python基础爬虫 视频的下载

python爬虫对于短视频爬取的案解析

案件如下：url 为 https://www.pearvideo.com/

# -*- coding: utf-8 -*-
import requests
import re

# srcUrl="(.*?)",vdoUrl
# https://video.pearvideo.com/mp4/short/20200108/cont-1640135-14776159-hd.mp4
# https://www.pearvideo.com/video_1640135

headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36",
}
url = "https://www.pearvideo.com/"
#   把视频下载封装下  提供    url  视频链接 path 保存路径
def download_file(url, path):
    with requests.get(url, stream=True) as r:
        chunk_size = 1024
        content_size = int(r.headers['content-length'])
        print("开始下载...")
        with open(path, "wb") as f:
            for chunk in r.iter_content(chunk_size=chunk_size):
                f.write(chunk)
#   获取首页url 的内容为  下面-- request 
req = requests.get(url=url,headers=headers)   #  只爬取一页短视频  想要获取多页  参考上一篇音乐资源的爬取
request = req.text
# print(req.text)

list_urls = []
# 正则匹配 所需单个视频的一段 为下面拼接做前提
pat1 = 'href="(.*?)" class="vervideo-lilink actplay"'
list_url = re.findall(pat1,request)

list_urls.extend(list_url)
video = None
for i in range(0,len(list_urls)):   #  如 上篇文章一样 遍历 然后拼接视频url地址
    video = i
    new_path = "D:\\video\\{}.mp4".format(video)
    new_url = url+list_urls[i]
    reqs = requests.get(url=new_url,headers=headers)
    new_url_request = reqs.text
    pat2 = 'srcUrl="(.*?)",vdoUrl'
    last_url = re.findall(pat2,new_url_request)[0]
    download_file(last_url, new_path)   #  调用 上面封装的函数  下载视频 
    print(last_url)

爬取结果如图所示

希望对你有所启发 有疑问 欢迎评论