微信视频号直播弹幕抓取（python）

最新推荐文章于 2024-07-08 13:56:33 发布
最新推荐文章于 2024-07-08 13:56:33 发布
阅读量644 收藏 10
点赞数 5
文章标签： 微信 python 开发语言
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/marye_1325/article/details/140131148
版权

关于微信视频号直播过程抓取弹幕需要，具体的代码如下：

import logging
from io import BytesIO

import requests
import time
import qrcode
import uuid
import time
import json
import queue
import os
import uvicorn
import base64

from PIL import Image
from fastapi import FastAPI
from fastapi.responses import FileResponse

from threading import Thread, Lock, enumerate

#线程锁
app = FastAPI()
msglist = queue.Queue()
mutex = Lock()
terminate_flag=False
uid = uuid.uuid4().hex
uid22=str(uuid.uuid4())
uid33=str(uuid.uuid4())
session = requests.Session()
finderUsername=''
txvideo_nickname=''
txvideo_headImgUrl=''
wx_nickname=''
wx_username=''
wx_encryptedHeadImage=''
adminNickname=''
fansCount=0
uniqId=''
authKey=""
X_Wechat_Uin=""
liveObjectId=""
liveId = ""
live_description = ""
liveCookies = ""

def filtertime():
    # 获取今天0点的时间戳
    today = time.time()
    filterEndTime = int(today) - (int(today) % 86400)

    # 减去 8664 天
    diff_days = 8664
    filterStartTime = filterEndTime - (diff_days * 86400)

    print("今天0点的时间戳：", filterEndTime)
    print("相减后的时间戳：", filterStartTime)    
    return filterEndTime, filterStartTime


def setcoockis(response):
    # 获取返回的cookie值
    cookies = response.cookies
    # 打印cookie值
    for cookie in cookies:
        print(cookie.name, cookie.value)

def generate_timestamp(length=10):
    current_time = time.time()
    if length == 10:
        timestamp = int(current_time)
    elif length == 13:
        timestamp = int(current_time * 1000)
    else:
        raise ValueError("Invalid timestamp length. Must be 10 or 13.")
    return str(timestamp)

#初始化信息
def hepler_merlin_mmdata():
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/helper/hepler_merlin_mmdata"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/login-for-iframe?dark_mode=true&host_type=1",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";v=\"117\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }
    time10=generate_timestamp(10)
    time13=generate_timestamp(13)
    data = {
        "id": 23865,
        "data": {
            "12": "",
            "13": "",
            "14": "",
            "15": "",
            "16": "",
            "17": time10,
            "18": time10,
            "19": 1,
            "20": "",
            "21": 2,
            "22": uid22,#"398e6d66-8c4d-45db-93f8-b13e240b0892",
            "23": "",
            "24": time13,
            "25": "",
            "26": 0,
            "27": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
            "28": "",
            "29": "",
            "30": "",
            "31": "LoginForIframe",
            "32": "",
            "33": uid33,#"556ff363-7c8b-4f2f-853e-79c35d51e4e7",
            "34": "",
            "35": "",
            "36": 1,
            "37": "{}",
            "38": "",
            "39": "{}",
            "40": "pageEnter",
            "41": "{}",
            "42": "{\"screenHeight\":1032;\"screenWidth\":1920;\"clientHeight\":0;\"clientWidth\":0}",
            "43": ""
        },
        "_log_finder_id": ""
    }

    response = session.post(url, headers=headers, json=data)

    if response.status_code == 200:
        return response.json()
    else:
        return None

#初始化信息2
def helper_mmdata():
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/helper/helper_mmdata"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/login-for-iframe?dark_mode=true&host_type=1",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";=\"117\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }
    data = {
        "id": 21307,
        "data": {
            "13": "",
            "14": "",
            "15": "",
            "17": "null",
            "19": None,
            "20": None,
            "21": int(generate_timestamp(13)),
            "22": generate_timestamp(13)
        },
        "addFinderUinBy": 16
    }

    response = session.post(url, headers=headers, json=data)

    if response.status_code == 200:
        return response.json()
    else:
        return None



#获取登录二维码
def getrcode():
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/auth/auth_login_code"

    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/login-for-iframe?dark_mode=true&host_type=1",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "X-WECHAT-UIN": "0000000000",
        "finger-print-device-id": uid,
        "sec-ch-ua": '"Google Chrome";v="117", "Not;A=Brand";v="8", "Chromium";v="117"',
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": '"Windows"'
    }

    data = {
        "timestamp": str(int(time.time() * 1000)),  # 使用13位时间戳
        "_log_finder_uin": "",
        "_log_finder_id": "",
        "rawKeyBuff": None,
        "pluginSessionId": None,
        "scene": 7,
        "reqScene": 7
    }

    response = session.post(url, headers=headers, json=data)
    #setcoockis(response)
    redata = response.json()

    print(f'getrcode_errMesg:{redata["errMsg"]}')

    if 'token' in redata['data']:
        return redata['data']['token']

    return ''


# 通过微信扫码登录
def request_qrcode(retoken):
    url = f"https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/auth/auth_login_status?token={retoken}&timestamp={generate_timestamp(13)}&_log_finder_uin=&_log_finder_id=&scene=7&reqScene=7"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/login-for-iframe?dark_mode=true&host_type=1",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "X-WECHAT-UIN": "0000000000",
        "finger-print-device-id": uid,
        "sec-ch-ua": '"Google Chrome";v="117", "Not;A=Brand";v="8", "Chromium";v="117"',
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": '"Windows"'
    }
    count = 0
    status = 0
    acctStatus = 0
    while count < 200:
        response = session.post(url, headers=headers)
        #setcoockis(response)
        rejson = response.json()
        if rejson['errCode'] == 0:
            # 处理返回的数据
            # ...
            status = rejson['data']['status']
            acctStatus = rejson['data']['acctStatus']
            if status == 0 and acctStatus == 0:
                print('请使用微信扫码登录！')
            elif status == 5 and acctStatus == 1:
                print('已扫码请在手机上点击确认登录！')
            elif status == 1 and acctStatus == 1:
                print('已成功登录！')
                break
            elif status == 3 and acctStatus == 0:
                print('已成功登录！')
                break
            else:
                print(rejson)
                print('超时或网络异常已退出')
                break

            count += 1
            time.sleep(1)
        else:
            print("请求失败")
            break

    if count >= 200:
        print("二维码已超时")
    if status == 1 & acctStatus == 1:
        return True
    return False


# 获取直播博主的信息，如wx_encryptedHeadImage、wx_nickname、wx_username等
def auth_data():
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/auth/auth_data"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/login",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "X-WECHAT-UIN": "0000000000",
        "finger-print-device-id": uid,
        "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";=\"117\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }
    data = {
        "timestamp": generate_timestamp(13),
        "_log_finder_uin": "",
        "_log_finder_id": "",
        "rawKeyBuff": None,
        "pluginSessionId": None,
        "scene": 7,
        "reqScene": 7
    }

    response = session.post(url, headers=headers, json=data)
    #setcoockis(response)
    rejson = response.json()
    #print(response.json())
    if rejson['errCode'] == 0:
        global wx_encryptedHeadImage
        wx_encryptedHeadImage = rejson['data']['userAttr']['encryptedHeadImage']
        global wx_nickname
        wx_nickname = rejson['data']['userAttr']['nickname']
        global wx_username
        wx_username = rejson['data']['userAttr']['username']
        global txvideo_headImgUrl
        txvideo_headImgUrl = rejson['data']['finderUser']['headImgUrl']
        global txvideo_nickname
        txvideo_nickname = rejson['data']['finderUser']['nickname']
        global finderUsername
        finderUsername = rejson['data']['finderUser']['finderUsername']
        return True
    else:
        print("登录异常："+rejson['errMsg'])
        return False


# 获取帮助加载的参数信息，如authKey、X_Wechat_Uin
def helper_upload_params():
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/helper/helper_upload_params"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/login",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "X-WECHAT-UIN": "0000000000",
        "finger-print-device-id": uid,
        "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";v=\"117\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }
    data = {
        "timestamp": generate_timestamp(13),
        "_log_finder_uin": "",
        "_log_finder_id": finderUsername,
        "rawKeyBuff": None,
        "pluginSessionId": None,
        "scene": 7,
        "reqScene": 7
    }

    response = session.post(url, headers=headers, json=data)
    rejson=response.json()
    if rejson['errCode'] == 0:
        global authKey
        authKey = rejson['data']['authKey']
        global X_Wechat_Uin
        X_Wechat_Uin = str(rejson['data']['uin'])
        return True
    else:
        return False


# 判断直播间状态，获取直播间id、描述、直播间对象id
def check_live_status():
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/live/check_live_status"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/live/home",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "X-WECHAT-UIN": X_Wechat_Uin,
        "finger-print-device-id": uid,
        "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";v=\"117\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }
    data = {
        "timestamp": generate_timestamp(13),
        "_log_finder_uin": "",
        "_log_finder_id": finderUsername,
        "rawKeyBuff": None,
        "pluginSessionId": None,
        "scene": 7,
        "reqScene": 7
    }
    #print("check_live_status")
    try:
        response = session.post(url, headers=headers, json=data,timeout=30)

        rejson = response.json()
        if rejson['errCode'] == 0:
            global liveId
            liveId = rejson['data']['liveId']
            global live_description
            live_description = rejson['data']['description']
            global liveObjectId
            liveObjectId = rejson['data']['liveObjectId']
            #print("check_live_status end")
            if rejson['data']['status'] == 1:
                print(f'直播间【{live_description}】状态正常')
            else:
                print(f'直播间【{live_description}】状态={str(rejson["data"]["status"])}')
            return True
        else:
            return False
    except requests.exceptions.Timeout:
        print("check_live_status请求超时了")
        return True


#获取历史直播场次的记录。这里可以不用调用
def get_live_history():
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/live/get_live_history"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/live/home",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "X-WECHAT-UIN": X_Wechat_Uin,
        "finger-print-device-id": uid,
        "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";=\"117\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }
    request = filtertime()
    filterEndTime, filterStartTime = request
    #查询的开始和结束时间
    data = {
        "pageSize": 1,
        "currentPage": 1,
        "reqType": 2,
        "filterStartTime": filterStartTime,
        "filterEndTime": filterEndTime,
        "timestamp":generate_timestamp(13),
        "_log_finder_uin": "",
        "_log_finder_id": finderUsername,
        "rawKeyBuff": None,
        "pluginSessionId": None,
        "scene": 7,
        "reqScene": 7
    }

    response = session.post(url, headers=headers, json=data)

    rejson=response.json()
    if rejson['errCode'] == 0:
        return True
    else:
        return False


# 判断live-info此链接访问是否正常，如果正常为true，否则为false
def get_live_info():
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/live/get_live_info"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/live/liveBuild",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "X-WECHAT-UIN": X_Wechat_Uin,
        "finger-print-device-id": uid,
        "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";v=\"117\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }
    data = {
        "liveObjectId": liveObjectId,
        "timestamp": generate_timestamp(13),
        "_log_finder_uin": "",
        "_log_finder_id": finderUsername,
        "rawKeyBuff": None,
        "pluginSessionId": None,
        "scene": 7,
        "reqScene": 7
    }
    #print('get_live_info')
    try:
        response = session.post(url, headers=headers, json=data, timeout=30)

        rejson = response.json()
        if rejson['errCode'] == 0:
            return True
        else:
            print(f"get_live_info异常：{rejson}")
            return False
    except requests.exceptions.Timeout:
        print("get_live_info请求超时了")
        return True

#获取msg消息刷新cookie
def join_live():
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/live/join_live"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/live/liveBuild",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "X-WECHAT-UIN": X_Wechat_Uin,
        "finger-print-device-id": uid,
        "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";v=\"117\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }
    data = {
        "objectId": liveObjectId,
        "finderUsername": finderUsername,
        "liveId": liveId,
        "timestamp": str(int(time.time() * 1000)),      # 使用当前的时间戳
        "_log_finder_uin": "",
        "_log_finder_id": finderUsername,
        "rawKeyBuff": None,
        "pluginSessionId": None,
        "scene": 7,
        "reqScene": 7
    }

    response = session.post(url, headers=headers, json=data)

    rejson = response.json()
    if rejson['errCode'] == 0:
        global liveCookies
        liveCookies = rejson['data']['liveCookies']
        return True
    else:
        print(f"join_live异常：{rejson}")
        return False


#获取最新在线人员信息
def a_online_member():
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/live/online_member"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/live/liveBuild",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "X-WECHAT-UIN": X_Wechat_Uin,
        "finger-print-device-id": uid,
        "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";v=\"117\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }
    data = {
        "objectId": liveObjectId,
        "finderUsername": finderUsername,
        "clearRecentRewardHistory": True,
        "liveId": liveId,
        "timestamp": generate_timestamp(13),
        "_log_finder_uin": "",
        "_log_finder_id": finderUsername,
        "rawKeyBuff": None,
        "pluginSessionId": None,
        "scene": 7,
        "reqScene": 7
    }

    #print(f'online_member',data)
    #print('online_member')
    try:
        response = session.post(url, headers=headers, json=data,timeout=30)
        rejson = response.json()
        #print(rejson)
        if rejson['errCode'] == 0:
            json_str = json.dumps(rejson)
            # 将 JSON 字符串写入本地文件
            with open("online_member.json", "w") as file:
                file.write(json_str)
            return True
        else:
            print(f"online_member异常：{rejson}")
            return False
    except requests.exceptions.Timeout:
        print("online_member请求超时")
        return True


# 获取直播的cookies，并将获取的data传递给downmsg()
def msg():
    global liveCookies
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/live/msg"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/live/liveBuild",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "X-WECHAT-UIN": X_Wechat_Uin,
        "finger-print-device-id": uid,
        "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";v=\"117\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }
    data = {
        "objectId": liveObjectId,
        "finderUsername": finderUsername,
        "liveCookies": liveCookies,
        "liveId": liveId,
        "longpollingScene": 0,
        "timestamp": generate_timestamp(13),
        "_log_finder_uin": "",
        "_log_finder_id": finderUsername,
        "rawKeyBuff": None,
        "pluginSessionId": None,
        "scene": 7,
        "reqScene": 7
    }
    #print("msg")
    try:
        response = session.post(url, json=data, headers=headers, timeout=30)
        #print('msg1')
        rejson = response.json()
        #print('msg2')
        if rejson['errCode'] == 0:
            #对本次的消息进行解析
            liveCookies = rejson['data']['liveCookies']
            #print("liveCookies",liveCookies)
            downmsg(rejson['data'])
            return True
        else:
            return False
    except requests.exceptions.Timeout:
        print("msg请求超时了")
        return True


# 直播间激励
def reward_gains():
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/live/reward_gains"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/live/liveBuild",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "X-WECHAT-UIN": X_Wechat_Uin,
        "finger-print-device-id": uid,
        "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";v=\"117\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }
    data = {
        "objectId": liveObjectId,
        "finderUsername": finderUsername,
        "clearRecentRewardHistory": True,
        "liveId": liveId,
        "timestamp": generate_timestamp(13),
        "_log_finder_uin": "",
        "_log_finder_id": finderUsername,
        "rawKeyBuff": None,
        "pluginSessionId": None,
        "scene": 7,
        "reqScene": 7
    }
    #print("reward_gains")
    try:
        response = session.post(url, headers=headers, json=data, timeout=30)
        rejson=response.json()

        if rejson['errCode'] == 0:
            return True
        else:
            print('reward_gains_err:')
            print(rejson)
            return False
    except requests.exceptions.Timeout:
        print("reward_gains请求超时了")
        return True


# 获取直播间的刷到的礼物数据
def gift_enum_list():
    url = "https://channels.weixin.qq.com/cgi-bin/mmfinderassistant-bin/live/gift_enum_list"
    headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "https://channels.weixin.qq.com",
        "Referer": "https://channels.weixin.qq.com/platform/live/liveBuild",
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        "X-WECHAT-UIN": X_Wechat_Uin,
        "finger-print-device-id": uid,
        "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";v=\"117\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }
    data = {
        "objectId": liveObjectId,
        "username": finderUsername,
        "liveId": liveId,
        "timestamp": generate_timestamp(13),
        "_log_finder_uin": "",
        "_log_finder_id": finderUsername,
        "rawKeyBuff": None,
        "pluginSessionId": None,
        "scene": 7,
        "reqScene": 7
    }
    
    response = session.post(url, headers=headers, json=data)
    rejson = response.json()
    print("gift_enum_list:")
    print(data)
    print(rejson)
    if rejson['errCode'] == 0:
        return True
    else:
        return False


# 解析获取到的msg，将获取的msg写入指定文件内
def downmsg(rejson):
    #######解析数据########
    newmsg = []
    for member in rejson['msgList']:
        type = member['type']
        if type == 10005:
            #print(member)
            nickname = member['nickname']
            username = member['username']
            content = member['content']
            signature = member['finderLiveContact']['contact']['signature']
            ext_info = member['finderLiveContact']['contact']['extInfo']
            badge_infos = member['finderLiveContact']['badgeInfos']
            newmsg.append({'nickname': nickname, 'msgType': type, 'username': username, 'content': content, 'signature': signature, 'ext_info': ext_info, 'badge_infos': badge_infos})
        if type == 1:
            #print(member)
            nickname = member['nickname']
            username = member['username']
            content = member['content']
            signature = member['finderLiveContact']['contact']['signature']
            ext_info = member['finderLiveContact']['contact']['extInfo']
            badge_infos = member['finderLiveContact']['badgeInfos']
            newmsg.append({'nickname': nickname, 'msgType': type, 'username': username, 'content': content,'signature':signature,'ext_info':ext_info,'badge_infos':badge_infos})   

    for member in rejson['appMsgList']:
        type = member['msgType']
        if type == 20009:
            badge_infos = member['fromUserContact']['badgeInfos']
            nickname = member['fromUserContact']['contact']['nickname']
            username = member['fromUserContact']['contact']['username']
            signature = ""
            ext_info = None
            base64_string = member['payload']
            decoded_string = base64.b64decode(base64_string).decode('utf-8')
            #print(decoded_string)
            gift_info = json.loads(decoded_string)
            newmsg.append({'nickname': nickname, 'msgType': type, 'username': username, 'gift_info': gift_info,'signature':signature,'ext_info':ext_info,'badge_infos':badge_infos})

    ######################
    # 将数据写入文件
    # 检测当前目录下是否存在msglist目录，如果不存在则创建
    if not os.path.exists("msglist"):
        os.makedirs("msglist")

    # 生成文件路径
    file_path = os.path.join("msglist", f"{generate_timestamp(13)}.json")

    if len(newmsg) > 0:
        # 将数据保存到文件中
        with open(file_path, "w") as file:
            json.dump(newmsg, file)


# 根据获取的msg判断直播实时状态，并在指定时间间隔进行睡眠操作
def getmsg():
    count = 0
    print(count)
    global terminate_flag
    while not terminate_flag:
        count += 1
        #print("当前时间：", time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()))
        if get_live_info() and msg():
            time.sleep(0.1)
        else:
            break
        if count % 3 == 0:
            if check_live_status() and a_online_member() and reward_gains():
                time.sleep(0.1)
            else:
                break


@app.get("/getmsg")
def getmsgs():
    msglist_dir = "msglist"  # 指定目录路径

    # 检查目录是否存在
    if not os.path.exists(msglist_dir):
        return {"code": 0, "message": "目录不存在"}

    # 获取目录下的所有文件
    files = os.listdir(msglist_dir)

    # 检查是否有文件
    if len(files) == 0:
        return {"code": 0, "message": "目前没有消息"}

    # 取第一个文件
    first_file = files[0]

    # 构建文件路径
    file_path = os.path.join(msglist_dir, first_file)

    # 读取文件内容
    with open(file_path, "r") as file:
        file_content = file.read()

    # 删除已读取的文件
    os.remove(file_path)

    # 返回文件内容
    return {"code": 1, "message": "读取成功", "data": json.loads(file_content)}


@app.get("/clsmsg")
def clear_messages():
    msglist_dir = "msglist"  # 指定目录路径

    # 检查目录是否存在
    if not os.path.exists(msglist_dir):
        return {"code": 0, "message": "目录不存在"}

    # 获取目录下的所有文件
    files = os.listdir(msglist_dir)

    # 删除目录下的所有文件
    for file in files:
        file_path = os.path.join(msglist_dir, file)
        os.remove(file_path)

    return {"code": 1, "message": "所有文件已删除"}

@app.get("/get_online_member")
async def get_online_members():
    return FileResponse("online_member.json")


if __name__ == '__main__':
    t1 = Thread(target=getmsg)

    # 获取登录二维码   目的是：拿到token
    retoken = getrcode()
    print(retoken)
    rehttp = f'https://channels.weixin.qq.com/mobile/confirm_login.html?token={retoken}'

    # 展示获取的二维码
    qr = qrcode.QRCode()
    qr.border = 1
    qr.add_data(rehttp)
    qr.make()
    # qr.print_ascii(out=None, tty=False, invert=False)
    # 创建PIL图像对象
    img = qr.make_image(fill_color="black", back_color="white")
    print('请使用微信扫码登录！')

    # 可以选择显示图像
    img.show()

    # 保存图像
    img.save("qrcode.png")
    time.sleep(1)

    # 获取二维码以及前期一系列准备工作。
    if request_qrcode(retoken) and auth_data() and helper_upload_params() and check_live_status() and get_live_info() and join_live() and a_online_member():
        print("加载成功，开启消息获取线程。获取实时弹幕消息。")
        t1.start()

    #启动本地api服务
    print("如需关闭服务，请输入ctrl+C来终止api服务进程，再输入exit退出监听。")
    uvicorn.run("webapi:app", host="127.0.0.1", port=8000, reload=True)

    while True:
        user_input = input("等待输入指令：")
        print("用户输入的指令是：" + user_input)
        
        if user_input == "exit":
            terminate_flag = True
            t1.join()
            break

拿走不谢！

Marye_爱吃樱桃
关注
视频号直播弹幕采集
tdl320721的博客
10-07 2745
本篇文章将讲解视频号直播弹幕的获取的流程，包括用户进入直播间、用户发言、用户刷礼物、用户的唯一标识获取。获取弹幕是制作直播插件的必要流程，比如直播弹幕互动游戏、数字人、半无人直播等等。
某站弹幕抓取，视频，评论......
weixin_73778478的博客
11-20 1367
爬虫爬取（点赞，弹幕，投币）
python如何攻破微信视频号数据的采集，实现微信视频号API接口数据自由
jiaguocong的博客
07-05 1181
想必大家都听说过今年315曝光的问题主板，这种特殊功能的主板可以实现一台电脑变成几十几百个手机，一个手机又可以登录1到多个微信账号。这种产品的原理在python抓取微信视频号数据方面也得到了广泛的应用，不仅仅是微信视频号，还有小红书、头条、抖音的数据抓取都在应用。上面的方法方案是目前常用的方法跟方案，不仅成本高，耗时耗力，目前市场上有成熟的技术可以实现微信视频号直接API接口的自由。执行方法：用硬件设备（具体的设备就不分享了）+海量的微信账号+海量的IP池，模拟人工去抓微信视频号数据。
微信又上“骚”操作！！！
简说Python的博客
07-03 555
文章来源：不正经程序员作者：????距离上次更新刚刚两周，微信有发布了新版本。不得不说，最近的节奏有点快，快跟不上了。那么这次又有什么更新呢？自定义拍一拍上次微信上了拍一拍后，大家玩得...
微信视频号直播 弹幕采集
最新发布
weixin_45307278的博客
07-08 564
微信视频号直播弹幕采集，不限微信版本，支持多直播间同时监控，可获取到部分匿名用户id。视频号 直播弹幕采集（简单演示）
用Python爬取腾讯视频弹幕
菜鸟学Python数据分析
10-19 1771
1.网页分析本文以爬取《脱口秀大会第3季》最后一期视频弹幕为例，首先通过以下步骤找到存放弹幕的真实url。通过删减各参数，发现仅有timestamp参数的变化会影响弹幕数据的爬取，且t...
bxlx视频弹幕信息采集抓取软件使用教程
umbato的博客
05-10 865
至于弹幕日期的格式，一定要按照图中所示格式，即年-月-日。本教程分为按照当天最大爬取量爬取和按照历史日期精确爬取，其中按照当天最大爬取量爬取需要用到视频网页中的BV值或cid值（爬取时使用其中任意一个即可），而按照日期精确爬取需要用到网页中的'user-agent'值和'cookie'值，本教程不会向您解释相关的名词定义，需要了解的可以去百度自行搜索相关解释。再如上图，在左上方的输入框中输入小写字母cid，下方即可自动弹出很多选项，我们随便点击一个即可，示例选择了第一个选项，点击后出现右侧的一行选项，我们。
python怎么爬腾讯视频_Python实战 | 如何抓取腾讯视频弹幕
weixin_39712611的博客
11-24 1132
我们以腾讯视频《天行九歌》为例，为大家细解析腾讯视频弹幕爬取的细节和难点。写爬虫需要理清目标数据和网址的变化规律，随后再去解决细节的数据定位和抓取，往往事半功倍。接下来先看看爬虫的一般步骤：第一步：明确需求，确定需要抓取的字段第二步：分析网站，寻找目标URL第三步：分析目标URL参数,请求方式（get,post）第四步：发起请求1.设置请求头(User-Agent,Cookie,Host)2.实例...
Python对某视频弹幕进行爬取，完成文本数据分析
m0_56140478的博客
03-05 860
Python对某视频弹幕进行爬取，完成文本数据分析
Live Cookies-crx插件
04-02
语言:English (United States) 扩展程序可以实时显示您的Cookie！ 实时Cookies为您提供了一个单独的窗口，该窗口实时显示您主浏览窗口中的所有cookie。 用户可以在另一个窗口中正常浏览时，使此单独的窗口向侧面打开。 当他们浏览时，扩展程序将实时更新，并由浏览窗口设置所有cookie。 用户可以在同域Cookie和跨域Cookie之间进行切换。 跨域Cookie是基于活动窗口的，并通过检查通过跟踪像素请求设置的Cookie来派生。 用户可以通过单击垃圾箱来删除单个cookie，也可以通过按“清除所有cookie”按钮删除所有cookie。 单击“复制所有cookie”按钮，会将所有活动的cookie以JSON格式复制到剪贴板。
python爬虫抖音主播_Python 爬取抖音视频
weixin_39702714的博客
12-05 3267
前面我们了解了一些关于 Python 爬虫的知识不过都是基于 PC 端浏览器网页中的内容进行爬取。现在手机 App 用的越来越多，而且很多也没有网页端，比如抖音就没有网页版，那么上面的视频就没法批量抓取了吗？答案当然是 No！对于 App 来说应用内的通信过程和网页是类似的，都是向后台发送请求，获取数据。在浏览器中我们打开调试工具就可以看到具体的请求内容，在 App 中我们无法直接看到。所以我们就...
python爬微信公众号视频_python爬虫微信公众号视频
weixin_39719077的博客
12-09 1266
import timeimport jsonimport randomimport csvfrom selenium import webdriverfrom lxml import htmlimport requestsimport refrom http import cookiejar# 获取文章class getEssay:def __init__(self):# 获取cookieswit...
这是一个爬取视频弹幕的代码
qq_42444651的博客
11-21 619
生成词云的代码大家可以自己写一下，下面是根据“996”、“躺平”、“美国”关键字爬取的弹幕词云。需求：根据视频关键字，爬取该关键字所搜出来的视频的弹幕。
如何获取主播直播时的弹幕，Python帮你完美解决
qq_46614154的博客
05-11 5971
前言 本文的文字及图片来源于网络,仅供学习、交流使用,不具有任何商业用途,版权归原作者所有,如有问题请及时联系我们以作处理。 作者：小雨 1、需要安装三个库 pip install requests BeautifulSoup4 lxml 代码如下图： 2、运行代码 弹幕消息会滚动在终端上 3、且会在当前目录下生成以主播名字命名的文件 效果如下图： 欢迎点击右上角关注小编，除了分享技术文章之外还有很多福利，私信学习资料可以领取包括不限于Pyt...
Python_爬虫复习_爬取直播间弹幕生成词云图
weixin_50640351的博客
05-30 870
爬取直播间弹幕，生成词云图 一、环境准备： 安装相关第三方库 pip install jieba pip install wordcloud 二、数据准备： 爬取对象：2021年5月23号，RNG夺冠直播间的弹幕信息 爬取对象路径： 方式1、根据开发者工具（F12），获取请求url、请求头、cookie等信息； 方式2：根据直播地址url，前+字符i 我们这里演示的是，采用方式2。 三‘、代码如下’ import requests, re import jieba, wordcloud """ # 以
python爬虫----简单的抓取斗鱼弹幕
老问题的博客
08-08 4283
近几年来直播越来越火，看直播也成为了人们生活的娱乐项目 个人也是比较喜欢看直播，看着主播的搞笑的操作和弹幕不时会开怀大笑。 于是就想能不能把弹幕抓取下来，带着这个问题我就点开了一个直播间。按照以前学过的方法好像根本没有办法弄到弹幕那一块， 于是赶紧去网上查，发现网上有不少人已经做了。呃......怎么说，大概了解了获取弹幕的原理，就是通过socket向斗鱼弹幕服务器发送请求， 然后
微信视频号数据采集方案
zyg_8929的博客
06-22 5459
历经劫难,终于完美解决.
python爬虫直播源_Python爬虫经典项目：各大直播平台的弹幕人气工具！
weixin_39970064的博客
11-24 505
目录一、功能学习Python中有不明白推荐加入交流群号：前面548中间377后面875群里有志同道合的小伙伴，互帮互助，群里有不错的学习教程！二、思路三、实现1. 获取弹幕2. 发送弹幕3. 封装调用一、功能功能很简单，就是将B站直播间的每条弹幕重新发送一遍。二、思路先通过post请求获取实时弹幕，再用post请求重新发送。三、实现1. 获取弹幕（1）因为实时弹幕是通过Ajax从服务器获取的，我们...
如何使用wireshark抓取微信视频号直播推流地址
05-11
使用 Wireshark 抓取微信视频号直播推流地址的步骤如下： 1. 在电脑上安装 Wireshark 软件，并打开软件。 2. 打开微信视频号，进入直播房间。 3. 在 Wireshark 中选择要抓取的网络接口，并点击“开始捕获”按钮。 4. 在微信视频号中点击“开始直播”，并等待一会儿，直到视频开始推流。 5. 在 Wireshark 中使用过滤器“http.request.method == POST”来过滤出 POST 请求。 6. 找到一个包含“/video/v1/live/create”字符串的请求，并右键点击这个请求，选择“跟踪”->“TCP流”。 7. 在跟踪窗口中，找到包含“play_url”字符串的响应，并查看其中的 JSON 数据，即可找到直播推流地址。 需要注意的是，抓取直播推流地址可能涉及到隐私和版权问题，请勿将抓取到的地址用于非法用途。
评论 3
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值