Python 笔记(三) 采取某音视频

Python 笔记(三) 采取某音视频

# -*- coding: utf-8 -*-
import csv
import re
from time import time

import parsel
import requests

# 爬取视频
from pip._vendor.rich import json


# 代码原理
# 1.发送请求，获取数据
# 2.解析数据，保存数据

# 多个视频采集 分析url变化规律
# 通过分析视频中的 src 跳转的 链接 找到链接的位置
# 用正则匹配出资源地址
# 解码出链接
# 保存数据到MP4文件


def main():
    start = time()

    # 单视频链接
    url = 'htt***in.com/video/7102976099893726468'

    headers = {
        'cookie': 'ttwid=1|hG0kpelVMqzSZfkO_rtj8iOALM-zNSkUnkVPKEZhGHM|1653807941|05d1a7f8d3b87e942cb7b78042736355b3d237751ac6fa0e8d1d6f648190c1d3; dou***com; strategyABtestKey=1653807944.929; passport_csrf_token=af41f908b3561447aada38684bc61922; passport_csrf_token_default=af41f908b3561447aada38684bc61922; _tea_utm_cache_2285=undefined; ttcid=14e69838859a41ca8c73be39d792b9bb18; _tea_utm_cache_6383=undefined; _tea_utm_cache_1300=undefined; THEME_STAY_TIME="299505"; IS_HIDE_THEME_CHANGE="1"; pwa_guide_count="3"; __ac_nonce=0629329ae00490204570a; __ac_signature=_02B4Z6wo00f01lP-nZAAAIDC0.xn0ZCu3hJT3pkAAPZ756XEuILz-YmH3p5as5tBwCjH9QBCFROw-9LYkUt9.nCeebXVx1DzPNVd-yBewu1woRj.AQw6XuAwAUqiscgaSQ0Bp7Azhm0MG79F32; home_can_add_dy_2_desktop="1"; msToken=oElEdtCwAY-oW727oex-ylY5s6bhyXc0vl7_JLS1O2D-qjfr1K0Z3ceAqNKNFC_H_JsJOox2nj0wbOlvYzeR-LfoVK_CLwwjJkBvEvVGu7p54EjJhngpk1I=; tt_scid=VQSplI87N418e17p3XKlO7S.AQhepL2rDMS9QAV8KqFVGDUu5.DTWdrH8mmWziSP3f35; AVATAR_FULL_LOGIN_GUIDE_ITA_TIMESTAMP="1653811641788"; AVATAR_FULL_LOGIN_GUIDE_ITA_COUNT="1"; s_v_web_id=verify_l3r0rjv0_JzCyMEuL_W5M8_4yOk_97B4_RH2THzWfqjNG; VIDEO_FILTER_MEMO_SELECT={"expireTime":1654416467488,"type":0}; msToken=9-2NQXP7MDpVtGJKKVA72dTFmnP_LHga9H_QseAfKSL5FO2Cw12c0_vJK416ciyO9a0ag6F5oClvZK3c5QNZXugD8VLVfZyJniqQWK_nff8re2EgqSzxyNU=',
        # 浏览器基本信息
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.93 Safari/537.36'
    }

    # 通过多视频列表采集到ID
    response = requests.get(url=url, headers=headers)
    # print(response.text)

    # 通过正则找数据 \d+ 表示匹配一个或多个数字 (.*?) 表示中间所有内容
    # 获取标题
    title = re.findall('<title data-react-helmet="true">(.*?)</title>', response.text)[0]
    print(title)

    # 获取初始的url
    video_url = re.findall('src(.*?)%22%7D%2C%7B%22', response.text)[0]     # 获取跳转网址编码内容
    print(video_url)

    # unquote 将url转码
    video_url_1 = requests.utils.unquote(video_url).replace('":"', 'https:') # 解析出编码
    print(video_url_1)

    video_content = requests.get(url=video_url_1, headers=headers).content # 发送请求获取二进制数据内容

    # 写入文件
    with open(title+'.mp4',mode='wb') as f:
        f.write(video_content) # 写入文件内容

    end = time()
    print('总共耗费了%.2f秒.' % (end - start))


# 采集抖音视频。
if __name__ == '__main__':
    main()