
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))
|
||||
put_link('返回主页', '/')
|
||||
|
||||
|
||||
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 = 5000
|
||||
app.run(host='0.0.0.0', port=port)
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user