python爬取慕课视频-python爬虫：爬取网站视频

新建一个py文件，代码如下：

#!/usr/bin/python

# -*- coding: UTF-8 -*-

import urllib,re,requests

import sys

reload(sys)

sys.setdefaultencoding('utf-8')

url_name = [] #url name

def get():

#获取源码

hd = {"User-Agent":"Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36"}

url = 'http://www.budejie.com/video/'

html = requests.get(url,headers=hd).text

url_content = re.compile(r'(

.*?

.*?)',re.S) #编译

url_contents = re.findall(url_content,html) #匹配

for i in url_contents:

#匹配视频

url_reg = r'data-mp4="(.*?)"' #视频地址

url_items = re.findall(url_reg,i)

#print url_items

if url_items: #判断视频是否存在

name_reg = re.compile(r'