Python 爬虫 Vimeo视频下载链接

python vimeo_d.py https://vimeo.com/228013581

在https://vimeo.com/上看到稀罕的视频按照上面加上视频的观看地址运行即可获得视频下载链接支持三种方式爬取下载

（为了凑够150字+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++）

 1 #coding:utf-8
 2 #sample url = 'https://vimeo.com/228013581'
 3 
 4 
 5 import requests
 6 import json
 7 import sys
 8 import re
 9 reload(sys)
10 sys.setdefaultencoding('utf-8')
11 
12 headers ={
13     'Accept-Encoding':'gzip, deflate, br',
14     'Accept-Language':'zh-CN,zh;q=0.8,en;q=0.6',
15     'Connection':'keep-alive',
16     'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36'
17 }
18 
19 def process_1(cmd,url,headers):
20     _url = '%s?action=load_download_config' % url
21 
22     headers['Host']='vimeo.com'
23     headers['Referer']='%s' % url
24     headers['X-Requested-With']='XMLHttpRequest'
25 
26     r = requests.get(_url,headers=headers)
27     if str(r.status_code) =='200':
28         f = r.json()['files']
29         for i in range(0,len(f)):
30             ml = f[i]
31             print "第%s条Download信息" % (i+1)
32             print '标题: %s' % ml['download_name']
33             print '链接: %s' % ml['download_url']
34             print ml['download_name'].split('_')[0]
35 
36 def process_2(cmd,url,headers):
37     _url = 'http://savevideo.me/get/'
38 
39     headers['Content-Type']='application/x-www-form-urlencoded; charset=UTF-8'
40     headers['Host']='savevideo.me'
41     headers['Origin']='http://savevideo.me'
42     headers['Referer']='http://savevideo.me/'
43 
44     r = requests.post(_url,headers=headers,data={'url':url})
45     if str(r.status_code) == '200':
46         title = re.findall(r"<a.*?href="(.*?)">D.*?</a>",r.text,re.S)
47         print title
48 
49 def process_3(cmd,url,headers):
50     _url = url
51 
52     r = requests.get(_url)
53     if str(r.status_code)=='200':
54         title = re.findall(r"<script>.*?"config_url.*?"(http.*?)".*?",r.text,re.S)
55         _url = title[0].replace('\/\/player','//player').replace('\/video\/','/video/').replace('\/config','/config')
56         _r = requests.get(_url)
57         if str(_r.status_code) == '200':
58             f = _r.json()['request']['files']['progressive']
59             q = _r.json()['video']['title']
60             print '标题:%s' % q
61             for i in range(0,len(f)):
62                 width = f[i]['width']
63                 height= f[i]['height']
64                 url = f[i]['url']
65                 quality = f[i]['quality']
66                 print "第%s条Download信息" % (i+1)
67                 print "质量%s*%s(mp4)" % (width,height)
68                 print "链接%s" % (url)
69 
70 
71 if __name__ == '__main__':
72     import sys
73     ml = eval("'parse',sys.argv[1],headers")
74     cmd, url, headers = ml
75     process_1(cmd,url,headers)
76     process_2(cmd,url,headers)
77     process_3(cmd,url,headers)