爬取tx视频

python 复制代码
import requests
import re
import pprint
from tqdm import tqdm
url = 'https://vd6.l.qq.com/proxyhttp'
data = {
    "adparam": "adType=preAd&vid=i0046sewh4r&sspKey=wswd",
    "buid": "vinfoad",
    "sspAdParam": "{\"ad_scene\":1,\"pre_ad_params\":{\"ad_scene\":1,\"user_type\":2,\"video\":{\"base\":{\"vid\":\"i0046sewh4r\",\"cid\":\"mzc00200xf3rir6\"},\"is_live\":false,\"type_id\":3,\"referer\":\"https://v.qq.com/channel/cartoon\",\"url\":\"https://v.qq.com/x/cover/mzc00200xf3rir6/i0046sewh4r.html\",\"flow_id\":\"12c49b0148a070b463c19b22b07a2034\",\"refresh_id\":\"7603483fb7735e21aa757c17a941620b_1708859388\",\"fmt\":\"hd\"},\"platform\":{\"guid\":\"5c0d295e0ff4d662\",\"channel_id\":0,\"site\":\"web\",\"platform\":\"in\",\"from\":0,\"device\":\"pc\",\"play_platform\":10201,\"pv_tag\":\"cn_bing_com|channel\",\"support_click_scan_integration\":true},\"player\":{\"version\":\"1.30.10\",\"plugin\":\"3.4.49\",\"switch\":1,\"play_type\":\"0\"},\"token\":{\"type\":1,\"vuid\":394241996,\"vuser_session\":\"yBkJUvSaBx9BoemqfNvI9g.M\",\"app_id\":\"101483052\",\"open_id\":\"67CCE33CD137331E1EBE8BEB3A673CA9\",\"access_token\":\"10C9D6EB7957BF26D29F1FC1E0C6C584\"}}}",
    "vinfoparam": "charge=0&otype=ojson&defnpayver=3&spau=1&spaudio=0&spwm=1&sphls=2&host=v.qq.com&refer=https%3A%2F%2Fv.qq.com%2Fx%2Fcover%2Fmzc00200xf3rir6%2Fi0046sewh4r.html&ehost=https%3A%2F%2Fv.qq.com%2Fx%2Fcover%2Fmzc00200xf3rir6%2Fi0046sewh4r.html&sphttps=1&encryptVer=9.2&cKey=EdO-OrXxl6W1Mc1Orq2-LnCjnpb8Ocr0cPTcH_2PzEul_f4vOWcoUmJPd8rTtrI9OVVA0wNXkhhz_4LVGCTZlxo--_XGuZWLjvmpaTXWr2DNOLGAi4iBp92IyPY9pJacm0SuoYMK5cclDyKh6cqchEKDlC2uGzpCCamWfdlZnHB5x6wVJHKsVyf3svRoLvLp4yt5irIvBazTFI6klX7qSYlxDPbyyf8e8SL3SEnu3RmvgibC5O696HeQxGSo4VOM35yfH6ml6Md27yDn8qJE56sunEyjWSbSstS_5B9-E8AnI4GF1djs5-uKo6GxqIcXJIUV87h2tMf3dK_nyIsyhKhOxYaKK-hZOuXwJ_9Azca2s1AGdWwZi7dSQjVD3QIqMKZsPLJBfqdonJgzpKI-zf7tPsma4I3itUH2mrJQ1t1eiMXOOgHDgPCj5Hqs5MBScLzt8CKeI50CFA5m8jmdx0UZ9fmN6AoQSIe8G9z4YoaLU_i1lZrcZ9k3VTDRFzAKGxinZ2F5WudDNC1ArujtJDazWU-cAwMDemsQ-A&clip=4&guid=5c0d295e0ff4d662&flowid=12c49b0148a070b463c19b22b07a2034&platform=10201&sdtfrom=v1010&appVer=1.30.10&unid=&auth_from=&auth_ext=&vid=i0046sewh4r&defn=&fhdswitch=0&dtype=3&spsrt=2&tm=1708859485&lang_code=0&logintoken=%7B%22access_token%22%3A%2210C9D6EB7957BF26D29F1FC1E0C6C584%22%2C%22appid%22%3A%22101483052%22%2C%22vusession%22%3A%22yBkJUvSaBx9BoemqfNvI9g.M%22%2C%22openid%22%3A%2267CCE33CD137331E1EBE8BEB3A673CA9%22%2C%22vuserid%22%3A%22394241996%22%2C%22video_guid%22%3A%225c0d295e0ff4d662%22%2C%22main_login%22%3A%22qq%22%7D&spvvpay=1&spadseg=3&spav1=15&hevclv=28&spsfrhdr=0&spvideo=0&spm3u8tag=67&spmasterm3u8=3&drm=40"
}
headers = {
    "Referer":"https://v.qq.com/",
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
    "Cookie":"RK=CDOsEWVy0h; ptcz=5f5910e759fd2884ffd2d52d1c28327f145b4c6a0ccca7e5c70c008ad77238bc; eas_sid=61l77025D7U361j4I7T540X3f0; pgv_pvid=6319095440; _qimei_uuid42=181140e1137100212f0fb5b9ad2749c71807166555; _qimei_fingerprint=5d6fc68e5584b64e7b5bba3d425a25c2; _qimei_q36=; _qimei_h38=e147f0c72f0fb5b9ad2749c702000006b18114; qq_domain_video_guid_verify=5c0d295e0ff4d662; o_minduid=8XsP05UE18-_djq9QKbhDmdsNPlsDWs7; pgv_info=ssid=s4700628002; vversion_name=8.2.95; video_omgid=5c0d295e0ff4d662; LPVLturn=898; LPLFturn=522; LPSJturn=300; LVINturn=440; LPHLSturn=603; LDERturn=442; LPPBturn=391; appuser=65C6CEEF9C26AFAB; ad_session_id=e5ri32oscp4dc; LZTturn=513; ufc=r64_1_1708859447"
}

response = requests.post(url=url,json=data,headers=headers)
html_data = response.json()['vinfo']
result = re.findall('url(.*?),',html_data)
m3u8_url = result[4].split('"')[2]
print(m3u8_url)
m3u8_data = requests.get(url=m3u8_url).text
m3u8_data = re.sub('#EXTM3U','',m3u8_data)
m3u8_data = re.sub('#EXT-X-VERSION:\d','',m3u8_data)
m3u8_data = re.sub('#EXT-X-MEDIA-SEQUENCE:\d','',m3u8_data)
m3u8_data = re.sub('#EXT-X-TARGETDURATION:\d+','',m3u8_data)
m3u8_data = re.sub('#EXT-X-PLAYLIST-TYPE:VOD','',m3u8_data)
m3u8_data = re.sub('#EXTINF:\d+\.\d+,','',m3u8_data)
m3u8_data = re.sub('#EXT-X-ENDLIST','',m3u8_data).split()
for ts in tqdm(m3u8_data):
    ts_url = 'https://ltsgdty.gtimg.com/B_MWKVMPpbmmy3lFOlyMFQVb6rtLRlH2V5NtArFWKYahE0djTdSn9bumr7eGey1VLo/svp_50112/sO2V1dWnlkKToKWRfOzI3cR3UhiZ17Z-Skp35KHHp4MrMsBZZetWMgF7OU_vY0Bvjib80b12PzHdbwUwdHwTFffu-wyt7np394Z2MmODF6Z9cJdqcjkIwEIE-F36tNBvL7lvhKZ4GVX_0kcgYIk820iFamTdTC_HWF403MZCQhkJqDjSAzdUpGJu5ptbogcxJY2JN0qIJi4rWxoGaCcT0itnOnp0fdYmoya4rYNcteV_wx-M3xp_qg/'+ts
    ts_content = requests.get(url=ts_url).content
    with open('斗罗大陆.mp4',mode='ab') as f:
        f.write(ts_content)
print('下载完成')

总结:

python 复制代码
    with open('斗罗大陆.mp4',mode='ab') as f:
        f.write(ts_content)

mode = 'ab'表示重复写入,可以把很多个ts文件写成一个

2.与爬取A站视频对比,都是先在xhr找到一个ts片段,然后取链接的参数进行搜索,找到一个链接,访问后能得到类似这样的界面

比较难的是tx中,这个链接难找,通过搜索后找到这样一个包

访问这个包,经过一系列过程,提取其中的一个m3u8链接,访问这个链接后得到最终想要的界面。

注意不要太频繁访问,否则会这样:

相关推荐
学习前端的小z3 小时前
【AI视频】Runway:Gen-2 图文生视频与运动模式详解
人工智能·aigc·音视频
羌俊恩7 小时前
视频服务器:GB28181网络视频协议
服务器·网络·音视频
cuijiecheng20188 小时前
音视频入门基础:AAC专题(3)——AAC的ADTS格式简介
音视频·aac
唯创知音10 小时前
电子烟智能化创新体验:WTK6900P语音交互芯片方案,融合频谱计算、精准语音识别与流畅音频播报
人工智能·单片机·物联网·音视频·智能家居·语音识别
cuijiecheng201813 小时前
音视频入门基础:AAC专题(6)——FFmpeg源码中解码ADTS格式的AAC的Header的实现
ffmpeg·音视频·aac
Rookie也要加油15 小时前
WebRtc一对一视频通话_New_peer信令处理
笔记·学习·音视频·webrtc
heidyxlw18 小时前
局域网视频
音视频
Mr数据杨19 小时前
我的AI工具箱Tauri版-VideoClipMixingCut视频批量混剪
音视频
!学习使我快乐!19 小时前
检测场景变化并将视频按场景分开
音视频
青柠视频云1 天前
青柠视频云——视频丢包(卡顿、花屏、绿屏)排查
服务器·网络·音视频