python爬取视频‍♀️‍♀️‍♀️

 

#  -*- coding = utf-8 -*-
import json
import pprint
import random
import string
from urllib.parse import quote
from urllib.request import Request, urlopen
from bs4 import BeautifulSoup
from io import BytesIO
import gzip
import os
import re
import json
import requests

my_headers = [
    {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'},
    {
        'user-agent': "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36"},
    {
        'user-agent': "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36"},
    {'user-agent': "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0"},
    {
        'user-agent': "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14"},
    {'user-agent': "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/6.0)"},
    {'user-agent': "Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11"},
    {'user-agent': 'Opera/9.25 (Windows NT 5.1; U; en)'},
    {'user-agent': 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)'},
    {'user-agent': 'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)'},
    {
        'user-agent': 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12'},
    {'user-agent': 'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9'},
    {
        'user-agent': "Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.7 (KHTML, like Gecko) Ubuntu/11.04 Chromium/16.0.912.77 Chrome/16.0.912.77 Safari/535.7"},
    {'user-agent': "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0"}
]


def get_video(title, arcurl):
    # url = "https://www.bilibili.com/video/av672827214"
    url = arcurl
    print(url)
    headers = {
        'User-Agent': 'Mozilla/5.0 (iPad; CPU OS 11_0 like Mac OS X) AppleWebKit/604.1.34 (KHTML, like Gecko) Version/11.0 Mobile/15A5341f Safari/604.1',
        'cookie': "PVID=1; _uuid=FA5AFE1E-3E22-ADFE-9226-095428A97F3345229infoc; buvid3=398554D6-6C1F-43DB-8895-C824AA004AF1148822infoc; LIVE_BUVID=AUTO7716288257439557; blackside_state=1; rpdid=|(k|k)uYu|lY0J'uYk))kl~~R; CURRENT_QUALITY=80; fingerprint=1c362c351c6ff64e9b65b1205605e8c7; buvid_fp=398554D6-6C1F-43DB-8895-C824AA004AF1148822infoc; buvid_fp_plain=398554D6-6C1F-43DB-8895-C824AA004AF1148822infoc; SESSDATA=a9f32a53%2C1646718341%2Cf9fe6%2A91; bili_jct=71f1aded9db7273a9f5c5e758de2dc63; DedeUserID=593705704; DedeUserID__ckMd5=0c57b9d95a2d6cde; sid=5ammui66; CURRENT_FNVAL=976; bsource=search_baidu; innersign=1",
        'referer': 'https://www.bilibili.com/video/av672827214'
    }
    response = requests.get(url, headers=headers)
    data = response.text

    # 获取json数据
    data_json = re.findall('<script>window\.__playinfo__=(.*?)</script>', data)[0]
    data_json = json.loads(data_json)
    # pprint.pprint(data_json)
    # 音频
    audio = data_json['data']['dash']['audio'][0]['baseUrl']
    # 视频
    video = data_json['data']['dash']['video'][0]['baseUrl']
    urlFrames = audio
    urlVoice = video

    # urlFrames = "https://cn-jxnc-cmcc-bcache-05.bilivideo.com/upgcxcode/26/02/329930226/329930226-1-30077.m4s?e=ig8euxZM2rNcNbdlhoNvNC8BqJIzNbfqXBvEqxTEto8BTrNvN0GvT90W5JZMkX_YN0MvXg8gNEV4NC8xNEV4N03eN0B5tZlqNxTEto8BTrNvNeZVuJ10Kj_g2UB02J0mN0B5tZlqNCNEto8BTrNvNC7MTX502C8f2jmMQJ6mqF2fka1mqx6gqj0eN0B599M=&uipk=5&nbs=1&deadline=1634961210&gen=playurlv2&os=bcache&oi=1862809570&trid=00006f7a6feb43274a8ab2d51253f1733491u&platform=pc&upsig=61c9525e98870b8ce26c8116e7b3e1e5&uparams=e,uipk,nbs,deadline,gen,os,oi,trid,platform&cdnid=4204&mid=593705704&bvc=vod&nettype=0&orderid=0,3&agrr=0&logo=80000000"
    # urlVoice = "https://xy117x141x226x28xy.mcdn.bilivideo.cn:4483/upgcxcode/26/02/329930226/329930226_nb2-1-30280.m4s?e=ig8euxZM2rNcNbdlhoNvNC8BqJIzNbfqXBvEqxTEto8BTrNvN0GvT90W5JZMkX_YN0MvXg8gNEV4NC8xNEV4N03eN0B5tZlqNxTEto8BTrNvNeZVuJ10Kj_g2UB02J0mN0B5tZlqNCNEto8BTrNvNC7MTX502C8f2jmMQJ6mqF2fka1mqx6gqj0eN0B599M=&uipk=5&nbs=1&deadline=1634961210&gen=playurlv2&os=mcdn&oi=1862809570&trid=00016f7a6feb43274a8ab2d51253f1733491u&platform=pc&upsig=b9cd2d4c8eb3d8955cd94b7408cbc035&uparams=e,uipk,nbs,deadline,gen,os,oi,trid,platform&mcdnid=2001012&mid=593705704&bvc=vod&nettype=0&orderid=0,3&agrr=0&logo=A0000002"
    # # 手动构造请求头参数
    # headers = {
    #     'User-Agent':'Mozilla/5.0 (iPad; CPU OS 11_0 like Mac OS X) AppleWebKit/604.1.34 (KHTML, like Gecko) Version/11.0 Mobile/15A5341f Safari/604.1',
    #     'referer':'https://www.bilibili.com/video/av672827214'
    # }
    # 发送请求，获取响应对象
    FramesResponse = requests.get(urlFrames, headers=headers)
    VoiceResponse = requests.get(urlVoice, headers=headers)
    # 字节类型的数据提取
    FramesData = FramesResponse.content
    VoiceData = VoiceResponse.content
    # 保存在本地
    with open("FramesResponse.mp4", 'wb') as f:
        f.write(FramesData)
    with open("VoiceResponse.mp3", 'wb') as f:
        f.write(VoiceData)

    # 视频合成 ： 第三方工具 ffmpeg
    os.system('ffmpeg -i "FramesResponse.mp4" -i "VoiceResponse.mp3" -c copy "' + title + '.mp4"')

if __name__ == '__main__':
    # header = random.choice(my_headers)
    # header['referer'] = "https://search.bilibili.com/all?keyword=%E9%99%88%E6%98%9F%E6%97%AD"
    # url = "https://search.bilibili.com/all?keyword=%E9%99%88%E6%98%9F%E6%97%AD"
    # url = quote(url, safe=string.printable)
    # request = Request(url, headers=header)
    # res = urlopen(request)
    # with open("./loadHTML/temp.html", "wb") as f:
    #     f.write(res.read())
    with open("./loadHTML/temp.html", "r", encoding='utf-8') as f:
        data = f.read()
    li = data.split('''window.__INITIAL_STATE__=''')
    li = li[1:]
    list = li[0].split(''';(function(){var s;(s=document.currentScript''')
    list = list[:-1]
    jsonList = json.loads(list[0])
    field = jsonList['flow']['fields'][0]
    listO = jsonList['flow'][field]['result'][-1:][0]
    lists = listO['data']
    for li in lists:
        title = str(li['title'])
        title = title.replace('''<em class="keyword">陈星旭</em>''', '').replace('【', '').replace('】', '')
        arcurl = li['arcurl']
        get_video(title, arcurl)
        break;

感谢 wangaolong0427的博客_会百度的皮卡丘_CSDN博客 的鼎力相助！！！