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 import argparse
  31 import feedparser
  32 try:
  33     import urlparse
  34 except ImportError:
  35     pass
  36 import urllib2
  37 try:
  38     import urllib2.urlparse as urlparse
  39 except ImportError:
  40     pass
  41 import sys
  42
  43 def main(url):
  44     page = urllib2.urlopen(url).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     return title+'.ts'
  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         size = 0
  81         for url in segments:
  82             ufile = urllib2.urlopen(url)
  83             print "\r{} MB".format(size/1024/1024),
  84             sys.stdout.flush()
  85             if decrypt:
  86                 iv=struct.pack("IIII",segment,0,0,0)
  87                 decryptor = AES.new(key, AES.MODE_CBC, iv)
  88             while(True):
  89                 buf = ufile.read(1024)
  90                 if buf:
  91                     if decrypt:
  92                         buf = decryptor.decrypt(buf)
  93                     ofile.write(buf)
  94                     size += len(buf)
  95                 else:
  96                     ufile.close()
  97                     break
  98             segment += 1
  99
 100 def parse_playlist(playlist):
 101     assert playlist.startswith("#EXTM3U")
 102     playlist = playlist.splitlines()[1:]
 103     items=[]
 104     for (metadata_string,url) in zip(playlist[0::2], playlist[1::2]):
 105         md = dict()
 106         assert 'EXT-X-STREAM-INF' in metadata_string.split(':')[0]
 107         for item in metadata_string.split(':')[1].split(','):
 108             if '=' in item:
 109                 md.update([item.split('='),])
 110         md['url']=url
 111         items.append(md)
 112     return items
 113
 114 def parse_segment_playlist(playlist):
 115     assert playlist.startswith("#EXTM3U")
 116     PATTERN = re.compile(r'''((?:[^,"']|"[^"]*"|'[^']*')+)''')
 117     segments = []
 118     next_is_url=False
 119     metadata = {}
 120     for row in playlist.splitlines():
 121         if next_is_url:
 122             segments.append(row)
 123             next_is_url=False
 124             continue
 125         if 'EXTINF' in row:
 126             next_is_url=True
 127         if "EXT-X-KEY" in row:
 128              row = row.split(':',1)[1] #skip first part
 129              parts = PATTERN.split(row)[1:-1] #do magic re split and keep quoting
 130              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
 131     return(segments, metadata)
 132
 133 if __name__ == "__main__":
 134     parser = argparse.ArgumentParser()
 135     parser.add_argument("-r", "--rss", help="Download all files in rss",
 136                     action="store_true")
 137     parser.add_argument("url")
 138     args = parser.parse_args()
 139     if args.rss:
 140         d = feedparser.parse(args.url)
 141         for e in d.entries:
 142             print("Downloading: %s"%e.title)
 143             filename = main(e.link)
 144             print Popen(["avconv","-i",filename,"-vcodec","copy","-acodec","copy", filename+'.mkv'], stdout=PIPE).communicate()[0]
 145         #print(e.description)
 146     else:
 147         filename = main(args.url)
 148         print("Saved to {}".format(filename))