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
CYB35324 小时前
R&S 罗德与施瓦茨 R&S VTC-VTE-VTS 视频测试仪
音视频
sweetone6 小时前
夏普LCD-46LX530A液晶电视机不开机故障之小修(包含RUNTKA829WJQZ电源板实测电路图)
经验分享·音视频
美狐美颜SDK开放平台6 小时前
从采集到渲染:直播APP开发中视频美颜SDK工作原理详解
人工智能·音视频·实时音视频·美颜sdk·视频美颜sdk·美颜api
Henrii_历小海7 小时前
WhatsApp Cloud API 媒体消息全链路:上传协议、类型约束、图片/视频预处理与发送管线
音视频·媒体
对讲机数码科普9 小时前
哈尔滨对讲机无声、音量小、喇叭破音故障修复 香坊双工电子音频组件专项维保
音视频
dualven_in_csdn12 小时前
【摄像头】虚拟摄像头
音视频
小二·14 小时前
多模态RAG实战:用LangChain+Milvus打造支持图文音视频的企业级知识库
langchain·音视频·milvus
田里的水稻15 小时前
EP_局域网传输音视频的主流方案
运维·人工智能·机器人·音视频
hz5678915 小时前
手术示教及远程会诊系统一体化方案:赋能医院教学与精准诊疗
安全·音视频·实时音视频·信息与通信
潜创微科技15 小时前
ITE联阳IT6520:Type-C口进、双MIPI出,一颗芯片把PD充电+DP视频+2屏驱动全包了
音视频