1 # -*- coding:utf-8 -*- 
 2 import requests
 3 from lxml import etree
 4 import re
 5 from urllib.request import urlretrieve
 6 #获取视频ID
 7 #拼接完整url
 8 #获取视频播放地址
 9 #下载视频
10 #Python学习交流群：125240963，群内每天分享干货，包括最新的python企业案例学习资料和零基础入门教程，欢迎各位小伙伴入群学习交流
11 
12 def download(url):
13     #url = ‘http://www.pearvideo.com/category_9‘
14     #获取源代码
15     #html = requests.get(url)
16     html = requests.get(url).text
17     #把文本文件处理成可解释的对象
18     #如果我用正则可以不可以也可以
19     html = etree.HTML(html)
20     video_id = html.xpath(‘//div[@class="vervideo-bd"]/a/@href‘)
21     video_url = []
22     starurl = ‘http://www.pearvideo.com‘
23     #完整拼接url
24     for id in video_id:
25         newurl = starurl + ‘/‘ + id
26         video_url.append(newurl)
27     #获取视频播放地址
28     for playurl in video_url:
29         #获取页面源代码
30         html = requests.get(playurl).text
31         #print(playurl)
32         req = ‘srcUrl="(.*?)"‘
33         #视频真正播放地址
34         purl = re.findall(req,html)
35         #print(purl)
36         #获取视频名称
37         req = ‘<h1 class="video-tt">(.*?)</h1>‘
38         pname = re.findall(req,html)
39         print("正在下载:%s"%pname)
40 
41         urlretrieve(purl[0],‘./video/%s.mp4‘%pname[0])
42 #download()
43 
44 def downloadmore():
45     n = 12
46     while True:
47         if n > 48:
48             return
49         url = "http://www.pearvideo.com/category_loading.jsp?reqType=5&categoryId=9&star=%d"%n
50         n+=12
51         download(url)
52 downloadmore()