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     try:
  45         videoid = re.findall("/video/(.*)[/]*",argv[1])[0]
  46         soup = BeautifulSoup(urllib2.urlopen("http://www.svtplay.se/video/%s/?type=embed"%videoid).read())
  47         flashvars = json.loads(soup.find("param", {"name":"flashvars",'value':True})['value'][5:])
  48     except(IndexError):
  49         page = urllib2.urlopen(argv[1]).read()
  50         videoid = re.findall("svt_article_id=(.*)[&]*",page)[0]
  51         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())
  52     try:
  53         title = flashvars['statistics']['title']
  54     except:
  55         title = "unnamed"
  56     if 'dynamicStreams' in flashvars:
  57         url = flashvars['dynamicStreams'][0].split('url:')[1].split('.mp4,')[0] +'.mp4'
  58         filename = title+".mp4"
  59         print Popen(["rtmpdump",u"-o"+filename,"-r", url], stdout=PIPE).communicate()[0]
  60     if 'pathflv' in flashvars:
  61         rtmp = flashvars['pathflv'][0]
  62         filename = title+".flv"
  63         print Popen(["mplayer","-dumpstream","-dumpfile",filename, rtmp], stdout=PIPE).communicate()[0]
  64     if 'video' in flashvars:
  65         for reference in flashvars['video']['videoReferences']:
  66             if reference['url'].endswith("m3u8"):
  67                 url=reference['url']
  68         download_from_playlist(url, title+'.ts')
  69     else:
  70         print "Could not find any streams"
  71         return
  72
  73 def download_from_playlist(url, title):
  74     playlist = parse_playlist(urllib2.urlopen(url).read())
  75     videourl = sorted(playlist, key=lambda k: int(k['BANDWIDTH']))[-1]['url']
  76     segments, metadata = parse_segment_playlist(urllib2.urlopen(videourl).read())
  77     if "EXT-X-KEY" in metadata:
  78         key = urllib2.urlopen(metadata["EXT-X-KEY"]['URI'].strip('"')).read()
  79         decrypt=True
  80     else:
  81         decrypt=False
  82     with open("%s"%title,"w") as ofile:
  83         segment=0
  84         for url in segments:
  85             print "Downloading: %s"%(url)
  86             ufile = urllib2.urlopen(url)
  87             if decrypt:
  88                 iv=struct.pack("IIII",segment,0,0,0)
  89                 decryptor = AES.new(key, AES.MODE_CBC, iv)
  90             while(True):
  91                 buf = ufile.read(1024)
  92                 if buf:
  93                     if decrypt:
  94                         buf = decryptor.decrypt(buf)
  95                     ofile.write(buf)
  96                 else:
  97                     ufile.close()
  98                     break
  99             segment += 1
 100
 101 def parse_playlist(playlist):
 102     assert playlist.startswith("#EXTM3U")
 103     playlist = playlist.splitlines()[1:]
 104     items=[]
 105     for (metadata_string,url) in zip(playlist[0::2], playlist[1::2]):
 106         md = dict()
 107         assert 'EXT-X-STREAM-INF' in metadata_string.split(':')[0]
 108         for item in metadata_string.split(':')[1].split(','):
 109             if '=' in item:
 110                 md.update([item.split('='),])
 111         md['url']=url
 112         items.append(md)
 113     return items
 114
 115 def parse_segment_playlist(playlist):
 116     assert playlist.startswith("#EXTM3U")
 117     PATTERN = re.compile(r'''((?:[^,"']|"[^"]*"|'[^']*')+)''')
 118     segments = []
 119     next_is_url=False
 120     metadata = {}
 121     for row in playlist.splitlines():
 122         if next_is_url:
 123             segments.append(row)
 124             next_is_url=False
 125             continue
 126         if 'EXTINF' in row:
 127             next_is_url=True
 128         if "EXT-X-KEY" in row:
 129              row = row.split(':',1)[1] #skip first part
 130              parts = PATTERN.split(row)[1:-1] #do magic re split and keep quoting
 131              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
 132     return(segments, metadata)
 133
 134 if __name__ == "__main__":
 135     sys.exit(main())