爬取单页视频

爬取单页视频

import urllib.request
import urllib
import re

url = “http://www.budejie.com/video”
req = urllib.request.build_opener()
headers=(“User-Agent”,
“Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36”)

强调内容此处必须这样，因为addheaders后必须是列表形式才能给他赋值

req.addheaders = [headers]
urllib.request.install_opener(req)
html = urllib.request.urlopen(url).read()
html = str(html)
reg = r’data-mp4=”(.*?)”’ #r目的是以原生字符串转义，不会改变类似于”\n”这样的字符串
for i in re.findall(reg, html): #找到视频地址
filename = i.split(“/”)[-1] #提取出文件名
print (“正在下载%s” %filename)
urllib.request.urlretrieve(i, “D://Test/%s” %filename) #下载
print (filename+”下载成功”)
print (“下载完成”)