Python爬虫爬取视频的详细介绍(2)-木庄网络博客

发现有很多请求，只能一条一条的分析了，其实视频格式就是那几种mp4，flv，avi了，一下就能看到了，复制到浏览器中打开，果然就是我们想要的下载链接了。

第三步

分析下载链接和视频链接的规律。即http://video.weibo.com/show?fid=1034:0988e59a12e5178acb7f23adc3fe5e97与xxx.mp4的关系。这个又需要分析网页源码了，其实可以注意上面那个以.m3u8后缀的链接,m3u8记录了一个索引纯文本文件，打开它时播放软件并不是播放它，而是根据它的索引找到对应的音视频文件的网络地址进行在线播放,打开看，里面确实记录着我们想要的下载链接。而且.m3u8后缀的链接就在网页源码中。

总结

经过前三步的分析，获取视频下载链接的思路就是先从网页源码中获取.m3u8后缀的链接，下载该文件，从里面得到视频下载链接，最后下载视频就好了

源码

#sinavideo.py
#coding=utf-8
import os
import re
import urllib2
import urllib 
from common import Common
class SinaVideo():
 
    URL_PIRFIX = "http://us.sinaimg.cn/"
    def getM3u8(self,html):
        reg = re.compile(r'list=([\s\S]*?)&fid')
        result = reg.findall(html)
        return result[0]
 
 
    def getName(self,url):
         return url.split('=')[1]
 
    def getSinavideoUrl(self,filepath):
        f = open(filepath,'r')
        lines = f.readlines()
        f.close()
        for line in lines:
            if line[0] !='#':
                return line
 
    def download(self,url,filepath):
        #获取名称
        name = self.getName(url)
        html = Common.getHtml(url)
        m3u8 = self.getM3u8(html)
        Common.download(urllib.unquote(m3u8),filepath,name + '.m3u8')
        url = self.URL_PIRFIX + self.getSinavideoUrl(filepath+name+'.m3u8')
        Common.download(url,filepath,name+'.mp4')

#common.py
#coding=utf-8
import urllib2
import os
import re
 
 
class Common():
    #  获取网页源码
    @staticmethod
    def getHtml(url):
        html = urllib2.urlopen(url).read()
        print  "[+]获取网页源码:"+url
        return html
 
    # 下载文件
    @staticmethod
    def download(url,filepath,filename):
        headers = {
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
            'Accept-Charset': 'UTF-8,*;q=0.5',
            'Accept-Encoding': 'gzip,deflate,sdch',
            'Accept-Language': 'en-US,en;q=0.8',
            'User-Agent': 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'
        }
        request = urllib2.Request(url,headers = headers);
        response = urllib2.urlopen(request)
        path = filepath + filename
        with open(path,'wb') as output:
            while True:
                buffer = response.read(1024*256);
                if not buffer:
                    break
                # received += len(buffer)
                output.write(buffer)
 
        print "[+]下载文件成功:"+path
 
    @staticmethod
    def isExist(filepath):
        return os.path.exists(filepath)
 
    @staticmethod
    def createDir(filepath):
         os.makedirs(filepath,0777)

调用方式：

1 2	`url =` `"http://video.weibo.com/show?fid=1034:0988e59a12e5178acb7f23adc3fe5e97"sinavideo = SinaVideo()` `sinavideo.download(url,""/Users/cheng/Documents/PyScript/res/"")`