svtplaydump.py

   1 #!/usr/bin/env python
   2 # -*- coding: utf-8 -*-
   3 #
   4 #   (C) Copyright 2010 Mikael Frykholm <mikael@frykholm.com>
   5 #
   6 #   This program is free software: you can redistribute it and/or modify
   7 #   it under the terms of the GNU General Public License as published by
   8 #   the Free Software Foundation, either version 3 of the License, or
   9 #   (at your option) any later version.
  10 #
  11 #   This program is distributed in the hope that it will be useful,
  12 #   but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 #   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 #   GNU General Public License for more details.
  15 #
  16 #   You should have received a copy of the GNU General Public License
  17 #   along with this program.  If not, see <http://www.gnu.org/licenses/>
  18 #
  19 # Changelog:
  20 # 0.3 added apple streaming playlist parsing and decryption
  21 # 0.2 added python 2.4 urlparse compatibility
  22 # 0.1 initial release
  23
  24 from BeautifulSoup import BeautifulSoup
  25 from subprocess import *
  26 import re
  27 import json
  28 from Crypto.Cipher import AES
  29 import struct
  30 try:
  31     import urlparse
  32 except ImportError:
  33     pass
  34 import urllib2
  35 try:
  36     import urllib2.urlparse as urlparse
  37 except ImportError:
  38     pass
  39 import sys
  40
  41 def main(argv=None):
  42     if argv is None:
  43         argv=sys.argv
  44     page = urllib2.urlopen(argv[1]).read()
  45     soup = BeautifulSoup(page,convertEntities=BeautifulSoup.HTML_ENTITIES)
  46     videoid = re.findall("svt_article_id=(.*)[&]*",page)[0]
  47     flashvars = json.loads(urllib2.urlopen("http://www.svt.se/wd?widgetId=248134&sectionId=1024&articleId=%s&position=0&format=json&type=embed&contextSectionId=1024"%videoid).read())
  48     try:
  49         title = soup.find('meta',{'property':'og:title'}).attrMap['content']
  50     except:
  51         title = "unnamed"
  52     if 'dynamicStreams' in flashvars:
  53         url = flashvars['dynamicStreams'][0].split('url:')[1].split('.mp4,')[0] +'.mp4'
  54         filename = title+".mp4"
  55         print Popen(["rtmpdump",u"-o"+filename,"-r", url], stdout=PIPE).communicate()[0]
  56     if 'pathflv' in flashvars:
  57         rtmp = flashvars['pathflv'][0]
  58         filename = title+".flv"
  59         print Popen(["mplayer","-dumpstream","-dumpfile",filename, rtmp], stdout=PIPE).communicate()[0]
  60     if 'video' in flashvars:
  61         for reference in flashvars['video']['videoReferences']:
  62             if reference['url'].endswith("m3u8"):
  63                 url=reference['url']
  64         download_from_playlist(url, title+'.ts')
  65     else:
  66         print "Could not find any streams"
  67         return
  68
  69 def download_from_playlist(url, title):
  70     playlist = parse_playlist(urllib2.urlopen(url).read())
  71     videourl = sorted(playlist, key=lambda k: int(k['BANDWIDTH']))[-1]['url']
  72     segments, metadata = parse_segment_playlist(urllib2.urlopen(videourl).read())
  73     if "EXT-X-KEY" in metadata:
  74         key = urllib2.urlopen(metadata["EXT-X-KEY"]['URI'].strip('"')).read()
  75         decrypt=True
  76     else:
  77         decrypt=False
  78     with open("%s"%title,"w") as ofile:
  79         segment=0
  80         for url in segments:
  81             print "Downloading: %s"%(url)
  82             ufile = urllib2.urlopen(url)
  83             if decrypt:
  84                 iv=struct.pack("IIII",segment,0,0,0)
  85                 decryptor = AES.new(key, AES.MODE_CBC, iv)
  86             while(True):
  87                 buf = ufile.read(1024)
  88                 if buf:
  89                     if decrypt:
  90                         buf = decryptor.decrypt(buf)
  91                     ofile.write(buf)
  92                 else:
  93                     ufile.close()
  94                     break
  95             segment += 1
  96
  97 def parse_playlist(playlist):
  98     assert playlist.startswith("#EXTM3U")
  99     playlist = playlist.splitlines()[1:]
 100     items=[]
 101     for (metadata_string,url) in zip(playlist[0::2], playlist[1::2]):
 102         md = dict()
 103         assert 'EXT-X-STREAM-INF' in metadata_string.split(':')[0]
 104         for item in metadata_string.split(':')[1].split(','):
 105             if '=' in item:
 106                 md.update([item.split('='),])
 107         md['url']=url
 108         items.append(md)
 109     return items
 110
 111 def parse_segment_playlist(playlist):
 112     assert playlist.startswith("#EXTM3U")
 113     PATTERN = re.compile(r'''((?:[^,"']|"[^"]*"|'[^']*')+)''')
 114     segments = []
 115     next_is_url=False
 116     metadata = {}
 117     for row in playlist.splitlines():
 118         if next_is_url:
 119             segments.append(row)
 120             next_is_url=False
 121             continue
 122         if 'EXTINF' in row:
 123             next_is_url=True
 124         if "EXT-X-KEY" in row:
 125              row = row.split(':',1)[1] #skip first part
 126              parts = PATTERN.split(row)[1:-1] #do magic re split and keep quoting
 127              metadata["EXT-X-KEY"] = dict([part.split('=',1) for part in parts if '=' in part]) #throw away the commas and make dict of the pairs
 128     return(segments, metadata)
 129
 130 if __name__ == "__main__":
 131     sys.exit(main())