mirror of
https://github.com/imgyh/tiktok.git
synced 2025-04-05 07:03:03 +08:00
feat(tiktok): 规范包目录结构
This commit is contained in:
imgyh
parent
3b1f9e7b5c
commit
942bc35912
376
DouYinCommand.py
Normal file
376
DouYinCommand.py
Normal file
@ -0,0 +1,376 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : DouYinCommand.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/12 16:01
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import sys
|
||||
import json
|
||||
import yaml
|
||||
import time
|
||||
|
||||
from apiproxy.douyin.douyin import Douyin
|
||||
from apiproxy.douyin.download import Download
|
||||
from apiproxy.douyin import douyin_headers
|
||||
from apiproxy.common import utils
|
||||
|
||||
configModel = {
|
||||
"link": [],
|
||||
"path": os.getcwd(),
|
||||
"music": True,
|
||||
"cover": True,
|
||||
"avatar": True,
|
||||
"json": True,
|
||||
"folderstyle": True,
|
||||
"mode": ["post"],
|
||||
"number": {
|
||||
"post": 0,
|
||||
"like": 0,
|
||||
"allmix": 0,
|
||||
"mix": 0,
|
||||
"music": 0,
|
||||
},
|
||||
'database': True,
|
||||
"increase": {
|
||||
"post": False,
|
||||
"like": False,
|
||||
"allmix": False,
|
||||
"mix": False,
|
||||
"music": False,
|
||||
},
|
||||
"thread": 5,
|
||||
"cookie": None
|
||||
|
||||
}
|
||||
|
||||
|
||||
def argument():
|
||||
parser = argparse.ArgumentParser(description='抖音批量下载工具 使用帮助')
|
||||
parser.add_argument("--cmd", "-C", help="使用命令行(True)或者配置文件(False), 默认为False",
|
||||
type=utils.str2bool, required=False, default=False)
|
||||
parser.add_argument("--link", "-l",
|
||||
help="作品(视频或图集)、直播、合集、音乐集合、个人主页的分享链接或者电脑浏览器网址, 可以设置多个链接(删除文案, 保证只有URL, https://v.douyin.com/kcvMpuN/ 或者 https://www.douyin.com/开头的)",
|
||||
type=str, required=False, default=[], action="append")
|
||||
parser.add_argument("--path", "-p", help="下载保存位置, 默认当前文件位置",
|
||||
type=str, required=False, default=os.getcwd())
|
||||
parser.add_argument("--music", "-m", help="是否下载视频中的音乐(True/False), 默认为True",
|
||||
type=utils.str2bool, required=False, default=True)
|
||||
parser.add_argument("--cover", "-c", help="是否下载视频的封面(True/False), 默认为True, 当下载视频时有效",
|
||||
type=utils.str2bool, required=False, default=True)
|
||||
parser.add_argument("--avatar", "-a", help="是否下载作者的头像(True/False), 默认为True",
|
||||
type=utils.str2bool, required=False, default=True)
|
||||
parser.add_argument("--json", "-j", help="是否保存获取到的数据(True/False), 默认为True",
|
||||
type=utils.str2bool, required=False, default=True)
|
||||
parser.add_argument("--folderstyle", "-fs", help="文件保存风格, 默认为True",
|
||||
type=utils.str2bool, required=False, default=True)
|
||||
parser.add_argument("--mode", "-M", help="link是个人主页时, 设置下载发布的作品(post)或喜欢的作品(like)或者用户所有合集(mix), 默认为post, 可以设置多种模式",
|
||||
type=str, required=False, default=[], action="append")
|
||||
parser.add_argument("--postnumber", help="主页下作品下载个数设置, 默认为0 全部下载",
|
||||
type=int, required=False, default=0)
|
||||
parser.add_argument("--likenumber", help="主页下喜欢下载个数设置, 默认为0 全部下载",
|
||||
type=int, required=False, default=0)
|
||||
parser.add_argument("--allmixnumber", help="主页下合集下载个数设置, 默认为0 全部下载",
|
||||
type=int, required=False, default=0)
|
||||
parser.add_argument("--mixnumber", help="单个合集下作品下载个数设置, 默认为0 全部下载",
|
||||
type=int, required=False, default=0)
|
||||
parser.add_argument("--musicnumber", help="音乐(原声)下作品下载个数设置, 默认为0 全部下载",
|
||||
type=int, required=False, default=0)
|
||||
parser.add_argument("--database", "-d", help="是否使用数据库, 默认为True 使用数据库; 如果不使用数据库, 增量更新不可用",
|
||||
type=utils.str2bool, required=False, default=True)
|
||||
parser.add_argument("--postincrease", help="是否开启主页作品增量下载(True/False), 默认为False",
|
||||
type=utils.str2bool, required=False, default=False)
|
||||
parser.add_argument("--likeincrease", help="是否开启主页喜欢增量下载(True/False), 默认为False",
|
||||
type=utils.str2bool, required=False, default=False)
|
||||
parser.add_argument("--allmixincrease", help="是否开启主页合集增量下载(True/False), 默认为False",
|
||||
type=utils.str2bool, required=False, default=False)
|
||||
parser.add_argument("--mixincrease", help="是否开启单个合集下作品增量下载(True/False), 默认为False",
|
||||
type=utils.str2bool, required=False, default=False)
|
||||
parser.add_argument("--musicincrease", help="是否开启音乐(原声)下作品增量下载(True/False), 默认为False",
|
||||
type=utils.str2bool, required=False, default=False)
|
||||
parser.add_argument("--thread", "-t",
|
||||
help="设置线程数, 默认5个线程",
|
||||
type=int, required=False, default=5)
|
||||
parser.add_argument("--cookie", help="设置cookie, 格式: \"name1=value1; name2=value2;\" 注意要加冒号",
|
||||
type=str, required=False, default='')
|
||||
args = parser.parse_args()
|
||||
if args.thread <= 0:
|
||||
args.thread = 5
|
||||
|
||||
return args
|
||||
|
||||
|
||||
def yamlConfig():
|
||||
curPath = os.path.dirname(os.path.realpath(sys.argv[0]))
|
||||
yamlPath = os.path.join(curPath, "config.yml")
|
||||
f = open(yamlPath, 'r', encoding='utf-8')
|
||||
cfg = f.read()
|
||||
configDict = yaml.load(stream=cfg, Loader=yaml.FullLoader)
|
||||
|
||||
try:
|
||||
if configDict["link"] != None:
|
||||
configModel["link"] = configDict["link"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:link未设置, 程序退出...\r\n")
|
||||
try:
|
||||
if configDict["path"] != None:
|
||||
configModel["path"] = configDict["path"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:path未设置, 使用当前路径...\r\n")
|
||||
try:
|
||||
if configDict["music"] != None:
|
||||
configModel["music"] = configDict["music"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:music未设置, 使用默认值True...\r\n")
|
||||
try:
|
||||
if configDict["cover"] != None:
|
||||
configModel["cover"] = configDict["cover"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:cover未设置, 使用默认值True...\r\n")
|
||||
try:
|
||||
if configDict["avatar"] != None:
|
||||
configModel["avatar"] = configDict["avatar"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:avatar未设置, 使用默认值True...\r\n")
|
||||
try:
|
||||
if configDict["json"] != None:
|
||||
configModel["json"] = configDict["json"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:json未设置, 使用默认值True...\r\n")
|
||||
try:
|
||||
if configDict["folderstyle"] != None:
|
||||
configModel["folderstyle"] = configDict["folderstyle"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:folderstyle未设置, 使用默认值True...\r\n")
|
||||
try:
|
||||
if configDict["mode"] != None:
|
||||
configModel["mode"] = configDict["mode"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:mode未设置, 使用默认值post...\r\n")
|
||||
try:
|
||||
if configDict["number"]["post"] != None:
|
||||
configModel["number"]["post"] = configDict["number"]["post"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:post number未设置, 使用默认值0...\r\n")
|
||||
try:
|
||||
if configDict["number"]["like"] != None:
|
||||
configModel["number"]["like"] = configDict["number"]["like"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:like number未设置, 使用默认值0...\r\n")
|
||||
try:
|
||||
if configDict["number"]["allmix"] != None:
|
||||
configModel["number"]["allmix"] = configDict["number"]["allmix"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:allmix number未设置, 使用默认值0...\r\n")
|
||||
try:
|
||||
if configDict["number"]["mix"] != None:
|
||||
configModel["number"]["mix"] = configDict["number"]["mix"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:mix number未设置, 使用默认值0...\r\n")
|
||||
try:
|
||||
if configDict["number"]["music"] != None:
|
||||
configModel["number"]["music"] = configDict["number"]["music"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:music number未设置, 使用默认值0...\r\n")
|
||||
try:
|
||||
if configDict["database"] != None:
|
||||
configModel["database"] = configDict["database"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:database未设置, 使用默认值False...\r\n")
|
||||
try:
|
||||
if configDict["increase"]["post"] != None:
|
||||
configModel["increase"]["post"] = configDict["increase"]["post"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:post 增量更新未设置, 使用默认值False...\r\n")
|
||||
try:
|
||||
if configDict["increase"]["like"] != None:
|
||||
configModel["increase"]["like"] = configDict["increase"]["like"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:like 增量更新未设置, 使用默认值False...\r\n")
|
||||
try:
|
||||
if configDict["increase"]["allmix"] != None:
|
||||
configModel["increase"]["allmix"] = configDict["increase"]["allmix"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:allmix 增量更新未设置, 使用默认值False...\r\n")
|
||||
try:
|
||||
if configDict["increase"]["mix"] != None:
|
||||
configModel["increase"]["mix"] = configDict["increase"]["mix"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:mix 增量更新未设置, 使用默认值False...\r\n")
|
||||
try:
|
||||
if configDict["increase"]["music"] != None:
|
||||
configModel["increase"]["music"] = configDict["increase"]["music"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:music 增量更新未设置, 使用默认值False...\r\n")
|
||||
try:
|
||||
if configDict["thread"] != None:
|
||||
configModel["thread"] = configDict["thread"]
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:thread未设置, 使用默认值5...\r\n")
|
||||
try:
|
||||
if configDict["cookies"] != None:
|
||||
cookiekey = configDict["cookies"].keys()
|
||||
cookieStr = ""
|
||||
for i in cookiekey:
|
||||
cookieStr = cookieStr + i + "=" + configDict["cookies"][i] + "; "
|
||||
configModel["cookie"] = cookieStr
|
||||
except Exception as e:
|
||||
pass
|
||||
try:
|
||||
if configDict["cookie"] != None:
|
||||
configModel["cookie"] = configDict["cookie"]
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
|
||||
def main():
|
||||
start = time.time() # 开始时间
|
||||
|
||||
args = argument()
|
||||
|
||||
if args.cmd:
|
||||
configModel["link"] = args.link
|
||||
configModel["path"] = args.path
|
||||
configModel["music"] = args.music
|
||||
configModel["cover"] = args.cover
|
||||
configModel["avatar"] = args.avatar
|
||||
configModel["json"] = args.json
|
||||
configModel["folderstyle"] = args.folderstyle
|
||||
if args.mode == None or args.mode == []:
|
||||
args.mode = []
|
||||
args.mode.append("post")
|
||||
configModel["mode"] = list(set(args.mode))
|
||||
configModel["number"]["post"] = args.postnumber
|
||||
configModel["number"]["like"] = args.likenumber
|
||||
configModel["number"]["allmix"] = args.allmixnumber
|
||||
configModel["number"]["mix"] = args.mixnumber
|
||||
configModel["number"]["music"] = args.musicnumber
|
||||
configModel["database"] = args.database
|
||||
configModel["increase"]["post"] = args.postincrease
|
||||
configModel["increase"]["like"] = args.likeincrease
|
||||
configModel["increase"]["allmix"] = args.allmixincrease
|
||||
configModel["increase"]["mix"] = args.mixincrease
|
||||
configModel["increase"]["music"] = args.musicincrease
|
||||
configModel["thread"] = args.thread
|
||||
configModel["cookie"] = args.cookie
|
||||
else:
|
||||
yamlConfig()
|
||||
|
||||
if configModel["link"] == []:
|
||||
return
|
||||
|
||||
if configModel["cookie"] is not None and configModel["cookie"] != "":
|
||||
douyin_headers["Cookie"] = configModel["cookie"]
|
||||
|
||||
configModel["path"] = os.path.abspath(configModel["path"])
|
||||
print("[ 提示 ]:数据保存路径 " + configModel["path"])
|
||||
if not os.path.exists(configModel["path"]):
|
||||
os.mkdir(configModel["path"])
|
||||
|
||||
dy = Douyin(database=configModel["database"])
|
||||
dl = Download(thread=configModel["thread"], music=configModel["music"], cover=configModel["cover"],
|
||||
avatar=configModel["avatar"], resjson=configModel["json"],
|
||||
folderstyle=configModel["folderstyle"])
|
||||
|
||||
for link in configModel["link"]:
|
||||
print("--------------------------------------------------------------------------------")
|
||||
print("[ 提示 ]:正在请求的链接: " + link + "\r\n")
|
||||
url = dy.getShareLink(link)
|
||||
key_type, key = dy.getKey(url)
|
||||
if key_type == "user":
|
||||
print("[ 提示 ]:正在请求用户主页下作品\r\n")
|
||||
data = dy.getUserDetailInfo(sec_uid=key)
|
||||
nickname = ""
|
||||
if data is not None and data != {}:
|
||||
nickname = utils.replaceStr(data['user']['nickname'])
|
||||
|
||||
userPath = os.path.join(configModel["path"], "user_" + nickname + "_" + key)
|
||||
if not os.path.exists(userPath):
|
||||
os.mkdir(userPath)
|
||||
|
||||
for mode in configModel["mode"]:
|
||||
print("--------------------------------------------------------------------------------")
|
||||
print("[ 提示 ]:正在请求用户主页模式: " + mode + "\r\n")
|
||||
if mode == 'post' or mode == 'like':
|
||||
datalist = dy.getUserInfo(key, mode, 35, configModel["number"][mode], configModel["increase"][mode])
|
||||
if datalist is not None and datalist != []:
|
||||
modePath = os.path.join(userPath, mode)
|
||||
if not os.path.exists(modePath):
|
||||
os.mkdir(modePath)
|
||||
dl.userDownload(awemeList=datalist, savePath=modePath)
|
||||
elif mode == 'mix':
|
||||
mixIdNameDict = dy.getUserAllMixInfo(key, 35, configModel["number"]["allmix"])
|
||||
if mixIdNameDict is not None and mixIdNameDict != {}:
|
||||
for mix_id in mixIdNameDict:
|
||||
print(f'[ 提示 ]:正在下载合集 [{mixIdNameDict[mix_id]}] 中的作品\r\n')
|
||||
mix_file_name = utils.replaceStr(mixIdNameDict[mix_id])
|
||||
datalist = dy.getMixInfo(mix_id, 35, 0, configModel["increase"]["allmix"], key)
|
||||
if datalist is not None and datalist != []:
|
||||
modePath = os.path.join(userPath, mode)
|
||||
if not os.path.exists(modePath):
|
||||
os.mkdir(modePath)
|
||||
dl.userDownload(awemeList=datalist, savePath=os.path.join(modePath, mix_file_name))
|
||||
print(f'[ 提示 ]:合集 [{mixIdNameDict[mix_id]}] 中的作品下载完成\r\n')
|
||||
elif key_type == "mix":
|
||||
print("[ 提示 ]:正在请求单个合集下作品\r\n")
|
||||
datalist = dy.getMixInfo(key, 35, configModel["number"]["mix"], configModel["increase"]["mix"], "")
|
||||
if datalist is not None and datalist != []:
|
||||
mixname = utils.replaceStr(datalist[0]["mix_info"]["mix_name"])
|
||||
mixPath = os.path.join(configModel["path"], "mix_" + mixname + "_" + key)
|
||||
if not os.path.exists(mixPath):
|
||||
os.mkdir(mixPath)
|
||||
dl.userDownload(awemeList=datalist, savePath=mixPath)
|
||||
elif key_type == "music":
|
||||
print("[ 提示 ]:正在请求音乐(原声)下作品\r\n")
|
||||
datalist = dy.getMusicInfo(key, 35, configModel["number"]["music"], configModel["increase"]["music"])
|
||||
|
||||
if datalist is not None and datalist != []:
|
||||
musicname = utils.replaceStr(datalist[0]["music"]["title"])
|
||||
musicPath = os.path.join(configModel["path"], "music_" + musicname + "_" + key)
|
||||
if not os.path.exists(musicPath):
|
||||
os.mkdir(musicPath)
|
||||
dl.userDownload(awemeList=datalist, savePath=musicPath)
|
||||
elif key_type == "aweme":
|
||||
print("[ 提示 ]:正在请求单个作品\r\n")
|
||||
datanew, dataraw = dy.getAwemeInfo(key)
|
||||
if datanew is not None and datanew != {}:
|
||||
datalist = []
|
||||
datalist.append(datanew)
|
||||
awemePath = os.path.join(configModel["path"], "aweme")
|
||||
if not os.path.exists(awemePath):
|
||||
os.mkdir(awemePath)
|
||||
dl.userDownload(awemeList=datalist, savePath=awemePath)
|
||||
elif key_type == "live":
|
||||
print("[ 提示 ]:正在进行直播解析\r\n")
|
||||
live_json = dy.getLiveInfo(key)
|
||||
if configModel["json"]:
|
||||
livePath = os.path.join(configModel["path"], "live")
|
||||
if not os.path.exists(livePath):
|
||||
os.mkdir(livePath)
|
||||
live_file_name = utils.replaceStr(key + live_json["nickname"])
|
||||
# 保存获取到json
|
||||
print("[ 提示 ]:正在保存获取到的信息到result.json\r\n")
|
||||
with open(os.path.join(livePath, live_file_name + ".json"), "w", encoding='utf-8') as f:
|
||||
f.write(json.dumps(live_json, ensure_ascii=False, indent=2))
|
||||
f.close()
|
||||
|
||||
end = time.time() # 结束时间
|
||||
print('\n' + '[下载完成]:总耗时: %d分钟%d秒\n' % (int((end - start) / 60), ((end - start) % 60))) # 输出下载用时时间
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
161
WebApi.py
Normal file
161
WebApi.py
Normal file
@ -0,0 +1,161 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : WebApi.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/12 18:52
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
|
||||
from flask import *
|
||||
from apiproxy.douyin.douyinapi import DouyinApi
|
||||
from apiproxy.douyin import douyin_headers
|
||||
import argparse
|
||||
|
||||
|
||||
def douyinwork(share_link, max_cursor, mode, cookie):
|
||||
dy = DouyinApi()
|
||||
|
||||
if cookie is not None and cookie != "":
|
||||
douyin_headers["Cookie"] = cookie
|
||||
|
||||
url = dy.getShareLink(share_link)
|
||||
key_type, key = dy.getKey(url)
|
||||
|
||||
data = None
|
||||
rawdata = None
|
||||
cursor = None
|
||||
has_more = None
|
||||
if key_type == "user":
|
||||
if mode == 'post' or mode == 'like':
|
||||
data, rawdata, cursor, has_more = dy.getUserInfoApi(sec_uid=key, mode=mode, count=35,
|
||||
max_cursor=max_cursor)
|
||||
elif mode == 'mix':
|
||||
data, rawdata, cursor, has_more = dy.getUserAllMixInfoApi(sec_uid=key, count=35, cursor=max_cursor)
|
||||
elif mode == 'detail':
|
||||
rawdata = dy.getUserDetailInfoApi(sec_uid=key)
|
||||
data = rawdata
|
||||
elif key_type == "mix":
|
||||
data, rawdata, cursor, has_more = dy.getMixInfoApi(mix_id=key, count=35, cursor=max_cursor)
|
||||
elif key_type == "music":
|
||||
data, rawdata, cursor, has_more = dy.getMusicInfoApi(music_id=key, count=35, cursor=max_cursor)
|
||||
elif key_type == "aweme":
|
||||
data, rawdata = dy.getAwemeInfoApi(aweme_id=key)
|
||||
elif key_type == "live":
|
||||
data, rawdata = dy.getLiveInfoApi(web_rid=key)
|
||||
|
||||
datadict = {}
|
||||
|
||||
if data is not None and data != []:
|
||||
datadict["data"] = data
|
||||
datadict["rawdata"] = rawdata
|
||||
datadict["cursor"] = cursor
|
||||
datadict["has_more"] = has_more
|
||||
datadict["status_code"] = 200
|
||||
else:
|
||||
datadict["status_code"] = 500
|
||||
return datadict
|
||||
|
||||
|
||||
def deal(mode=None):
|
||||
usefuldict = {}
|
||||
if request.headers.get("content_type") == "application/json":
|
||||
result = request.get_json(force=True)
|
||||
else:
|
||||
result = request.form
|
||||
|
||||
share_link = None
|
||||
cursor = 0
|
||||
cookie = None
|
||||
|
||||
try:
|
||||
share_link = result["share_link"]
|
||||
cursor = result["cursor"]
|
||||
cookie = result["cookie"]
|
||||
except Exception as e:
|
||||
usefuldict["status_code"] = 500
|
||||
|
||||
try:
|
||||
if share_link is not None and share_link != "":
|
||||
usefuldict = douyinwork(share_link, cursor, mode, cookie)
|
||||
usefuldict["status_code"] = 200
|
||||
except Exception as e:
|
||||
usefuldict["status_code"] = 500
|
||||
return jsonify(usefuldict)
|
||||
|
||||
|
||||
app = Flask(__name__)
|
||||
# 设置编码
|
||||
app.config['JSON_AS_ASCII'] = False
|
||||
|
||||
|
||||
def argument():
|
||||
parser = argparse.ArgumentParser(description='抖音去水印工具 使用帮助')
|
||||
parser.add_argument("--port", "-p", help="Web端口",
|
||||
type=int, required=False, default=5000)
|
||||
args = parser.parse_args()
|
||||
|
||||
return args
|
||||
|
||||
|
||||
@app.route("/douyin/music", methods=["POST"])
|
||||
def douyinMusic():
|
||||
return deal()
|
||||
|
||||
|
||||
@app.route("/douyin/mix", methods=["POST"])
|
||||
def douyinMix():
|
||||
return deal()
|
||||
|
||||
|
||||
@app.route("/douyin/user/mix", methods=["POST"])
|
||||
def douyinUserMix():
|
||||
return deal(mode="mix")
|
||||
|
||||
|
||||
@app.route("/douyin/user/like", methods=["POST"])
|
||||
def douyinUserLike():
|
||||
return deal(mode="like")
|
||||
|
||||
|
||||
@app.route("/douyin/user/post", methods=["POST"])
|
||||
def douyinUserPost():
|
||||
return deal(mode="post")
|
||||
|
||||
@app.route("/douyin/user/detail", methods=["POST"])
|
||||
def douyinUserDetail():
|
||||
return deal(mode="detail")
|
||||
|
||||
@app.route("/douyin/aweme", methods=["POST"])
|
||||
def douyinAweme():
|
||||
return deal()
|
||||
|
||||
|
||||
@app.route("/douyin/live", methods=["POST"])
|
||||
def douyinLive():
|
||||
return deal()
|
||||
|
||||
|
||||
@app.route("/douyin", methods=["POST"])
|
||||
def douyin():
|
||||
return deal()
|
||||
|
||||
|
||||
@app.route("/", methods=["GET"])
|
||||
def index():
|
||||
return render_template("index.html")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
args = argument()
|
||||
app.run(debug=False, host="0.0.0.0", port=args.port)
|
||||
20
apiproxy/__init__.py
Normal file
20
apiproxy/__init__.py
Normal file
@ -0,0 +1,20 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : __init__.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/12 14:32
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
|
||||
ua = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36'
|
||||
21
apiproxy/common/__init__.py
Normal file
21
apiproxy/common/__init__.py
Normal file
@ -0,0 +1,21 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : __init__.py.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/12 16:10
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
from .utils import Utils
|
||||
|
||||
utils = Utils()
|
||||
201
apiproxy/common/utils.py
Normal file
201
apiproxy/common/utils.py
Normal file
@ -0,0 +1,201 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : utils.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/12 15:18
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
|
||||
import random
|
||||
import requests
|
||||
import re
|
||||
import os
|
||||
import sys
|
||||
import hashlib
|
||||
import base64
|
||||
import time
|
||||
|
||||
import apiproxy
|
||||
|
||||
|
||||
class Utils(object):
|
||||
def __init__(self):
|
||||
pass
|
||||
|
||||
def replaceStr(self, filenamestr: str):
|
||||
"""
|
||||
替换非法字符，缩短字符长度，使其能成为文件名
|
||||
"""
|
||||
# 匹配 汉字 字母 数字 空格
|
||||
match = "([0-9A-Za-z\u4e00-\u9fa5]+)"
|
||||
|
||||
result = re.findall(match, filenamestr)
|
||||
|
||||
result = "".join(result).strip()
|
||||
if len(result) > 20:
|
||||
result = result[:20]
|
||||
# 去除前后空格
|
||||
return result
|
||||
|
||||
def resource_path(self, relative_path):
|
||||
if getattr(sys, 'frozen', False): # 是否Bundle Resource
|
||||
base_path = sys._MEIPASS
|
||||
else:
|
||||
base_path = os.path.dirname(os.path.abspath(__file__))
|
||||
return os.path.join(base_path, relative_path)
|
||||
|
||||
def str2bool(self, v):
|
||||
if isinstance(v, bool):
|
||||
return v
|
||||
if v.lower() in ('yes', 'true', 't', 'y', '1'):
|
||||
return True
|
||||
elif v.lower() in ('no', 'false', 'f', 'n', '0'):
|
||||
return False
|
||||
else:
|
||||
return True
|
||||
|
||||
def generate_random_str(self, randomlength=16):
|
||||
"""
|
||||
根据传入长度产生随机字符串
|
||||
"""
|
||||
random_str = ''
|
||||
base_str = 'ABCDEFGHIGKLMNOPQRSTUVWXYZabcdefghigklmnopqrstuvwxyz0123456789='
|
||||
length = len(base_str) - 1
|
||||
for _ in range(randomlength):
|
||||
random_str += base_str[random.randint(0, length)]
|
||||
return random_str
|
||||
|
||||
# https://www.52pojie.cn/thread-1589242-1-1.html
|
||||
def getttwid(self):
|
||||
url = 'https://ttwid.bytedance.com/ttwid/union/register/'
|
||||
data = '{"region":"cn","aid":1768,"needFid":false,"service":"www.ixigua.com","migrate_info":{"ticket":"","source":"node"},"cbUrlProtocol":"https","union":true}'
|
||||
res = requests.post(url=url, data=data)
|
||||
|
||||
for i, j in res.cookies.items():
|
||||
return j
|
||||
|
||||
def getXbogus(self, payload, form='', ua=apiproxy.ua):
|
||||
xbogus = self.get_xbogus(payload, ua, form)
|
||||
params = payload + "&X-Bogus=" + xbogus
|
||||
return params
|
||||
|
||||
def get_xbogus(self, payload, ua, form):
|
||||
short_str = "Dkdpgh4ZKsQB80/Mfvw36XI1R25-WUAlEi7NLboqYTOPuzmFjJnryx9HVGcaStCe="
|
||||
arr2 = self.get_arr2(payload, ua, form)
|
||||
|
||||
garbled_string = self.get_garbled_string(arr2)
|
||||
|
||||
xbogus = ""
|
||||
|
||||
for i in range(0, 21, 3):
|
||||
char_code_num0 = garbled_string[i]
|
||||
char_code_num1 = garbled_string[i + 1]
|
||||
char_code_num2 = garbled_string[i + 2]
|
||||
base_num = char_code_num2 | char_code_num1 << 8 | char_code_num0 << 16
|
||||
str1 = short_str[(base_num & 16515072) >> 18]
|
||||
str2 = short_str[(base_num & 258048) >> 12]
|
||||
str3 = short_str[(base_num & 4032) >> 6]
|
||||
str4 = short_str[base_num & 63]
|
||||
xbogus += str1 + str2 + str3 + str4
|
||||
|
||||
return xbogus
|
||||
|
||||
def get_garbled_string(self, arr2):
|
||||
p = [
|
||||
arr2[0], arr2[10], arr2[1], arr2[11], arr2[2], arr2[12], arr2[3], arr2[13], arr2[4], arr2[14],
|
||||
arr2[5], arr2[15], arr2[6], arr2[16], arr2[7], arr2[17], arr2[8], arr2[18], arr2[9]
|
||||
]
|
||||
|
||||
char_array = [chr(i) for i in p]
|
||||
f = []
|
||||
f.extend([2, 255])
|
||||
tmp = ['ÿ']
|
||||
bytes_ = self._0x30492c(tmp, "".join(char_array))
|
||||
|
||||
for i in range(len(bytes_)):
|
||||
f.append(bytes_[i])
|
||||
|
||||
return f
|
||||
|
||||
def get_arr2(self, payload, ua, form):
|
||||
salt_payload_bytes = hashlib.md5(hashlib.md5(payload.encode()).digest()).digest()
|
||||
salt_payload = [byte for byte in salt_payload_bytes]
|
||||
|
||||
salt_form_bytes = hashlib.md5(hashlib.md5(form.encode()).digest()).digest()
|
||||
salt_form = [byte for byte in salt_form_bytes]
|
||||
|
||||
ua_key = ['\u0000', '\u0001', '\u000e']
|
||||
salt_ua_bytes = hashlib.md5(base64.b64encode(self._0x30492c(ua_key, ua))).digest()
|
||||
salt_ua = [byte for byte in salt_ua_bytes]
|
||||
|
||||
timestamp = int(time.time())
|
||||
canvas = 1489154074
|
||||
|
||||
arr1 = [
|
||||
64, # 固定
|
||||
0, # 固定
|
||||
1, # 固定
|
||||
14, # 固定 这个还要再看一下，14,12,0都出现过
|
||||
salt_payload[14], # payload 相关
|
||||
salt_payload[15],
|
||||
salt_form[14], # form 相关
|
||||
salt_form[15],
|
||||
salt_ua[14], # ua 相关
|
||||
salt_ua[15],
|
||||
(timestamp >> 24) & 255,
|
||||
(timestamp >> 16) & 255,
|
||||
(timestamp >> 8) & 255,
|
||||
(timestamp >> 0) & 255,
|
||||
(canvas >> 24) & 255,
|
||||
(canvas >> 16) & 255,
|
||||
(canvas >> 8) & 255,
|
||||
(canvas >> 0) & 255,
|
||||
64, # 校验位
|
||||
]
|
||||
|
||||
for i in range(1, len(arr1) - 1):
|
||||
arr1[18] ^= arr1[i]
|
||||
|
||||
arr2 = [arr1[0], arr1[2], arr1[4], arr1[6], arr1[8], arr1[10], arr1[12], arr1[14], arr1[16], arr1[18], arr1[1],
|
||||
arr1[3], arr1[5], arr1[7], arr1[9], arr1[11], arr1[13], arr1[15], arr1[17]]
|
||||
|
||||
return arr2
|
||||
|
||||
def _0x30492c(self, a, b):
|
||||
d = [i for i in range(256)]
|
||||
c = 0
|
||||
result = bytearray(len(b))
|
||||
|
||||
for i in range(256):
|
||||
c = (c + d[i] + ord(a[i % len(a)])) % 256
|
||||
e = d[i]
|
||||
d[i] = d[c]
|
||||
d[c] = e
|
||||
|
||||
t = 0
|
||||
c = 0
|
||||
|
||||
for i in range(len(b)):
|
||||
t = (t + 1) % 256
|
||||
c = (c + d[t]) % 256
|
||||
e = d[t]
|
||||
d[t] = d[c]
|
||||
d[c] = e
|
||||
result[i] = ord(b[i]) ^ d[(d[t] + d[c]) % 256]
|
||||
|
||||
return result
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
pass
|
||||
27
apiproxy/douyin/__init__.py
Normal file
27
apiproxy/douyin/__init__.py
Normal file
@ -0,0 +1,27 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : __init__.py.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/12 14:44
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
import apiproxy
|
||||
from apiproxy.common import utils
|
||||
|
||||
douyin_headers = {
|
||||
'User-Agent': apiproxy.ua,
|
||||
'referer': 'https://www.douyin.com/',
|
||||
'accept-encoding': None,
|
||||
'Cookie': f"msToken={utils.generate_random_str(107)}; ttwid={utils.getttwid()}; odin_tt=324fb4ea4a89c0c05827e18a1ed9cf9bf8a17f7705fcc793fec935b637867e2a5a9b8168c885554d029919117a18ba69; passport_csrf_token=f61602fc63757ae0e4fd9d6bdcee4810;"
|
||||
}
|
||||
172
apiproxy/douyin/database.py
Normal file
172
apiproxy/douyin/database.py
Normal file
@ -0,0 +1,172 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : database.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/12 15:15
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
|
||||
import sqlite3
|
||||
import json
|
||||
|
||||
|
||||
class DataBase(object):
|
||||
def __init__(self):
|
||||
self.conn = sqlite3.connect('data.db')
|
||||
self.cursor = self.conn.cursor()
|
||||
self.create_user_post_table()
|
||||
self.create_user_like_table()
|
||||
self.create_mix_table()
|
||||
self.create_music_table()
|
||||
|
||||
def create_user_post_table(self):
|
||||
sql = """CREATE TABLE if not exists t_user_post (
|
||||
id integer primary key autoincrement,
|
||||
sec_uid varchar(200),
|
||||
aweme_id integer unique,
|
||||
rawdata json
|
||||
);"""
|
||||
|
||||
try:
|
||||
self.cursor.execute(sql)
|
||||
self.conn.commit()
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def get_user_post(self, sec_uid: str, aweme_id: int):
|
||||
sql = """select id, sec_uid, aweme_id, rawdata from t_user_post where sec_uid=? and aweme_id=?;"""
|
||||
|
||||
try:
|
||||
self.cursor.execute(sql, (sec_uid, aweme_id))
|
||||
self.conn.commit()
|
||||
res = self.cursor.fetchone()
|
||||
return res
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def insert_user_post(self, sec_uid: str, aweme_id: int, data: dict):
|
||||
insertsql = """insert into t_user_post (sec_uid, aweme_id, rawdata) values(?,?,?);"""
|
||||
|
||||
try:
|
||||
self.cursor.execute(insertsql, (sec_uid, aweme_id, json.dumps(data)))
|
||||
self.conn.commit()
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def create_user_like_table(self):
|
||||
sql = """CREATE TABLE if not exists t_user_like (
|
||||
id integer primary key autoincrement,
|
||||
sec_uid varchar(200),
|
||||
aweme_id integer unique,
|
||||
rawdata json
|
||||
);"""
|
||||
|
||||
try:
|
||||
self.cursor.execute(sql)
|
||||
self.conn.commit()
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def get_user_like(self, sec_uid: str, aweme_id: int):
|
||||
sql = """select id, sec_uid, aweme_id, rawdata from t_user_like where sec_uid=? and aweme_id=?;"""
|
||||
|
||||
try:
|
||||
self.cursor.execute(sql, (sec_uid, aweme_id))
|
||||
self.conn.commit()
|
||||
res = self.cursor.fetchone()
|
||||
return res
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def insert_user_like(self, sec_uid: str, aweme_id: int, data: dict):
|
||||
insertsql = """insert into t_user_like (sec_uid, aweme_id, rawdata) values(?,?,?);"""
|
||||
|
||||
try:
|
||||
self.cursor.execute(insertsql, (sec_uid, aweme_id, json.dumps(data)))
|
||||
self.conn.commit()
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def create_mix_table(self):
|
||||
sql = """CREATE TABLE if not exists t_mix (
|
||||
id integer primary key autoincrement,
|
||||
sec_uid varchar(200),
|
||||
mix_id varchar(200),
|
||||
aweme_id integer,
|
||||
rawdata json
|
||||
);"""
|
||||
|
||||
try:
|
||||
self.cursor.execute(sql)
|
||||
self.conn.commit()
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def get_mix(self, sec_uid: str, mix_id: str, aweme_id: int):
|
||||
sql = """select id, sec_uid, mix_id, aweme_id, rawdata from t_mix where sec_uid=? and mix_id=? and aweme_id=?;"""
|
||||
|
||||
try:
|
||||
self.cursor.execute(sql, (sec_uid, mix_id, aweme_id))
|
||||
self.conn.commit()
|
||||
res = self.cursor.fetchone()
|
||||
return res
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def insert_mix(self, sec_uid: str, mix_id: str, aweme_id: int, data: dict):
|
||||
insertsql = """insert into t_mix (sec_uid, mix_id, aweme_id, rawdata) values(?,?,?,?);"""
|
||||
|
||||
try:
|
||||
self.cursor.execute(insertsql, (sec_uid, mix_id, aweme_id, json.dumps(data)))
|
||||
self.conn.commit()
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def create_music_table(self):
|
||||
sql = """CREATE TABLE if not exists t_music (
|
||||
id integer primary key autoincrement,
|
||||
music_id varchar(200),
|
||||
aweme_id integer unique,
|
||||
rawdata json
|
||||
);"""
|
||||
|
||||
try:
|
||||
self.cursor.execute(sql)
|
||||
self.conn.commit()
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def get_music(self, music_id: str, aweme_id: int):
|
||||
sql = """select id, music_id, aweme_id, rawdata from t_music where music_id=? and aweme_id=?;"""
|
||||
|
||||
try:
|
||||
self.cursor.execute(sql, (music_id, aweme_id))
|
||||
self.conn.commit()
|
||||
res = self.cursor.fetchone()
|
||||
return res
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def insert_music(self, music_id: str, aweme_id: int, data: dict):
|
||||
insertsql = """insert into t_music (music_id, aweme_id, rawdata) values(?,?,?);"""
|
||||
|
||||
try:
|
||||
self.cursor.execute(insertsql, (music_id, aweme_id, json.dumps(data)))
|
||||
self.conn.commit()
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
pass
|
||||
688
apiproxy/douyin/douyin.py
Normal file
688
apiproxy/douyin/douyin.py
Normal file
@ -0,0 +1,688 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : douyin.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/12 14:52
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
|
||||
import re
|
||||
import requests
|
||||
import json
|
||||
import time
|
||||
import copy
|
||||
|
||||
from apiproxy.douyin import douyin_headers
|
||||
from apiproxy.douyin.urls import Urls
|
||||
from apiproxy.douyin.result import Result
|
||||
from apiproxy.douyin.database import DataBase
|
||||
from apiproxy.common import utils
|
||||
|
||||
|
||||
class Douyin(object):
|
||||
|
||||
def __init__(self, database=False):
|
||||
self.urls = Urls()
|
||||
self.result = Result()
|
||||
self.database = database
|
||||
if database:
|
||||
self.db = DataBase()
|
||||
# 用于设置重复请求某个接口的最大时间
|
||||
self.timeout = 10
|
||||
|
||||
# 从分享链接中提取网址
|
||||
def getShareLink(self, string):
|
||||
# findall() 查找匹配正则表达式的字符串
|
||||
return re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', string)[0]
|
||||
|
||||
# 得到 作品id 或者 用户id
|
||||
# 传入 url 支持 https://www.iesdouyin.com 与 https://v.douyin.com
|
||||
def getKey(self, url):
|
||||
key = None
|
||||
key_type = None
|
||||
|
||||
try:
|
||||
r = requests.get(url=url, headers=douyin_headers)
|
||||
except Exception as e:
|
||||
print('[ 错误 ]:输入链接有误！\r')
|
||||
return key_type, key
|
||||
|
||||
# 抖音把图集更新为note
|
||||
# 作品 第一步解析出来的链接是share/video/{aweme_id}
|
||||
# https://www.iesdouyin.com/share/video/7037827546599263488/?region=CN&mid=6939809470193126152&u_code=j8a5173b&did=MS4wLjABAAAA1DICF9-A9M_CiGqAJZdsnig5TInVeIyPdc2QQdGrq58xUgD2w6BqCHovtqdIDs2i&iid=MS4wLjABAAAAomGWi4n2T0H9Ab9x96cUZoJXaILk4qXOJlJMZFiK6b_aJbuHkjN_f0mBzfy91DX1&with_sec_did=1&titleType=title&schema_type=37&from_ssr=1&utm_source=copy&utm_campaign=client_share&utm_medium=android&app=aweme
|
||||
# 用户 第一步解析出来的链接是share/user/{sec_uid}
|
||||
# https://www.iesdouyin.com/share/user/MS4wLjABAAAA06y3Ctu8QmuefqvUSU7vr0c_ZQnCqB0eaglgkelLTek?did=MS4wLjABAAAA1DICF9-A9M_CiGqAJZdsnig5TInVeIyPdc2QQdGrq58xUgD2w6BqCHovtqdIDs2i&iid=MS4wLjABAAAAomGWi4n2T0H9Ab9x96cUZoJXaILk4qXOJlJMZFiK6b_aJbuHkjN_f0mBzfy91DX1&with_sec_did=1&sec_uid=MS4wLjABAAAA06y3Ctu8QmuefqvUSU7vr0c_ZQnCqB0eaglgkelLTek&from_ssr=1&u_code=j8a5173b×tamp=1674540164&ecom_share_track_params=%7B%22is_ec_shopping%22%3A%221%22%2C%22secuid%22%3A%22MS4wLjABAAAA-jD2lukp--I21BF8VQsmYUqJDbj3FmU-kGQTHl2y1Cw%22%2C%22enter_from%22%3A%22others_homepage%22%2C%22share_previous_page%22%3A%22others_homepage%22%7D&utm_source=copy&utm_campaign=client_share&utm_medium=android&app=aweme
|
||||
# 合集
|
||||
# https://www.douyin.com/collection/7093490319085307918
|
||||
urlstr = str(r.request.path_url)
|
||||
|
||||
if "/user/" in urlstr:
|
||||
# 获取用户 sec_uid
|
||||
if '?' in r.request.path_url:
|
||||
for one in re.finditer(r'user\/([\d\D]*)([?])', str(r.request.path_url)):
|
||||
key = one.group(1)
|
||||
else:
|
||||
for one in re.finditer(r'user\/([\d\D]*)', str(r.request.path_url)):
|
||||
key = one.group(1)
|
||||
key_type = "user"
|
||||
elif "/video/" in urlstr:
|
||||
# 获取作品 aweme_id
|
||||
key = re.findall('video/(\d+)?', urlstr)[0]
|
||||
key_type = "aweme"
|
||||
elif "/note/" in urlstr:
|
||||
# 获取note aweme_id
|
||||
key = re.findall('note/(\d+)?', urlstr)[0]
|
||||
key_type = "aweme"
|
||||
elif "/mix/detail/" in urlstr:
|
||||
# 获取合集 id
|
||||
key = re.findall('/mix/detail/(\d+)?', urlstr)[0]
|
||||
key_type = "mix"
|
||||
elif "/collection/" in urlstr:
|
||||
# 获取合集 id
|
||||
key = re.findall('/collection/(\d+)?', urlstr)[0]
|
||||
key_type = "mix"
|
||||
elif "/music/" in urlstr:
|
||||
# 获取原声 id
|
||||
key = re.findall('music/(\d+)?', urlstr)[0]
|
||||
key_type = "music"
|
||||
elif "/webcast/reflow/" in urlstr:
|
||||
key1 = re.findall('reflow/(\d+)?', urlstr)[0]
|
||||
url = self.urls.LIVE2 + utils.getXbogus(
|
||||
f'live_id=1&room_id={key1}&app_id=1128')
|
||||
res = requests.get(url, headers=douyin_headers)
|
||||
resjson = json.loads(res.text)
|
||||
key = resjson['data']['room']['owner']['web_rid']
|
||||
key_type = "live"
|
||||
elif "live.douyin.com" in r.url:
|
||||
key = r.url.replace('https://live.douyin.com/', '')
|
||||
key_type = "live"
|
||||
|
||||
if key is None or key_type is None:
|
||||
print('[ 错误 ]:输入链接有误！无法获取 id\r')
|
||||
return key_type, key
|
||||
|
||||
return key_type, key
|
||||
|
||||
# 传入 aweme_id
|
||||
# 返回 数据 字典
|
||||
def getAwemeInfo(self, aweme_id):
|
||||
print('[ 提示 ]:正在请求的作品 id = %s\r' % aweme_id)
|
||||
if aweme_id is None:
|
||||
return None
|
||||
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
|
||||
try:
|
||||
# 单作品接口返回 'aweme_detail'
|
||||
# 主页作品接口返回 'aweme_list'->['aweme_detail']
|
||||
jx_url = self.urls.POST_DETAIL + utils.getXbogus(
|
||||
f'aweme_id={aweme_id}&device_platform=webapp&aid=6383')
|
||||
|
||||
raw = requests.get(url=jx_url, headers=douyin_headers).text
|
||||
datadict = json.loads(raw)
|
||||
if datadict is not None and datadict["status_code"] == 0:
|
||||
break
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
|
||||
return {}, {}
|
||||
|
||||
|
||||
# 清空self.awemeDict
|
||||
self.result.clearDict(self.result.awemeDict)
|
||||
|
||||
# 默认为视频
|
||||
awemeType = 0
|
||||
try:
|
||||
# datadict['aweme_detail']["images"] 不为 None 说明是图集
|
||||
if datadict['aweme_detail']["images"] is not None:
|
||||
awemeType = 1
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:接口中未找到 images\r")
|
||||
|
||||
# 转换成我们自己的格式
|
||||
self.result.dataConvert(awemeType, self.result.awemeDict, datadict['aweme_detail'])
|
||||
|
||||
return self.result.awemeDict, datadict
|
||||
|
||||
# 传入 url 支持 https://www.iesdouyin.com 与 https://v.douyin.com
|
||||
# mode : post | like 模式选择 like为用户点赞 post为用户发布
|
||||
def getUserInfo(self, sec_uid, mode="post", count=35, number=0, increase=False):
|
||||
print('[ 提示 ]:正在请求的用户 id = %s\r\n' % sec_uid)
|
||||
if sec_uid is None:
|
||||
return None
|
||||
if number <= 0:
|
||||
numflag = False
|
||||
else:
|
||||
numflag = True
|
||||
|
||||
max_cursor = 0
|
||||
awemeList = []
|
||||
increaseflag = False
|
||||
numberis0 = False
|
||||
|
||||
print("[ 提示 ]:正在获取所有作品数据请稍后...\r")
|
||||
print("[ 提示 ]:会进行多次请求，等待时间较长...\r\n")
|
||||
times = 0
|
||||
while True:
|
||||
times = times + 1
|
||||
print("[ 提示 ]:正在对 [主页] 进行第 " + str(times) + " 次请求...\r")
|
||||
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
|
||||
try:
|
||||
if mode == "post":
|
||||
url = self.urls.USER_POST + utils.getXbogus(
|
||||
f'sec_user_id={sec_uid}&count={count}&max_cursor={max_cursor}&device_platform=webapp&aid=6383')
|
||||
elif mode == "like":
|
||||
url = self.urls.USER_FAVORITE_A + utils.getXbogus(
|
||||
f'sec_user_id={sec_uid}&count={count}&max_cursor={max_cursor}&device_platform=webapp&aid=6383')
|
||||
else:
|
||||
print("[ 错误 ]:模式选择错误, 仅支持post、like、mix, 请检查后重新运行!\r")
|
||||
return None
|
||||
|
||||
res = requests.get(url=url, headers=douyin_headers)
|
||||
datadict = json.loads(res.text)
|
||||
print('[ 提示 ]:本次请求返回 ' + str(len(datadict["aweme_list"])) + ' 条数据\r')
|
||||
|
||||
if datadict is not None and datadict["status_code"] == 0:
|
||||
break
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
|
||||
return awemeList
|
||||
|
||||
|
||||
for aweme in datadict["aweme_list"]:
|
||||
if self.database:
|
||||
# 退出条件
|
||||
if increase is False and numflag and numberis0:
|
||||
break
|
||||
if increase and numflag and numberis0 and increaseflag:
|
||||
break
|
||||
# 增量更新, 找到非置顶的最新的作品发布时间
|
||||
if mode == "post":
|
||||
if self.db.get_user_post(sec_uid=sec_uid, aweme_id=aweme['aweme_id']) is not None:
|
||||
if increase and aweme['is_top'] == 0:
|
||||
increaseflag = True
|
||||
else:
|
||||
self.db.insert_user_post(sec_uid=sec_uid, aweme_id=aweme['aweme_id'], data=aweme)
|
||||
elif mode == "like":
|
||||
if self.db.get_user_like(sec_uid=sec_uid, aweme_id=aweme['aweme_id']) is not None:
|
||||
if increase and aweme['is_top'] == 0:
|
||||
increaseflag = True
|
||||
else:
|
||||
self.db.insert_user_like(sec_uid=sec_uid, aweme_id=aweme['aweme_id'], data=aweme)
|
||||
|
||||
# 退出条件
|
||||
if increase and numflag is False and increaseflag:
|
||||
break
|
||||
if increase and numflag and numberis0 and increaseflag:
|
||||
break
|
||||
else:
|
||||
if numflag and numberis0:
|
||||
break
|
||||
|
||||
if numflag:
|
||||
number -= 1
|
||||
if number == 0:
|
||||
numberis0 = True
|
||||
|
||||
# 清空self.awemeDict
|
||||
self.result.clearDict(self.result.awemeDict)
|
||||
|
||||
# 默认为视频
|
||||
awemeType = 0
|
||||
try:
|
||||
if aweme["images"] is not None:
|
||||
awemeType = 1
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:接口中未找到 images\r")
|
||||
|
||||
# 转换成我们自己的格式
|
||||
self.result.dataConvert(awemeType, self.result.awemeDict, aweme)
|
||||
|
||||
if self.result.awemeDict is not None and self.result.awemeDict != {}:
|
||||
awemeList.append(copy.deepcopy(self.result.awemeDict))
|
||||
|
||||
if self.database:
|
||||
if increase and numflag is False and increaseflag:
|
||||
print("\r\n[ 提示 ]: [主页] 下作品增量更新数据获取完成...\r\n")
|
||||
break
|
||||
elif increase is False and numflag and numberis0:
|
||||
print("\r\n[ 提示 ]: [主页] 下指定数量作品数据获取完成...\r\n")
|
||||
break
|
||||
elif increase and numflag and numberis0 and increaseflag:
|
||||
print("\r\n[ 提示 ]: [主页] 下指定数量作品数据获取完成, 增量更新数据获取完成...\r\n")
|
||||
break
|
||||
else:
|
||||
if numflag and numberis0:
|
||||
print("\r\n[ 提示 ]: [主页] 下指定数量作品数据获取完成...\r\n")
|
||||
break
|
||||
|
||||
# 更新 max_cursor
|
||||
max_cursor = datadict["max_cursor"]
|
||||
|
||||
# 退出条件
|
||||
if datadict["has_more"] == 0 or datadict["has_more"] == False:
|
||||
print("\r\n[ 提示 ]: [主页] 下所有作品数据获取完成...\r\n")
|
||||
break
|
||||
else:
|
||||
print("\r\n[ 提示 ]:[主页] 第 " + str(times) + " 次请求成功...\r\n")
|
||||
|
||||
return awemeList
|
||||
|
||||
def getLiveInfo(self, web_rid: str):
|
||||
print('[ 提示 ]:正在请求的直播间 id = %s\r\n' % web_rid)
|
||||
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
|
||||
try:
|
||||
live_api = self.urls.LIVE + utils.getXbogus(
|
||||
f'aid=6383&device_platform=web&web_rid={web_rid}')
|
||||
|
||||
response = requests.get(live_api, headers=douyin_headers)
|
||||
live_json = json.loads(response.text)
|
||||
if live_json != {} and live_json['status_code'] == 0:
|
||||
break
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
|
||||
return {}
|
||||
|
||||
# 清空字典
|
||||
self.result.clearDict(self.result.liveDict)
|
||||
|
||||
# 类型
|
||||
self.result.liveDict["awemeType"] = 2
|
||||
# 是否在播
|
||||
self.result.liveDict["status"] = live_json['data']['data'][0]['status']
|
||||
|
||||
if self.result.liveDict["status"] == 4:
|
||||
print('[ 📺 ]:当前直播已结束，正在退出')
|
||||
return self.result.liveDict
|
||||
|
||||
# 直播标题
|
||||
self.result.liveDict["title"] = live_json['data']['data'][0]['title']
|
||||
|
||||
# 直播cover
|
||||
self.result.liveDict["cover"] = live_json['data']['data'][0]['cover']['url_list'][0]
|
||||
|
||||
# 头像
|
||||
self.result.liveDict["avatar"] = live_json['data']['data'][0]['owner']['avatar_thumb']['url_list'][0].replace(
|
||||
"100x100", "1080x1080")
|
||||
|
||||
# 观看人数
|
||||
self.result.liveDict["user_count"] = live_json['data']['data'][0]['user_count_str']
|
||||
|
||||
# 昵称
|
||||
self.result.liveDict["nickname"] = live_json['data']['data'][0]['owner']['nickname']
|
||||
|
||||
# sec_uid
|
||||
self.result.liveDict["sec_uid"] = live_json['data']['data'][0]['owner']['sec_uid']
|
||||
|
||||
# 直播间观看状态
|
||||
self.result.liveDict["display_long"] = live_json['data']['data'][0]['room_view_stats']['display_long']
|
||||
|
||||
# 推流
|
||||
self.result.liveDict["flv_pull_url"] = live_json['data']['data'][0]['stream_url']['flv_pull_url']
|
||||
|
||||
try:
|
||||
# 分区
|
||||
self.result.liveDict["partition"] = live_json['data']['partition_road_map']['partition']['title']
|
||||
self.result.liveDict["sub_partition"] = \
|
||||
live_json['data']['partition_road_map']['sub_partition']['partition']['title']
|
||||
except Exception as e:
|
||||
self.result.liveDict["partition"] = '无'
|
||||
self.result.liveDict["sub_partition"] = '无'
|
||||
|
||||
info = '[ 💻 ]:直播间：%s 当前%s 主播：%s 分区：%s-%s\r' % (
|
||||
self.result.liveDict["title"], self.result.liveDict["display_long"], self.result.liveDict["nickname"],
|
||||
self.result.liveDict["partition"], self.result.liveDict["sub_partition"])
|
||||
print(info)
|
||||
|
||||
flv = []
|
||||
print('[ 🎦 ]:直播间清晰度')
|
||||
for i, f in enumerate(self.result.liveDict["flv_pull_url"].keys()):
|
||||
print('[ %s ]: %s' % (i, f))
|
||||
flv.append(f)
|
||||
|
||||
rate = int(input('[ 🎬 ]输入数字选择推流清晰度：'))
|
||||
|
||||
self.result.liveDict["flv_pull_url0"] = self.result.liveDict["flv_pull_url"][flv[rate]]
|
||||
|
||||
# 显示清晰度列表
|
||||
print('[ %s ]:%s' % (flv[rate], self.result.liveDict["flv_pull_url"][flv[rate]]))
|
||||
print('[ 📺 ]:复制链接使用下载工具下载')
|
||||
return self.result.liveDict
|
||||
|
||||
def getMixInfo(self, mix_id: str, count=35, number=0, increase=False, sec_uid=''):
|
||||
print('[ 提示 ]:正在请求的合集 id = %s\r\n' % mix_id)
|
||||
if mix_id is None:
|
||||
return None
|
||||
if number <= 0:
|
||||
numflag = False
|
||||
else:
|
||||
numflag = True
|
||||
|
||||
cursor = 0
|
||||
awemeList = []
|
||||
increaseflag = False
|
||||
numberis0 = False
|
||||
|
||||
print("[ 提示 ]:正在获取合集下的所有作品数据请稍后...\r")
|
||||
print("[ 提示 ]:会进行多次请求，等待时间较长...\r\n")
|
||||
times = 0
|
||||
while True:
|
||||
times = times + 1
|
||||
print("[ 提示 ]:正在对 [合集] 进行第 " + str(times) + " 次请求...\r")
|
||||
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
|
||||
try:
|
||||
url = self.urls.USER_MIX + utils.getXbogus(
|
||||
f'mix_id={mix_id}&cursor={cursor}&count={count}&device_platform=webapp&aid=6383')
|
||||
|
||||
res = requests.get(url=url, headers=douyin_headers)
|
||||
datadict = json.loads(res.text)
|
||||
print('[ 提示 ]:本次请求返回 ' + str(len(datadict["aweme_list"])) + ' 条数据\r')
|
||||
|
||||
if datadict is not None:
|
||||
break
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
|
||||
return awemeList
|
||||
|
||||
|
||||
for aweme in datadict["aweme_list"]:
|
||||
if self.database:
|
||||
# 退出条件
|
||||
if increase is False and numflag and numberis0:
|
||||
break
|
||||
if increase and numflag and numberis0 and increaseflag:
|
||||
break
|
||||
# 增量更新, 找到非置顶的最新的作品发布时间
|
||||
if self.db.get_mix(sec_uid=sec_uid, mix_id=mix_id, aweme_id=aweme['aweme_id']) is not None:
|
||||
if increase and aweme['is_top'] == 0:
|
||||
increaseflag = True
|
||||
else:
|
||||
self.db.insert_mix(sec_uid=sec_uid, mix_id=mix_id, aweme_id=aweme['aweme_id'], data=aweme)
|
||||
|
||||
# 退出条件
|
||||
if increase and numflag is False and increaseflag:
|
||||
break
|
||||
if increase and numflag and numberis0 and increaseflag:
|
||||
break
|
||||
else:
|
||||
if numflag and numberis0:
|
||||
break
|
||||
|
||||
if numflag:
|
||||
number -= 1
|
||||
if number == 0:
|
||||
numberis0 = True
|
||||
|
||||
# 清空self.awemeDict
|
||||
self.result.clearDict(self.result.awemeDict)
|
||||
|
||||
# 默认为视频
|
||||
awemeType = 0
|
||||
try:
|
||||
if aweme["images"] is not None:
|
||||
awemeType = 1
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:接口中未找到 images\r")
|
||||
|
||||
# 转换成我们自己的格式
|
||||
self.result.dataConvert(awemeType, self.result.awemeDict, aweme)
|
||||
|
||||
if self.result.awemeDict is not None and self.result.awemeDict != {}:
|
||||
awemeList.append(copy.deepcopy(self.result.awemeDict))
|
||||
|
||||
if self.database:
|
||||
if increase and numflag is False and increaseflag:
|
||||
print("\r\n[ 提示 ]: [合集] 下作品增量更新数据获取完成...\r\n")
|
||||
break
|
||||
elif increase is False and numflag and numberis0:
|
||||
print("\r\n[ 提示 ]: [合集] 下指定数量作品数据获取完成...\r\n")
|
||||
break
|
||||
elif increase and numflag and numberis0 and increaseflag:
|
||||
print("\r\n[ 提示 ]: [合集] 下指定数量作品数据获取完成, 增量更新数据获取完成...\r\n")
|
||||
break
|
||||
else:
|
||||
if numflag and numberis0:
|
||||
print("\r\n[ 提示 ]: [合集] 下指定数量作品数据获取完成...\r\n")
|
||||
break
|
||||
|
||||
# 更新 max_cursor
|
||||
cursor = datadict["cursor"]
|
||||
|
||||
# 退出条件
|
||||
if datadict["has_more"] == 0 or datadict["has_more"] == False:
|
||||
print("\r\n[ 提示 ]:[合集] 下所有作品数据获取完成...\r\n")
|
||||
break
|
||||
else:
|
||||
print("\r\n[ 提示 ]:[合集] 第 " + str(times) + " 次请求成功...\r\n")
|
||||
|
||||
return awemeList
|
||||
|
||||
def getUserAllMixInfo(self, sec_uid, count=35, number=0):
|
||||
print('[ 提示 ]:正在请求的用户 id = %s\r\n' % sec_uid)
|
||||
if sec_uid is None:
|
||||
return None
|
||||
if number <= 0:
|
||||
numflag = False
|
||||
else:
|
||||
numflag = True
|
||||
|
||||
cursor = 0
|
||||
mixIdNameDict = {}
|
||||
|
||||
print("[ 提示 ]:正在获取主页下所有合集 id 数据请稍后...\r")
|
||||
print("[ 提示 ]:会进行多次请求，等待时间较长...\r\n")
|
||||
times = 0
|
||||
while True:
|
||||
times = times + 1
|
||||
print("[ 提示 ]:正在对 [合集列表] 进行第 " + str(times) + " 次请求...\r")
|
||||
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
|
||||
try:
|
||||
url = self.urls.USER_MIX_LIST + utils.getXbogus(
|
||||
f'sec_user_id={sec_uid}&count={count}&cursor={cursor}&device_platform=webapp&aid=6383')
|
||||
|
||||
res = requests.get(url=url, headers=douyin_headers)
|
||||
datadict = json.loads(res.text)
|
||||
print('[ 提示 ]:本次请求返回 ' + str(len(datadict["mix_infos"])) + ' 条数据\r')
|
||||
|
||||
if datadict is not None and datadict["status_code"] == 0:
|
||||
break
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
|
||||
return mixIdNameDict
|
||||
|
||||
|
||||
for mix in datadict["mix_infos"]:
|
||||
mixIdNameDict[mix["mix_id"]] = mix["mix_name"]
|
||||
if numflag:
|
||||
number -= 1
|
||||
if number == 0:
|
||||
break
|
||||
if numflag and number == 0:
|
||||
print("\r\n[ 提示 ]:[合集列表] 下指定数量合集数据获取完成...\r\n")
|
||||
break
|
||||
|
||||
# 更新 max_cursor
|
||||
cursor = datadict["cursor"]
|
||||
|
||||
# 退出条件
|
||||
if datadict["has_more"] == 0 or datadict["has_more"] == False:
|
||||
print("[ 提示 ]:[合集列表] 下所有合集 id 数据获取完成...\r\n")
|
||||
break
|
||||
else:
|
||||
print("\r\n[ 提示 ]:[合集列表] 第 " + str(times) + " 次请求成功...\r\n")
|
||||
|
||||
return mixIdNameDict
|
||||
|
||||
def getMusicInfo(self, music_id: str, count=35, number=0, increase=False):
|
||||
print('[ 提示 ]:正在请求的音乐集合 id = %s\r\n' % music_id)
|
||||
if music_id is None:
|
||||
return None
|
||||
if number <= 0:
|
||||
numflag = False
|
||||
else:
|
||||
numflag = True
|
||||
|
||||
cursor = 0
|
||||
awemeList = []
|
||||
increaseflag = False
|
||||
numberis0 = False
|
||||
|
||||
print("[ 提示 ]:正在获取音乐集合下的所有作品数据请稍后...\r")
|
||||
print("[ 提示 ]:会进行多次请求，等待时间较长...\r\n")
|
||||
times = 0
|
||||
while True:
|
||||
times = times + 1
|
||||
print("[ 提示 ]:正在对 [音乐集合] 进行第 " + str(times) + " 次请求...\r")
|
||||
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
|
||||
try:
|
||||
url = self.urls.MUSIC + utils.getXbogus(
|
||||
f'music_id={music_id}&cursor={cursor}&count={count}&device_platform=webapp&aid=6383')
|
||||
|
||||
res = requests.get(url=url, headers=douyin_headers)
|
||||
datadict = json.loads(res.text)
|
||||
print('[ 提示 ]:本次请求返回 ' + str(len(datadict["aweme_list"])) + ' 条数据\r')
|
||||
|
||||
if datadict is not None and datadict["status_code"] == 0:
|
||||
break
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
|
||||
return awemeList
|
||||
|
||||
|
||||
for aweme in datadict["aweme_list"]:
|
||||
if self.database:
|
||||
# 退出条件
|
||||
if increase is False and numflag and numberis0:
|
||||
break
|
||||
if increase and numflag and numberis0 and increaseflag:
|
||||
break
|
||||
# 增量更新, 找到非置顶的最新的作品发布时间
|
||||
if self.db.get_music(music_id=music_id, aweme_id=aweme['aweme_id']) is not None:
|
||||
if increase and aweme['is_top'] == 0:
|
||||
increaseflag = True
|
||||
else:
|
||||
self.db.insert_music(music_id=music_id, aweme_id=aweme['aweme_id'], data=aweme)
|
||||
|
||||
# 退出条件
|
||||
if increase and numflag is False and increaseflag:
|
||||
break
|
||||
if increase and numflag and numberis0 and increaseflag:
|
||||
break
|
||||
else:
|
||||
if numflag and numberis0:
|
||||
break
|
||||
|
||||
if numflag:
|
||||
number -= 1
|
||||
if number == 0:
|
||||
numberis0 = True
|
||||
|
||||
# 清空self.awemeDict
|
||||
self.result.clearDict(self.result.awemeDict)
|
||||
|
||||
# 默认为视频
|
||||
awemeType = 0
|
||||
try:
|
||||
if aweme["images"] is not None:
|
||||
awemeType = 1
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:接口中未找到 images\r")
|
||||
|
||||
# 转换成我们自己的格式
|
||||
self.result.dataConvert(awemeType, self.result.awemeDict, aweme)
|
||||
|
||||
if self.result.awemeDict is not None and self.result.awemeDict != {}:
|
||||
awemeList.append(copy.deepcopy(self.result.awemeDict))
|
||||
|
||||
if self.database:
|
||||
if increase and numflag is False and increaseflag:
|
||||
print("\r\n[ 提示 ]: [音乐集合] 下作品增量更新数据获取完成...\r\n")
|
||||
break
|
||||
elif increase is False and numflag and numberis0:
|
||||
print("\r\n[ 提示 ]: [音乐集合] 下指定数量作品数据获取完成...\r\n")
|
||||
break
|
||||
elif increase and numflag and numberis0 and increaseflag:
|
||||
print("\r\n[ 提示 ]: [音乐集合] 下指定数量作品数据获取完成, 增量更新数据获取完成...\r\n")
|
||||
break
|
||||
else:
|
||||
if numflag and numberis0:
|
||||
print("\r\n[ 提示 ]: [音乐集合] 下指定数量作品数据获取完成...\r\n")
|
||||
break
|
||||
|
||||
# 更新 cursor
|
||||
cursor = datadict["cursor"]
|
||||
|
||||
# 退出条件
|
||||
if datadict["has_more"] == 0 or datadict["has_more"] == False:
|
||||
print("\r\n[ 提示 ]:[音乐集合] 下所有作品数据获取完成...\r\n")
|
||||
break
|
||||
else:
|
||||
print("\r\n[ 提示 ]:[音乐集合] 第 " + str(times) + " 次请求成功...\r\n")
|
||||
|
||||
return awemeList
|
||||
|
||||
def getUserDetailInfo(self, sec_uid):
|
||||
if sec_uid is None:
|
||||
return None
|
||||
|
||||
datadict = {}
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
|
||||
try:
|
||||
url = self.urls.USER_DETAIL + utils.getXbogus(
|
||||
f'sec_user_id={sec_uid}&device_platform=webapp&aid=6383')
|
||||
|
||||
res = requests.get(url=url, headers=douyin_headers)
|
||||
datadict = json.loads(res.text)
|
||||
|
||||
if datadict is not None and datadict["status_code"] == 0:
|
||||
return datadict
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
|
||||
return datadict
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
pass
|
||||
398
apiproxy/douyin/douyinapi.py
Normal file
398
apiproxy/douyin/douyinapi.py
Normal file
@ -0,0 +1,398 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : douyinapi.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/20 22:13
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
|
||||
import re
|
||||
import requests
|
||||
import json
|
||||
import time
|
||||
import copy
|
||||
|
||||
from apiproxy.douyin import douyin_headers
|
||||
from apiproxy.douyin.urls import Urls
|
||||
from apiproxy.douyin.result import Result
|
||||
from apiproxy.common import utils
|
||||
|
||||
class DouyinApi(object):
|
||||
def __init__(self):
|
||||
self.urls = Urls()
|
||||
self.result = Result()
|
||||
# 用于设置重复请求某个接口的最大时间
|
||||
self.timeout = 10
|
||||
|
||||
# 从分享链接中提取网址
|
||||
def getShareLink(self, string):
|
||||
# findall() 查找匹配正则表达式的字符串
|
||||
return re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', string)[0]
|
||||
|
||||
# 得到 作品id 或者 用户id
|
||||
# 传入 url 支持 https://www.iesdouyin.com 与 https://v.douyin.com
|
||||
def getKey(self, url):
|
||||
key = None
|
||||
key_type = None
|
||||
|
||||
try:
|
||||
r = requests.get(url=url, headers=douyin_headers)
|
||||
except Exception as e:
|
||||
print('[ 错误 ]:输入链接有误！\r')
|
||||
return key_type, key
|
||||
|
||||
# 抖音把图集更新为note
|
||||
# 作品 第一步解析出来的链接是share/video/{aweme_id}
|
||||
# https://www.iesdouyin.com/share/video/7037827546599263488/?region=CN&mid=6939809470193126152&u_code=j8a5173b&did=MS4wLjABAAAA1DICF9-A9M_CiGqAJZdsnig5TInVeIyPdc2QQdGrq58xUgD2w6BqCHovtqdIDs2i&iid=MS4wLjABAAAAomGWi4n2T0H9Ab9x96cUZoJXaILk4qXOJlJMZFiK6b_aJbuHkjN_f0mBzfy91DX1&with_sec_did=1&titleType=title&schema_type=37&from_ssr=1&utm_source=copy&utm_campaign=client_share&utm_medium=android&app=aweme
|
||||
# 用户 第一步解析出来的链接是share/user/{sec_uid}
|
||||
# https://www.iesdouyin.com/share/user/MS4wLjABAAAA06y3Ctu8QmuefqvUSU7vr0c_ZQnCqB0eaglgkelLTek?did=MS4wLjABAAAA1DICF9-A9M_CiGqAJZdsnig5TInVeIyPdc2QQdGrq58xUgD2w6BqCHovtqdIDs2i&iid=MS4wLjABAAAAomGWi4n2T0H9Ab9x96cUZoJXaILk4qXOJlJMZFiK6b_aJbuHkjN_f0mBzfy91DX1&with_sec_did=1&sec_uid=MS4wLjABAAAA06y3Ctu8QmuefqvUSU7vr0c_ZQnCqB0eaglgkelLTek&from_ssr=1&u_code=j8a5173b×tamp=1674540164&ecom_share_track_params=%7B%22is_ec_shopping%22%3A%221%22%2C%22secuid%22%3A%22MS4wLjABAAAA-jD2lukp--I21BF8VQsmYUqJDbj3FmU-kGQTHl2y1Cw%22%2C%22enter_from%22%3A%22others_homepage%22%2C%22share_previous_page%22%3A%22others_homepage%22%7D&utm_source=copy&utm_campaign=client_share&utm_medium=android&app=aweme
|
||||
# 合集
|
||||
# https://www.douyin.com/collection/7093490319085307918
|
||||
urlstr = str(r.request.path_url)
|
||||
|
||||
if "/user/" in urlstr:
|
||||
# 获取用户 sec_uid
|
||||
if '?' in r.request.path_url:
|
||||
for one in re.finditer(r'user\/([\d\D]*)([?])', str(r.request.path_url)):
|
||||
key = one.group(1)
|
||||
else:
|
||||
for one in re.finditer(r'user\/([\d\D]*)', str(r.request.path_url)):
|
||||
key = one.group(1)
|
||||
key_type = "user"
|
||||
elif "/video/" in urlstr:
|
||||
# 获取作品 aweme_id
|
||||
key = re.findall('video/(\d+)?', urlstr)[0]
|
||||
key_type = "aweme"
|
||||
elif "/note/" in urlstr:
|
||||
# 获取note aweme_id
|
||||
key = re.findall('note/(\d+)?', urlstr)[0]
|
||||
key_type = "aweme"
|
||||
elif "/mix/detail/" in urlstr:
|
||||
# 获取合集 id
|
||||
key = re.findall('/mix/detail/(\d+)?', urlstr)[0]
|
||||
key_type = "mix"
|
||||
elif "/collection/" in urlstr:
|
||||
# 获取合集 id
|
||||
key = re.findall('/collection/(\d+)?', urlstr)[0]
|
||||
key_type = "mix"
|
||||
elif "/music/" in urlstr:
|
||||
# 获取原声 id
|
||||
key = re.findall('music/(\d+)?', urlstr)[0]
|
||||
key_type = "music"
|
||||
elif "/webcast/reflow/" in urlstr:
|
||||
key1 = re.findall('reflow/(\d+)?', urlstr)[0]
|
||||
url = self.urls.LIVE2 + utils.getXbogus(
|
||||
f'live_id=1&room_id={key1}&app_id=1128')
|
||||
res = requests.get(url, headers=douyin_headers)
|
||||
resjson = json.loads(res.text)
|
||||
key = resjson['data']['room']['owner']['web_rid']
|
||||
key_type = "live"
|
||||
elif "live.douyin.com" in r.url:
|
||||
key = r.url.replace('https://live.douyin.com/', '')
|
||||
key_type = "live"
|
||||
|
||||
if key is None or key_type is None:
|
||||
print('[ 错误 ]:输入链接有误！无法获取 id\r')
|
||||
return key_type, key
|
||||
|
||||
return key_type, key
|
||||
|
||||
def getAwemeInfoApi(self, aweme_id):
|
||||
if aweme_id is None:
|
||||
return None
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
try:
|
||||
jx_url = self.urls.POST_DETAIL + utils.getXbogus(
|
||||
f'aweme_id={aweme_id}&device_platform=webapp&aid=6383')
|
||||
|
||||
raw = requests.get(url=jx_url, headers=douyin_headers).text
|
||||
datadict = json.loads(raw)
|
||||
if datadict is not None and datadict["status_code"] == 0:
|
||||
break
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
return None
|
||||
|
||||
# 清空self.awemeDict
|
||||
self.result.clearDict(self.result.awemeDict)
|
||||
|
||||
# 默认为视频
|
||||
awemeType = 0
|
||||
try:
|
||||
if datadict['aweme_detail']["images"] is not None:
|
||||
awemeType = 1
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
# 转换成我们自己的格式
|
||||
self.result.dataConvert(awemeType, self.result.awemeDict, datadict['aweme_detail'])
|
||||
|
||||
return self.result.awemeDict, datadict
|
||||
|
||||
def getUserInfoApi(self, sec_uid, mode="post", count=35, max_cursor=0):
|
||||
if sec_uid is None:
|
||||
return None
|
||||
|
||||
awemeList = []
|
||||
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
try:
|
||||
if mode == "post":
|
||||
url = self.urls.USER_POST + utils.getXbogus(
|
||||
f'sec_user_id={sec_uid}&count={count}&max_cursor={max_cursor}&device_platform=webapp&aid=6383')
|
||||
elif mode == "like":
|
||||
url = self.urls.USER_FAVORITE_A + utils.getXbogus(
|
||||
f'sec_user_id={sec_uid}&count={count}&max_cursor={max_cursor}&device_platform=webapp&aid=6383')
|
||||
else:
|
||||
return None
|
||||
|
||||
res = requests.get(url=url, headers=douyin_headers)
|
||||
datadict = json.loads(res.text)
|
||||
if datadict is not None and datadict["status_code"] == 0:
|
||||
break
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
return None
|
||||
|
||||
for aweme in datadict["aweme_list"]:
|
||||
# 清空self.awemeDict
|
||||
self.result.clearDict(self.result.awemeDict)
|
||||
|
||||
# 默认为视频
|
||||
awemeType = 0
|
||||
try:
|
||||
if aweme["images"] is not None:
|
||||
awemeType = 1
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
# 转换成我们自己的格式
|
||||
self.result.dataConvert(awemeType, self.result.awemeDict, aweme)
|
||||
|
||||
if self.result.awemeDict is not None and self.result.awemeDict != {}:
|
||||
awemeList.append(copy.deepcopy(self.result.awemeDict))
|
||||
|
||||
return awemeList, datadict, datadict["max_cursor"], datadict["has_more"]
|
||||
|
||||
def getLiveInfoApi(self, web_rid: str):
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
try:
|
||||
live_api = self.urls.LIVE + utils.getXbogus(
|
||||
f'aid=6383&device_platform=web&web_rid={web_rid}')
|
||||
|
||||
response = requests.get(live_api, headers=douyin_headers)
|
||||
live_json = json.loads(response.text)
|
||||
if live_json != {} and live_json['status_code'] == 0:
|
||||
break
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
return None
|
||||
|
||||
# 清空字典
|
||||
self.result.clearDict(self.result.liveDict)
|
||||
|
||||
# 类型
|
||||
self.result.liveDict["awemeType"] = 2
|
||||
# 是否在播
|
||||
self.result.liveDict["status"] = live_json['data']['data'][0]['status']
|
||||
|
||||
if self.result.liveDict["status"] == 4:
|
||||
return self.result.liveDict, live_json
|
||||
|
||||
# 直播标题
|
||||
self.result.liveDict["title"] = live_json['data']['data'][0]['title']
|
||||
|
||||
# 直播cover
|
||||
self.result.liveDict["cover"] = live_json['data']['data'][0]['cover']['url_list'][0]
|
||||
|
||||
# 头像
|
||||
self.result.liveDict["avatar"] = live_json['data']['data'][0]['owner']['avatar_thumb']['url_list'][0].replace(
|
||||
"100x100", "1080x1080")
|
||||
|
||||
# 观看人数
|
||||
self.result.liveDict["user_count"] = live_json['data']['data'][0]['user_count_str']
|
||||
|
||||
# 昵称
|
||||
self.result.liveDict["nickname"] = live_json['data']['data'][0]['owner']['nickname']
|
||||
|
||||
# sec_uid
|
||||
self.result.liveDict["sec_uid"] = live_json['data']['data'][0]['owner']['sec_uid']
|
||||
|
||||
# 直播间观看状态
|
||||
self.result.liveDict["display_long"] = live_json['data']['data'][0]['room_view_stats']['display_long']
|
||||
|
||||
# 推流
|
||||
self.result.liveDict["flv_pull_url"] = live_json['data']['data'][0]['stream_url']['flv_pull_url']
|
||||
|
||||
try:
|
||||
# 分区
|
||||
self.result.liveDict["partition"] = live_json['data']['partition_road_map']['partition']['title']
|
||||
self.result.liveDict["sub_partition"] = \
|
||||
live_json['data']['partition_road_map']['sub_partition']['partition']['title']
|
||||
except Exception as e:
|
||||
self.result.liveDict["partition"] = '无'
|
||||
self.result.liveDict["sub_partition"] = '无'
|
||||
|
||||
flv = []
|
||||
|
||||
for i, f in enumerate(self.result.liveDict["flv_pull_url"].keys()):
|
||||
flv.append(f)
|
||||
|
||||
self.result.liveDict["flv_pull_url0"] = self.result.liveDict["flv_pull_url"][flv[0]]
|
||||
|
||||
return self.result.liveDict, live_json
|
||||
|
||||
def getMixInfoApi(self, mix_id: str, count=35, cursor=0):
|
||||
if mix_id is None:
|
||||
return None
|
||||
|
||||
awemeList = []
|
||||
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
try:
|
||||
url = self.urls.USER_MIX + utils.getXbogus(
|
||||
f'mix_id={mix_id}&cursor={cursor}&count={count}&device_platform=webapp&aid=6383')
|
||||
|
||||
res = requests.get(url=url, headers=douyin_headers)
|
||||
datadict = json.loads(res.text)
|
||||
if datadict is not None:
|
||||
break
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
return None
|
||||
|
||||
for aweme in datadict["aweme_list"]:
|
||||
|
||||
# 清空self.awemeDict
|
||||
self.result.clearDict(self.result.awemeDict)
|
||||
|
||||
# 默认为视频
|
||||
awemeType = 0
|
||||
try:
|
||||
if aweme["images"] is not None:
|
||||
awemeType = 1
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
# 转换成我们自己的格式
|
||||
self.result.dataConvert(awemeType, self.result.awemeDict, aweme)
|
||||
|
||||
if self.result.awemeDict is not None and self.result.awemeDict != {}:
|
||||
awemeList.append(copy.deepcopy(self.result.awemeDict))
|
||||
|
||||
return awemeList, datadict, datadict["cursor"], datadict["has_more"]
|
||||
|
||||
def getUserAllMixInfoApi(self, sec_uid, count=35, cursor=0):
|
||||
|
||||
if sec_uid is None:
|
||||
return None
|
||||
|
||||
mixIdlist = []
|
||||
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
try:
|
||||
url = self.urls.USER_MIX_LIST + utils.getXbogus(
|
||||
f'sec_user_id={sec_uid}&count={count}&cursor={cursor}&device_platform=webapp&aid=6383')
|
||||
|
||||
res = requests.get(url=url, headers=douyin_headers)
|
||||
datadict = json.loads(res.text)
|
||||
if datadict is not None and datadict["status_code"] == 0:
|
||||
break
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
return None
|
||||
|
||||
for mix in datadict["mix_infos"]:
|
||||
mixIdNameDict = {}
|
||||
mixIdNameDict["https://www.douyin.com/collection/" + mix["mix_id"]] = mix["mix_name"]
|
||||
mixIdlist.append(mixIdNameDict)
|
||||
|
||||
return mixIdlist, datadict, datadict["cursor"], datadict["has_more"]
|
||||
|
||||
def getMusicInfoApi(self, music_id: str, count=35, cursor=0):
|
||||
if music_id is None:
|
||||
return None
|
||||
|
||||
awemeList = []
|
||||
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
try:
|
||||
url = self.urls.MUSIC + utils.getXbogus(
|
||||
f'music_id={music_id}&cursor={cursor}&count={count}&device_platform=webapp&aid=6383')
|
||||
|
||||
res = requests.get(url=url, headers=douyin_headers)
|
||||
datadict = json.loads(res.text)
|
||||
if datadict is not None and datadict["status_code"] == 0:
|
||||
break
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
return None
|
||||
|
||||
for aweme in datadict["aweme_list"]:
|
||||
# 清空self.awemeDict
|
||||
self.result.clearDict(self.result.awemeDict)
|
||||
|
||||
# 默认为视频
|
||||
awemeType = 0
|
||||
try:
|
||||
if aweme["images"] is not None:
|
||||
awemeType = 1
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
# 转换成我们自己的格式
|
||||
self.result.dataConvert(awemeType, self.result.awemeDict, aweme)
|
||||
|
||||
if self.result.awemeDict is not None and self.result.awemeDict != {}:
|
||||
awemeList.append(copy.deepcopy(self.result.awemeDict))
|
||||
|
||||
return awemeList, datadict, datadict["cursor"], datadict["has_more"]
|
||||
|
||||
def getUserDetailInfoApi(self, sec_uid):
|
||||
if sec_uid is None:
|
||||
return None
|
||||
|
||||
start = time.time() # 开始时间
|
||||
while True:
|
||||
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
|
||||
try:
|
||||
url = self.urls.USER_DETAIL + utils.getXbogus(
|
||||
f'sec_user_id={sec_uid}&device_platform=webapp&aid=6383')
|
||||
|
||||
res = requests.get(url=url, headers=douyin_headers)
|
||||
datadict = json.loads(res.text)
|
||||
|
||||
if datadict is not None and datadict["status_code"] == 0:
|
||||
return datadict
|
||||
except Exception as e:
|
||||
end = time.time() # 结束时间
|
||||
if end - start > self.timeout:
|
||||
return None
|
||||
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
pass
|
||||
205
apiproxy/douyin/download.py
Normal file
205
apiproxy/douyin/download.py
Normal file
@ -0,0 +1,205 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : download.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/12 15:18
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
|
||||
import os
|
||||
import json
|
||||
import time
|
||||
import requests
|
||||
from tqdm import tqdm
|
||||
from concurrent.futures import ThreadPoolExecutor, wait, ALL_COMPLETED
|
||||
|
||||
from apiproxy.douyin import douyin_headers
|
||||
from apiproxy.common import utils
|
||||
|
||||
|
||||
class Download(object):
|
||||
def __init__(self, thread=5, music=True, cover=True, avatar=True, resjson=True, folderstyle=True):
|
||||
self.thread = thread
|
||||
self.music = music
|
||||
self.cover = cover
|
||||
self.avatar = avatar
|
||||
self.resjson = resjson
|
||||
self.folderstyle = folderstyle
|
||||
|
||||
def progressBarDownload(self, url, filepath, desc):
|
||||
response = requests.get(url, stream=True, headers=douyin_headers)
|
||||
chunk_size = 1024 # 每次下载的数据大小
|
||||
content_size = int(response.headers['content-length']) # 下载文件总大小
|
||||
try:
|
||||
if response.status_code == 200: # 判断是否响应成功
|
||||
with open(filepath, 'wb') as file, tqdm(total=content_size,
|
||||
unit="iB",
|
||||
desc=desc,
|
||||
unit_scale=True,
|
||||
unit_divisor=1024,
|
||||
|
||||
) as bar: # 显示进度条
|
||||
for data in response.iter_content(chunk_size=chunk_size):
|
||||
size = file.write(data)
|
||||
bar.update(size)
|
||||
except Exception as e:
|
||||
# 下载异常 删除原来下载的文件, 可能未下成功
|
||||
if os.path.exists(filepath):
|
||||
os.remove(filepath)
|
||||
print("[ 错误 ]:下载出错\r")
|
||||
|
||||
def awemeDownload(self, awemeDict: dict, savePath=os.getcwd()):
|
||||
if awemeDict is None:
|
||||
return
|
||||
if not os.path.exists(savePath):
|
||||
os.mkdir(savePath)
|
||||
|
||||
try:
|
||||
# 使用作品 创建时间+描述 当文件夹
|
||||
file_name = awemeDict["create_time"] + "_" + utils.replaceStr(awemeDict["desc"])
|
||||
if self.folderstyle:
|
||||
aweme_path = os.path.join(savePath, file_name)
|
||||
if not os.path.exists(aweme_path):
|
||||
os.mkdir(aweme_path)
|
||||
else:
|
||||
aweme_path = savePath
|
||||
|
||||
# 保存获取到的字典信息
|
||||
if self.resjson:
|
||||
try:
|
||||
with open(os.path.join(aweme_path, "result_" + file_name + ".json"), "w", encoding='utf-8') as f:
|
||||
f.write(json.dumps(awemeDict, ensure_ascii=False, indent=2))
|
||||
f.close()
|
||||
except Exception as e:
|
||||
print("[ 错误 ]:保存 result.json 失败... 作品名: " + file_name + "\r\n")
|
||||
|
||||
desc = file_name[:30]
|
||||
# 下载 视频
|
||||
if awemeDict["awemeType"] == 0:
|
||||
video_path = os.path.join(aweme_path, "video_" + file_name + ".mp4")
|
||||
|
||||
if os.path.exists(video_path):
|
||||
pass
|
||||
else:
|
||||
try:
|
||||
url = awemeDict["video"]["play_addr"]["url_list"][0]
|
||||
if url != "":
|
||||
self.isdwownload = False
|
||||
self.alltask.append(
|
||||
self.pool.submit(self.progressBarDownload, url, video_path, "[ 视频 ]:" + desc))
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:视频下载失败,请重试... 作品名: " + file_name + "\r\n")
|
||||
|
||||
# 下载 图集
|
||||
if awemeDict["awemeType"] == 1:
|
||||
for ind, image in enumerate(awemeDict["images"]):
|
||||
image_path = os.path.join(aweme_path, "image_" + file_name + "_" + str(ind) + ".jpeg")
|
||||
if os.path.exists(image_path):
|
||||
pass
|
||||
else:
|
||||
try:
|
||||
url = image["url_list"][0]
|
||||
if url != "":
|
||||
self.isdwownload = False
|
||||
self.alltask.append(
|
||||
self.pool.submit(self.progressBarDownload, url, image_path, "[ 图集 ]:" + desc))
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:图片下载失败,请重试... 作品名: " + file_name + "\r\n")
|
||||
|
||||
# 下载 音乐
|
||||
if self.music:
|
||||
music_name = utils.replaceStr(awemeDict["music"]["title"])
|
||||
music_path = os.path.join(aweme_path, "music_" + music_name + "_" + file_name + ".mp3")
|
||||
|
||||
if os.path.exists(music_path):
|
||||
pass
|
||||
else:
|
||||
try:
|
||||
url = awemeDict["music"]["play_url"]["url_list"][0]
|
||||
if url != "":
|
||||
self.isdwownload = False
|
||||
self.alltask.append(
|
||||
self.pool.submit(self.progressBarDownload, url, music_path, "[ 原声 ]:" + desc))
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:音乐(原声)下载失败,请重试... 作品名: " + file_name + "\r\n")
|
||||
|
||||
# 下载 cover
|
||||
if self.cover and awemeDict["awemeType"] == 0:
|
||||
cover_path = os.path.join(aweme_path, "cover_" + file_name + ".jpeg")
|
||||
|
||||
if os.path.exists(cover_path):
|
||||
pass
|
||||
else:
|
||||
try:
|
||||
url = awemeDict["video"]["cover"]["url_list"][0]
|
||||
if url != "":
|
||||
self.isdwownload = False
|
||||
self.alltask.append(
|
||||
self.pool.submit(self.progressBarDownload, url, cover_path, "[ 封面 ]:" + desc))
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:cover下载失败,请重试... 作品名: " + file_name + "\r\n")
|
||||
|
||||
# 下载 avatar
|
||||
if self.avatar:
|
||||
avatar_path = os.path.join(aweme_path, "avatar_" + file_name + ".jpeg")
|
||||
|
||||
if os.path.exists(avatar_path):
|
||||
pass
|
||||
else:
|
||||
try:
|
||||
url = awemeDict["author"]["avatar"]["url_list"][0]
|
||||
if url != "":
|
||||
self.isdwownload = False
|
||||
self.alltask.append(
|
||||
self.pool.submit(self.progressBarDownload, url, avatar_path, "[ 头像 ]:" + desc))
|
||||
except Exception as e:
|
||||
print("[ 警告 ]:avatar下载失败,请重试... 作品名: " + file_name + "\r\n")
|
||||
except Exception as e:
|
||||
print("[ 错误 ]:下载作品时出错\r\n")
|
||||
|
||||
def userDownload(self, awemeList: list, savePath=os.getcwd()):
|
||||
if awemeList is None:
|
||||
return
|
||||
if not os.path.exists(savePath):
|
||||
os.mkdir(savePath)
|
||||
|
||||
self.alltask = []
|
||||
self.pool = ThreadPoolExecutor(max_workers=self.thread)
|
||||
|
||||
start = time.time() # 开始时间
|
||||
|
||||
for aweme in awemeList:
|
||||
self.awemeDownload(awemeDict=aweme, savePath=savePath)
|
||||
|
||||
wait(self.alltask, return_when=ALL_COMPLETED)
|
||||
|
||||
# 检查下载是否完成
|
||||
while True:
|
||||
print("[ 提示 ]:正在检查下载是否完成...")
|
||||
self.isdwownload = True
|
||||
# 下载上一步失败的
|
||||
for aweme in awemeList:
|
||||
self.awemeDownload(awemeDict=aweme, savePath=savePath)
|
||||
|
||||
wait(self.alltask, return_when=ALL_COMPLETED)
|
||||
|
||||
if self.isdwownload:
|
||||
break
|
||||
|
||||
end = time.time() # 结束时间
|
||||
print('\n' + '[下载完成]:耗时: %d分钟%d秒\n' % (int((end - start) / 60), ((end - start) % 60))) # 输出下载用时时间
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
pass
|
||||
315
apiproxy/douyin/result.py
Normal file
315
apiproxy/douyin/result.py
Normal file
@ -0,0 +1,315 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : result.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/12 15:16
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
|
||||
import time
|
||||
import copy
|
||||
|
||||
|
||||
class Result(object):
|
||||
def __init__(self):
|
||||
# 作者信息
|
||||
self.authorDict = {
|
||||
"avatar_thumb": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
},
|
||||
"avatar": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
},
|
||||
"cover_url": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
},
|
||||
# 喜欢的作品数
|
||||
"favoriting_count": "",
|
||||
# 粉丝数
|
||||
"follower_count": "",
|
||||
# 关注数
|
||||
"following_count": "",
|
||||
# 昵称
|
||||
"nickname": "",
|
||||
# 是否允许下载
|
||||
"prevent_download": "",
|
||||
# 用户 url id
|
||||
"sec_uid": "",
|
||||
# 是否私密账号
|
||||
"secret": "",
|
||||
# 短id
|
||||
"short_id": "",
|
||||
# 签名
|
||||
"signature": "",
|
||||
# 总获赞数
|
||||
"total_favorited": "",
|
||||
# 用户id
|
||||
"uid": "",
|
||||
# 用户自定义唯一id 抖音号
|
||||
"unique_id": "",
|
||||
# 年龄
|
||||
"user_age": "",
|
||||
|
||||
}
|
||||
# 图片信息
|
||||
self.picDict = {
|
||||
"height": "",
|
||||
"mask_url_list": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
}
|
||||
# 音乐信息
|
||||
self.musicDict = {
|
||||
"cover_hd": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
},
|
||||
"cover_large": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
},
|
||||
"cover_medium": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
},
|
||||
"cover_thumb": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
},
|
||||
# 音乐作者抖音号
|
||||
"owner_handle": "",
|
||||
# 音乐作者id
|
||||
"owner_id": "",
|
||||
# 音乐作者昵称
|
||||
"owner_nickname": "",
|
||||
"play_url": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_key": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
},
|
||||
# 音乐名字
|
||||
"title": "",
|
||||
}
|
||||
# 视频信息
|
||||
self.videoDict = {
|
||||
"play_addr": {
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
},
|
||||
"cover_original_scale": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
},
|
||||
"dynamic_cover": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
},
|
||||
"origin_cover": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
},
|
||||
"cover": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": ""
|
||||
}
|
||||
}
|
||||
# mix信息
|
||||
self.mixInfo = {
|
||||
"cover_url": {
|
||||
"height": "",
|
||||
"uri": "",
|
||||
"url_list": [],
|
||||
"width": 720
|
||||
},
|
||||
"ids": "",
|
||||
"is_serial_mix": "",
|
||||
"mix_id": "",
|
||||
"mix_name": "",
|
||||
"mix_pic_type": "",
|
||||
"mix_type": "",
|
||||
"statis": {
|
||||
"current_episode": "",
|
||||
"updated_to_episode": ""
|
||||
}
|
||||
}
|
||||
# 作品信息
|
||||
self.awemeDict = {
|
||||
# 作品创建时间
|
||||
"create_time": "",
|
||||
# awemeType=0 视频, awemeType=1 图集, awemeType=2 直播
|
||||
"awemeType": "",
|
||||
# 作品 id
|
||||
"aweme_id": "",
|
||||
# 作者信息
|
||||
"author": self.authorDict,
|
||||
# 作品描述
|
||||
"desc": "",
|
||||
# 图片
|
||||
"images": [],
|
||||
# 音乐
|
||||
"music": self.musicDict,
|
||||
# 合集
|
||||
"mix_info": self.mixInfo,
|
||||
# 视频
|
||||
"video": self.videoDict,
|
||||
# 作品信息统计
|
||||
"statistics": {
|
||||
"admire_count": "",
|
||||
"collect_count": "",
|
||||
"comment_count": "",
|
||||
"digg_count": "",
|
||||
"play_count": "",
|
||||
"share_count": ""
|
||||
}
|
||||
}
|
||||
# 用户作品信息
|
||||
self.awemeList = []
|
||||
# 直播信息
|
||||
self.liveDict = {
|
||||
# awemeType=0 视频, awemeType=1 图集, awemeType=2 直播
|
||||
"awemeType": "",
|
||||
# 是否在播
|
||||
"status": "",
|
||||
# 直播标题
|
||||
"title": "",
|
||||
# 直播cover
|
||||
"cover": "",
|
||||
# 头像
|
||||
"avatar": "",
|
||||
# 观看人数
|
||||
"user_count": "",
|
||||
# 昵称
|
||||
"nickname": "",
|
||||
# sec_uid
|
||||
"sec_uid": "",
|
||||
# 直播间观看状态
|
||||
"display_long": "",
|
||||
# 推流
|
||||
"flv_pull_url": "",
|
||||
# 分区
|
||||
"partition": "",
|
||||
"sub_partition": "",
|
||||
# 最清晰的地址
|
||||
"flv_pull_url0": "",
|
||||
}
|
||||
|
||||
|
||||
|
||||
# 将得到的json数据（dataRaw）精简成自己定义的数据（dataNew）
|
||||
# 转换得到的数据
|
||||
def dataConvert(self, awemeType, dataNew, dataRaw):
|
||||
for item in dataNew:
|
||||
try:
|
||||
# 作品创建时间
|
||||
if item == "create_time":
|
||||
dataNew['create_time'] = time.strftime(
|
||||
"%Y-%m-%d %H.%M.%S", time.localtime(dataRaw['create_time']))
|
||||
continue
|
||||
# 设置 awemeType
|
||||
if item == "awemeType":
|
||||
dataNew["awemeType"] = awemeType
|
||||
continue
|
||||
# 当 解析的链接 是图片时
|
||||
if item == "images":
|
||||
if awemeType == 1:
|
||||
for image in dataRaw[item]:
|
||||
for i in image:
|
||||
self.picDict[i] = image[i]
|
||||
# 字典要深拷贝
|
||||
self.awemeDict["images"].append(copy.deepcopy(self.picDict))
|
||||
continue
|
||||
# 当 解析的链接 是视频时
|
||||
if item == "video":
|
||||
if awemeType == 0:
|
||||
self.dataConvert(awemeType, dataNew[item], dataRaw[item])
|
||||
continue
|
||||
# 将小头像放大
|
||||
if item == "avatar":
|
||||
for i in dataNew[item]:
|
||||
if i == "url_list":
|
||||
for j in self.awemeDict["author"]["avatar_thumb"]["url_list"]:
|
||||
dataNew[item][i].append(j.replace("100x100", "1080x1080"))
|
||||
elif i == "uri":
|
||||
dataNew[item][i] = self.awemeDict["author"]["avatar_thumb"][i].replace("100x100",
|
||||
"1080x1080")
|
||||
else:
|
||||
dataNew[item][i] = self.awemeDict["author"]["avatar_thumb"][i]
|
||||
continue
|
||||
|
||||
# 原来的json是[{}] 而我们的是 {}
|
||||
if item == "cover_url":
|
||||
self.dataConvert(awemeType, dataNew[item], dataRaw[item][0])
|
||||
continue
|
||||
|
||||
# 根据 uri 获取 1080p 视频
|
||||
if item == "play_addr":
|
||||
dataNew[item]["uri"] = dataRaw["bit_rate"][0]["play_addr"]["uri"]
|
||||
# 使用 这个api 可以获得1080p
|
||||
# dataNew[item]["url_list"] = "https://aweme.snssdk.com/aweme/v1/play/?video_id=%s&ratio=1080p&line=0" \
|
||||
# % dataNew[item]["uri"]
|
||||
dataNew[item]["url_list"] = copy.deepcopy(dataRaw["bit_rate"][0]["play_addr"]["url_list"])
|
||||
continue
|
||||
|
||||
# 常规 递归遍历 字典
|
||||
if isinstance(dataNew[item], dict):
|
||||
self.dataConvert(awemeType, dataNew[item], dataRaw[item])
|
||||
else:
|
||||
# 赋值
|
||||
dataNew[item] = dataRaw[item]
|
||||
except Exception as e:
|
||||
# 删除这个警告, 总是让人误会出错了
|
||||
# print("[ 警告 ]:转换数据时在接口中未找到 %s\r" % (item))
|
||||
pass
|
||||
|
||||
def clearDict(self, data):
|
||||
for item in data:
|
||||
# 常规 递归遍历 字典
|
||||
if isinstance(data[item], dict):
|
||||
self.clearDict(data[item])
|
||||
elif isinstance(data[item], list):
|
||||
data[item] = []
|
||||
else:
|
||||
data[item] = ""
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
pass
|
||||
80
apiproxy/douyin/urls.py
Normal file
80
apiproxy/douyin/urls.py
Normal file
@ -0,0 +1,80 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : urls.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/12 15:04
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
|
||||
|
||||
class Urls(object):
|
||||
def __init__(self):
|
||||
######################################### WEB #########################################
|
||||
# 首页推荐
|
||||
self.TAB_FEED = 'https://www.douyin.com/aweme/v1/web/tab/feed/?'
|
||||
|
||||
# 用户短信息（给多少个用户secid就返回多少的用户信息）
|
||||
self.USER_SHORT_INFO = 'https://www.douyin.com/aweme/v1/web/im/user/info/?'
|
||||
|
||||
# 用户详细信息
|
||||
self.USER_DETAIL = 'https://www.douyin.com/aweme/v1/web/user/profile/other/?'
|
||||
|
||||
# 用户作品
|
||||
self.USER_POST = 'https://www.douyin.com/aweme/v1/web/aweme/post/?'
|
||||
|
||||
# 作品信息
|
||||
self.POST_DETAIL = 'https://www.douyin.com/aweme/v1/web/aweme/detail/?'
|
||||
|
||||
# 用户喜欢A
|
||||
# 需要 odin_tt
|
||||
self.USER_FAVORITE_A = 'https://www.douyin.com/aweme/v1/web/aweme/favorite/?'
|
||||
|
||||
# 用户喜欢B
|
||||
self.USER_FAVORITE_B = 'https://www.iesdouyin.com/web/api/v2/aweme/like/?'
|
||||
|
||||
# 用户历史
|
||||
self.USER_HISTORY = 'https://www.douyin.com/aweme/v1/web/history/read/?'
|
||||
|
||||
# 用户收藏
|
||||
self.USER_COLLECTION = 'https://www.douyin.com/aweme/v1/web/aweme/listcollection/?'
|
||||
|
||||
# 用户评论
|
||||
self.COMMENT = 'https://www.douyin.com/aweme/v1/web/comment/list/?'
|
||||
|
||||
# 首页朋友作品
|
||||
self.FRIEND_FEED = 'https://www.douyin.com/aweme/v1/web/familiar/feed/?'
|
||||
|
||||
# 关注用户作品
|
||||
self.FOLLOW_FEED = 'https://www.douyin.com/aweme/v1/web/follow/feed/?'
|
||||
|
||||
# 合集下所有作品
|
||||
# 只需要X-Bogus
|
||||
self.USER_MIX = 'https://www.douyin.com/aweme/v1/web/mix/aweme/?'
|
||||
|
||||
# 用户所有合集列表
|
||||
# 需要 ttwid
|
||||
self.USER_MIX_LIST = 'https://www.douyin.com/aweme/v1/web/mix/list/?'
|
||||
|
||||
# 直播
|
||||
self.LIVE = 'https://live.douyin.com/webcast/room/web/enter/?'
|
||||
self.LIVE2 = 'https://webcast.amemv.com/webcast/room/reflow/info/?'
|
||||
|
||||
# 音乐
|
||||
self.MUSIC = 'https://www.douyin.com/aweme/v1/web/music/aweme/?'
|
||||
|
||||
#######################################################################################
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
pass
|
||||
18
apiproxy/tiktok/__init__.py
Normal file
18
apiproxy/tiktok/__init__.py
Normal file
@ -0,0 +1,18 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
'''
|
||||
@FileName : __init__.py.py
|
||||
@Project : apiproxy
|
||||
@Description:
|
||||
@Author : imgyh
|
||||
@Mail : admin@imgyh.com
|
||||
@Github : https://github.com/imgyh
|
||||
@Site : https://www.imgyh.com
|
||||
@Date : 2023/5/12 14:43
|
||||
@Version : v1.0
|
||||
@ChangeLog
|
||||
------------------------------------------------
|
||||
|
||||
------------------------------------------------
|
||||
'''
|
||||
Loading…
x
Reference in New Issue
Block a user