import requests
import re
import subprocess


# 今日头条视频爬虫
def TouTCraw(url):
    headers = {
        'cookie': 'tt_webid=7139605604477388318; ttcid=aadd7eb74eb44a01b84a41b1a9b79ac634; _tea_utm_cache_24={'
                  '%22utm_source%22:%22copy_link%22%2C%22utm_medium%22:%22toutiao_android%22%2C%22utm_campaign%22'
                  ':%22client_share%22}; s_v_web_id=verify_l7npsvjl_GqaI64FF_6lGb_4UCu_9cqF_V1RQsEXiqB4H; '
                  'local_city_cache=%E5%8C%97%E4%BA%AC; _tea_utm_cache_1300={'
                  '%22utm_source%22:%22copy_link%22%2C%22utm_medium%22:%22toutiao_android%22%2C%22utm_campaign%22'
                  ':%22client_share%22}; csrftoken=043b3faa03fcf1b602eaa21751189f06; '
                  'msToken=EuKsGE-znZHJPqf78tWyhYPXmmoHLSTy_26uW5Zaym9IaO4TlXpcEasOm-BstVKnPKD0'
                  '-K8fDCtL2rKsTfDvpzYylXM53l6XoUp_Kd5oB0jt; MONITOR_WEB_ID=7139605604477388318; '
                  'ttwid=1%7CzJeA_hNSisnYWtfAdXu37DQ4Y-_vr-eRGyl03F23qbM%7C1662376254'
                  '%7C74f23fb8683a5eea15ab1f36724e67bc7add7270b4a36fdd290d3ee9c84b05bd; '
                  'tt_scid=U.wVvxl6xFthEs63E56aFWNT6Jg6mftTUY9opJDAe9amsXDG3u58Kp0mReukDAhm8146',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                      'Chrome/105.0.0.0 Safari/537.36 Edg/105.0.1343.27 '
    }
    response = requests.get(url=url, headers=headers)
    response.encoding = 'utf-8'
    # print(response.text)
    title = re.findall('<title>(.*?)</title>', response.text)[0]
    title = title.replace(' ', '_')
    # print(title)
    data = re.findall('videoPlayInfo(.*?)</script>', response.text)[0]
    url = requests.utils.unquote(data)
    # print(url)
    # 获得视频地址
    data1 = re.findall('video_meta":{"definition":"720p"(.*?),"backup_url', url)[0]
    # print(data1)
    video_url = re.findall('main_url":"(.*?)"', data1)[0]
    # 获得音频地址
    audio_url = re.findall('dynamic_audio_list":\[{"main_url":"(.*?)","backup_url"', url)[0]
    # print(video_url)
    # print(audio_url)
    audio_content = requests.get(url=audio_url, headers=headers).content
    video_content = requests.get(url=video_url, headers=headers).content
    # 获得音频内容和视频内容
    with open('audio\\' + title + '.mp3', mode='wb') as audio:
        audio.write(audio_content)
    with open('video\\' + title + '.mp4', mode='wb') as video:
        video.write(video_content)
    # 音频内容和视频内容合并
    cmd = f"ffmpeg -i E:\\爬虫\\video\\{title}.mp4 -i E:\\爬虫\\audio\\{title}.mp3 -c:v copy -c:a aac -strict experimental " \
          f"E:\\爬虫\\video\\{title}output.mp4 "
    # print(cmd)
    subprocess.run(cmd, shell=True)