python requests库 爬取视频

python requests库 爬取视频

一、总结

一句话总结：

爬取视频操作和爬取图片操作比较类似，我们可以设置请求中的stream参数来选择以一整个块的方式来爬取视频或者以流的方式爬取

# 显示下载视频的进度
import requests
headers = {
    "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36",
}
url ="https://video.pearvideo.com/mp4/adshort/20200709/cont-1684816-15252785_adpkg-ad_hd.mp4"
response = requests.get(url,headers=headers,stream=True)
print(response.status_code)
print(response.headers['content-length'])
content_size = int(response.headers['content-length'])
# print(response.text)
# print(response.content)
n = 1
with open("v.mp4","wb") as f:
    for i in response.iter_content(chunk_size=1024):
        rate=n*1024/content_size
        print("下载进度：{0:%}".format(rate))
        f.write(i)
        n+=1
    print("下载完成")

1、爬虫如何获取视频的大小？

用响应头里面的content-length属性即可，即response.headers['content-length']

二、python requests库 爬取视频

转自或参考：

import requests


# 下载视频
def download(url):
    with requests.get(url, stream=True) as r:
        print('开始下载。。。')
        with open('v.mp4', 'wb')as f:
            for i in r.iter_content(chunk_size=1024):
                f.write(i)
    print('下载结束')


# 带下载进度下载视频
def download_level2(url):
    with requests.get(url, stream=True) as r:
        print('开始下载。。。')
        content_size = int(r.headers['content-length'])
        with open('v.mp4', 'wb')as f:
            n = 1
            for i in r.iter_content(chunk_size=1024):
                loaded = n * 1024.0 / content_size
                print(loaded)
                f.write(i)
                print('已下载{0:%}'.format(loaded))
                n += 1
    print('下载结束')


if __name__ == '__main__':
    URL = 'http://tb-video.bdstatic.com/tieba-smallvideo-transcode/3853363_adac7ec8907890797b3970e570aba43a_140b8b74a014_3.mp4'
    # 下载视频
    # download(URL)
    # 带下载进度
    download_level2(URL)