1 Star 1 Fork 27

chishubiao/youku_fetch_video

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
该仓库未声明开源许可证文件(LICENSE),使用请关注具体项目描述及其代码上游依赖。
克隆/下载
fcflv.py 6.47 KB
一键复制 编辑 原始数据 按行查看 历史
#!/usr/bin/python
#coding=utf-8
from __future__ import division
import re
import sys
import urllib
import urllib2
import datetime
import json
import time
import random
import decimal
import threading
from common import *
reload(sys)
sys.setdefaultencoding('utf-8')
'''
视频解析类
'''
class FCFLV(object):
def __init__(self):
self.url = ""
self.headers = {"Accept":"*/*", "Accept-Language":"zh-CN", "":"",
"User-Agent":"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1482.0 Safari/537.36",
#"Accept-Encoding":"gzip, deflate",
"Pragma":"no-cache",
"Content-type":"text/html; charset=UTF-8",
"Cache-Control":"no-cache",
"Connection":"Keep-Alive"}
self.openapi= 'http://v.youku.com/player/getPlayList/VideoIDS/'
def fcFLV(self, url):
pattern = r'^http:\/\/www.youku.com/show_page/id_([\w=]+).html(?(\w)+=\d)*'
if (re.match(pattern, url)==None):
print u'你输入的地址不正确'
return False
else:
req = urllib2.Request(url, headers=self.headers)
content = urllib2.urlopen(req).read()
pattern = '<a\s+href=[\'\"](?P<download_url>\S+)[\'\"]\s+title=(.*)charset=(.*)target=(.*)[\'\"]>(.*)<\/a>'
links = re.compile(r''+pattern+'', re.IGNORECASE).finditer(content)
download_url=[]
threads=[]
if links != None:
for url in links:
download_url.append(url.group('download_url'))
print url.group('download_url')
for durl in download_url:
threads.append(threading.Thread(target=self.parse, args=(durl,)))
for i, t in enumerate(threads):
t.start()
time.sleep(2)
for t in threads:
t.join()
else:
print("URL Not Found")
return False
return True
def parse(self, url):
videoIDS=self.find_video_id_from_url(url)
if videoIDS == False:
print u'你输入的地址不正确'
return False
self.url = self.openapi + videoIDS
req = urllib2.Request(url=self.url, headers=self.headers)
res = urllib2.urlopen(req)
content = res.read()
videoData = json.loads(content)
if (videoData['data'][0].has_key('error')):
show_error=videoData['data'][0]['error']
raise Exception(u'该视频仅对好友公开,或该视频已被删除!Invalid youku error: '+show_error)
#检测支持格式,默认是mp4, 不支持mp4就用flv
if "flv" in videoData['data'][0]['streamfileids']:
fileid = videoData['data'][0]['streamfileids']['flv']
if "mp4" in videoData['data'][0]['streamfileids']:
fileid = videoData['data'][0]['streamfileids']['mp4']
if "flv" in videoData['data'][0]['segs']:
media_blocks = videoData['data'][0]['segs']['flv']
media_flag="flv"
if "mp4" in videoData['data'][0]['segs']:
media_blocks = videoData['data'][0]['segs']['mp4']
media_flag="mp4"
title = videoData['data'][0]['title']
ct = videoData['data'][0]['ct']
cs = videoData['data'][0]['cs']
img_src = videoData['data'][0]['logo']
key1 = videoData['data'][0]['key1']
key2 = videoData['data'][0]['key2']
seed = videoData['data'][0]['seed']
userid = videoData['data'][0]['userid']
videoid = videoData['data'][0]['videoid']
#时间总长
totalsec = videoData['data'][0]['seconds']
#showid_v2 = videoData['data'][0]['show']['showid']
#paid = videoData['data'][0]['show']['paid']
#copyright = videoData['data'][0]['show']['copyright']
#theaterid = videoData['data'][0]['show']['theaterid']
#以上内容是获得播放列表中的四个关键值,key1,key2,fileid,seed;
sid = self.getSid()
fid = self.getFileId(fileid, seed)
blocks_key = self.getKey(media_blocks)
#生成分段视频链接
youku_file_url = "http://f.youku.com/player/getFlvPath/sid/"
total_blocks = len(media_blocks)
i = 0;
urls = []
while i<total_blocks :
if i<= 15:
block = '0'+ ("%x" % i )
else:
block = ("%x" % i)
hex_current_block = block.upper()
new_s1 = fid[0:8] + re.sub('^\d{2}', hex_current_block, fid[8:len(fid)])
#result = re.sub(pattern, replacement, subject)
url = youku_file_url + sid + '_' + hex_current_block + "/st/"+media_flag+"/fileid/" + new_s1 + "?K=" + blocks_key[i]
urls.append((url, int(media_blocks[i]['size'])))
i+=1
urls, sizes = zip(*urls)
total_size = sum(sizes)
for val in urls:
print val
download_urls(urls, title, media_flag, total_size, '.')
return True
def getSid(self):
sid = str(int(time.time()))+str(random.randint(0,9000)+10000)
return sid
def getFileId(self, fileid, seed):
mixed = self.getMixString(seed)
ids = fileid.split('*')
del ids[len(ids)-1]
readId = ''
i=0
while i<len(ids):
idx = int(ids[i])
readId+= mixed[idx:(idx+1)]
i+=1
return readId
@staticmethod
def getMixString(seed):
source = list('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\\:._-1234567890')
mixed =''
while source:
seed = (int(seed) * 211 + 30031) % 65536
index = int( (seed / 65536) * len(source) )
c = source.pop(index)
mixed += str(c)
return mixed
@staticmethod
def getKey(k):
arr = []
for val in k:
arr.append(val['k'])
return arr
@staticmethod
def find_video_id_from_url(url):
rs = re.match(r'^http://v.youku.com/v_show/id_([\w=]+).html', url)
if rs == None:
return False
else:
return rs.group(1)
if __name__ == "__main__":
fcflv = FCFLV()
#fcflv.parse('http://v.youku.com/v_show/id_XNjA1MTg0NDE2.html?firsttime=2292')
fcflv.parse(sys.argv[1])
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
1
https://gitee.com/cylinux_admin/youku_fetch_video.git
[email protected]:cylinux_admin/youku_fetch_video.git
cylinux_admin
youku_fetch_video
youku_fetch_video
master

搜索帮助