html5怎么爬虫,python - 爬虫爬取html5页面上的视频是怎样的一种处理方式的

以这个为例：http://www.imooc.com/video/10903

在f12时候可以看到这一串信息

但在我处理页面的时候都没发现有这链接

这页面需要登入之后才能看，我已经处理了登入程序，可以正常登入，但在用session.get这页面时候，找不到上面的链接信息。

以下是我的代码：

from bs4 import BeautifulSoup

import requests

import configparser

import json

imooc_url = r'http://www.imooc.com'

login_session = requests.session()

headers = {

"Accept":"application/json, text/javascript, */*; q=0.01",

"Accept-Encoding":"gzip, deflate",

"Accept-Language":"zh-CN,zh;q=0.8",

"Connection":"keep-alive",

"Host":"www.imooc.com",

"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.80 Safari/537.36",

"X-Requested-With":"XMLHttpRequest"

}

class imoocLogin(object):

def __init__(self,configfile):

self.loginurl = r'http://www.imooc.com/passport/user/login'

config = configparser.ConfigParser()

config.read(configfile)

configname = 'imooc'

self.username = config.get(configname,'username')

self.password = config.get(configname,'password')

def startLogin(self):

login_text = requests.get(imooc_url).text

login_soup = BeautifulSoup(login_text,'lxml')

verify = login_soup.find_all('img',class_="verify-img")

print "verify: %s" %verify

if verify:

for verify_data in verify:

verify_data = verify_data.get('src')

verify_url = imooc_url+verify_data

print verify_url

verify_data = raw_input('input verify:')

login_data = {

"username":self.username,

"password":self.password,

"remember":'1',

"verify":verify_data,

"referer":"http://www.imooc.com"

}

else:

login_data = {

"username":self.username,

"password":self.password,

"remember":"1",

"referer":"http://www.imooc.com"

}

print 'ddddddddddddd'

s_login = login_session.post(self.loginurl,data=login_data,headers=headers)

print 'wwwwwwwwwwwwww'

print(s_login)

print s_login.json()

print type(s_login.json())

for k,v in s_login.json().items():

print k,v

# print json.dump(s_login.json(),indent=4,sort_keys=True)

if __name__=='__main__':

abc_url = r'http://www.imooc.com/video/10903'

user_url = r'http://www.imooc.com/u/1322083/courses'

loginPro = imoocLogin('config.ini')

loginPro.startLogin()

video_url = login_session.get(abc_url,headers=headers).text

video_soup = BeautifulSoup(video_url,'lxml')

print video_soup

html5页面上的东西是不是还需要其他的处理的？搞不懂为咋获取不到的。