网页编程网

# -*- coding: utf-8 -*-
import requests
import urllib.request#下载方法
import re
from importlib import reload
import sys

reload(sys)#设编码，删除也可
url_name=[]
#新建一个函数，获取数据
def get():
    headers={
            'User-Agent':'Mozilla/5.0 (Windows NT 6.1; ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/82.0.4068.4 Safari/537.36'
            }
    url='http://www.budejie.com/video/'
    html=requests.get(url,headers=headers).text
    #print(html)
    #r是保留字符串原有的意思
    url_content=re.compile(r'(<div class="j-r-list-c">.*?</div>.*?</div>)',re.S)
    contents=re.findall(url_content,html)
    for i in contents:
        url_reg=r'data-mp4="(.*")'#视频地址
        url_it=re.findall(url_reg,i)
        if url_it:#有些视频看不了，不存在的
            name_reg=re.compile(r'<a href="/detail-.{8}.html">(.*?)</a>',re.S)
            name_it=re.findall(name_reg,i)
            #print(name_it)
        for i,k in zip(name_it,url_it):#zip将对应元素打包成元组
            url_name.append([i,k])
    
    for i in url_name:#i[0]=name i[1]=url
        urllib.request.urlretrieve(i[1],r'video\%s.mp4' %str(i[0]))
        print('down...'+i[0])
    
if __name__  =='__main__':  
    get()