python爬虫抖某音爬取视频 Airtest+fiddler

//保存到本地添加开始
        
		//这是抖音的地址  设定视频包的链接名
		if (
			oSession.fullUrl.Contains("v1-dy.bytecdn.cn")||
			oSession.fullUrl.Contains("v3-dy-y.bytecdn.cn")||
			oSession.fullUrl.Contains("v3-dy.z.bytecdn.cn")||
			oSession.fullUrl.Contains("v5-dy.bytecdn.cn")||
			oSession.fullUrl.Contains("v6-dy.bytecdn.cn") ||
			oSession.fullUrl.Contains("v9-dy-z.bytecdn.cn") ||
		    oSession.fullUrl.Contains("v9-dy.bytecdn.cn")
		){
            
			var fso;
			var file;
			fso = new ActiveXObject("Scripting.FileSystemObject");
			//文件保存路径，可自定义  自动保存的txt文档地址
			file = fso.OpenTextFile("E:\\url_bt\\douyin.txt",8,true);
			//file.writeLine("Request-url:" + oSession.url);
			file.writeLine("http://"+oSession.url)
			//file.writeLine("Request-host:" + oSession.host);
			//file.writeLine("Request-header:" + "\n" + oSession.oRequest.headers);
			//file.writeLine("Request-body:" + oSession.GetRequestBodyAsString());
			//file.writeLine("\n");
			file.close();
		}        
		//保存到本地添加结束

__author__ = "xiaojun"

from airtest.core.api import *

auto_setup(__file__)

from poco.drivers.android.uiautomation import AndroidUiautomationPoco


poco = AndroidUiautomationPoco(use_airtest_input=True, screenshot_each_action=False)
#模拟滑动
def douyin_spwipe():
    #无限循环向上滑动
    while True:
        #坐标，以及速度
        poco.swipe([0.5,0.8],[0.5,0.3],duration=0.2)
        sleep(3)

import os
import requests
import sys

import time
from fake_useragent import UserAgent

headers = {
    ‘User-Agent‘:UserAgent().chrome
}
#去重
def distinct_data():
    datalist_blank = []
    with open(r‘E:\url_bt\douyin.txt‘,‘r‘) as f:
        #读取所有行，生成列表
        f_data_list = f.readlines()
        print(f_data_list)
        for url in f_data_list:
            if len(url)>40:
                datalist_blank.append(url.strip()) #去掉\n strip去掉头尾默认空格或换行符
                # print(url.strip())


        f.close()
    # print(len(datalist_blank), datalist_blank)
    # print(len(set(datalist_blank)), set(datalist_blank))
    #去重后的列表url
    datalist_blank= list(set(datalist_blank))

    return datalist_blank

#写入文件夹
def responsedouyin():
    #获得种子链接
    data_url=distinct_data()

    #统计文件夹中视频数量
    DIR = r‘E:\url_bt\douyin_mp4‘  # 要统计的文件夹
    num = len([name for name in os.listdir(DIR) if os.path.isfile(os.path.join(DIR, name))])+1
    print(num)#文件夹现文件数量
    for url in data_url:
        # stream=True作用是推迟下载响应体直到访问Response.content属性
        # res = requests.get(url,stream=True,headers=headers)
        res = requests.get(url=url, stream=True, headers=headers)
#         #定义视频存放的路径
        pathinfo = r‘E:\url_bt\douyin_mp4\%d.mp4‘%num  #%d 用于整数输出   %s用于字符串输出
        # 实现下载进度条显示，这一步需要得到总视频大小
        total_size = int(res.headers[‘Content-Length‘])
        print(‘这是视频的总大小：‘,total_size)
        #设置流的起始值为0
        temp_size = 0
        if res.status_code == 200:
            # 将视频写入文件夹
            with open(pathinfo, ‘wb‘) as file:
                file.write(res.content)
                print(pathinfo + ‘下载完成啦啦啦啦啦‘)
                num += 1

    with open(r‘E:\url_bt\douyin.txt‘, ‘w‘) as f:
        f.write(‘‘)
        f.close()
    time.sleep(700)