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+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++） 

#coding:utf-8
#sample url = 'https://vimeo.com/228013581'


import requests
import json
import sys
import re
reload(sys)
sys.setdefaultencoding('utf-8')

headers ={
    'Accept-Encoding':'gzip, deflate, br',
    'Accept-Language':'zh-CN,zh;q=0.8,en;q=0.6',
    'Connection':'keep-alive',
    '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'
}

def process_1(cmd,url,headers):
    _url = '%s?action=load_download_config' % url

    headers['Host']='vimeo.com'
    headers['Referer']='%s' % url
    headers['X-Requested-With']='XMLHttpRequest'

    r = requests.get(_url,headers=headers)
    if str(r.status_code) =='200':
        f = r.json()['files']
        for i in range(0,len(f)):
            ml = f[i]
            print "第%s条Download信息" % (i+1)
            print '标题: %s' % ml['download_name']
            print '链接: %s' % ml['download_url']
            print ml['download_name'].split('_')[0]

def process_2(cmd,url,headers):
    _url = 'http://savevideo.me/get/'

    headers['Content-Type']='application/x-www-form-urlencoded; charset=UTF-8'
    headers['Host']='savevideo.me'
    headers['Origin']='http://savevideo.me'
    headers['Referer']='http://savevideo.me/'

    r = requests.post(_url,headers=headers,data={'url':url})
    if str(r.status_code) == '200':
        title = re.findall(r"<a.*?href=\"(.*?)\">D.*?<\/a>",r.text,re.S)
        print title

def process_3(cmd,url,headers):
    _url = url

    r = requests.get(_url)
    if str(r.status_code)=='200':
        title = re.findall(r"<script>.*?\"config_url.*?\"(http.*?)\".*?",r.text,re.S)
        _url = title[0].replace('\\/\\/player','//player').replace('\\/video\\/','/video/').replace('\\/config','/config')
        _r = requests.get(_url)
        if str(_r.status_code) == '200':
            f = _r.json()['request']['files']['progressive']
            q = _r.json()['video']['title']
            print '标题:%s' % q
            for i in range(0,len(f)):
                width = f[i]['width']
                height= f[i]['height']
                url = f[i]['url']
                quality = f[i]['quality']
                print "第%s条Download信息" % (i+1)
                print "质量%s*%s(mp4)" % (width,height)
                print "链接%s" % (url)


if __name__ == '__main__':
    import sys
    ml = eval("'parse',sys.argv[1],headers")
    cmd, url, headers = ml
    process_1(cmd,url,headers)
    process_2(cmd,url,headers)
    process_3(cmd,url,headers)