爬虫4: 把li视频网站的视频抓取到本地

最新推荐文章于 2025-07-22 10:18:52 发布

原创最新推荐文章于 2025-07-22 10:18:52 发布 · 642 阅读

4 ·

CC 4.0 BY-SA版权

文章标签：

#爬虫 #音视频 #python #程序人生

DataSci2.爬虫专栏收录该内容

6 篇文章

订阅专栏

1.获取在XHR中捕获的srcUrl

2.修改srcUrl内容, 使其转为视频下载地址video_XHR_url

3.根据video_XHR_url下载视频并保存

import requests
# 1.获取在XHR中捕获的srcUrl
page_url='https://www.pearvideo.com/video_1796692'
video_id=page_url.split("_")[1]
video_XHR=f'https://www.pearvideo.com/videoStatus.jsp?contId{video_id}&mrd=0.3002955535528544'

headers={
"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36",
# 防盗链, 追溯上一级页面地址
"referer":page_url
}
resp=requests.get(video_XHR,headers=headers)

# 修改srcUrl内容, 使其转为视频下载地址video_XHR_url
systime=resp.json()["systemTime"]
video_XHR_url=resp.json()["videoInfo"]["videos"]["srcUrl"]
video_XHR_url=video_XHR_url.replace(systime, f"cont-{video_id}")

# 下载视频并保存
with open(r"CCTV.mp4","wb") as f:
video=requests.get(video_XHR_url).content
f.write(video)

import requests
# 1.获取在XHR中捕获的srcUrl
page_url='https://www.pearvideo.com/video_1796692'
video_id=page_url.split("_")[1]
video_XHR=f'https://www.pearvideo.com/videoStatus.jsp?contId{video_id}&mrd=0.3002955535528544'

headers={
    "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36",
    # 防盗链, 追溯上一级页面地址
    "referer":page_url
}
resp=requests.get(video_XHR,headers=headers)

# 修改srcUrl内容, 使其转为视频下载地址video_XHR_url
systime=resp.json()["systemTime"]
video_XHR_url=resp.json()["videoInfo"]["videos"]["srcUrl"]
video_XHR_url=video_XHR_url.replace(systime, f"cont-{video_id}")

# 下载视频并保存
with open(r"CCTV.mp4","wb") as f:
    video=requests.get(video_XHR_url).content
    f.write(video)