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 # 0.4 added mirror mode.
  21 # 0.3 added apple streaming playlist parsing and decryption
  22 # 0.2 added python 2.4 urlparse compatibility
  23 # 0.1 initial release
  24
  25 from BeautifulSoup import BeautifulSoup
  26 from subprocess import *
  27 import re
  28 import json
  29 from Crypto.Cipher import AES
  30 import struct
  31 import argparse
  32 import feedparser
  33 try:
  34     import urlparse
  35 except ImportError:
  36     pass
  37 import urllib2
  38 try:
  39     import urllib2.urlparse as urlparse
  40 except ImportError:
  41     pass
  42 import sys, os
  43
  44 def main(url, title):
  45     """
  46     Try to scrape the site for video and download.
  47     """
  48     if not url.startswith('http'):
  49         url = "http://www.svtplay.se" + url
  50     video = {}
  51     page = urllib2.urlopen(url).read()
  52     soup = BeautifulSoup(page,convertEntities=BeautifulSoup.HTML_ENTITIES)
  53     video_player = soup.body('a',{'data-json-href':True})[0]
  54     flashvars = json.loads(urllib2.urlopen("http://www.svtplay.se/%s"%video_player.attrMap['data-json-href']+"?output=json").read())
  55     video['title'] = title
  56     if not title:
  57         video['title'] = soup.find('meta',{'property':'og:title'}).attrMap['content'].replace('|','_').replace('/','_')
  58     if 'dynamicStreams' in flashvars:
  59         video['url'] = flashvars['dynamicStreams'][0].split('url:')[1].split('.mp4,')[0] +'.mp4'
  60         filename = video['title']+".mp4"
  61         print Popen(["rtmpdump",u"-o"+filename,"-r", url], stdout=PIPE).communicate()[0]
  62     if 'pathflv' in flashvars:
  63         rtmp = flashvars['pathflv'][0]
  64         filename = video['title']+".flv"
  65         print Popen(["mplayer","-dumpstream","-dumpfile",filename, rtmp], stdout=PIPE).communicate()[0]
  66     if 'video' in flashvars:
  67         for reference in flashvars['video']['videoReferences']:
  68             if reference['url'].endswith("m3u8"):
  69                 video['url']=reference['url']
  70                 video['filename'] = video['title']+'.ts'
  71                 if 'statistics' in flashvars:
  72                     video['category'] = flashvars['statistics']['category']
  73         download_from_playlist(video)
  74     else:
  75         print "Could not find any streams"
  76         return
  77     return video
  78
  79 def download_from_playlist(video):
  80     playlist = parse_playlist(urllib2.urlopen(video['url']).read())
  81     videourl = sorted(playlist, key=lambda k: int(k['BANDWIDTH']))[-1]['url']
  82     segments, metadata = parse_segment_playlist(urllib2.urlopen(videourl).read())
  83     if "EXT-X-KEY" in metadata:
  84         key = urllib2.urlopen(metadata["EXT-X-KEY"]['URI'].strip('"')).read()
  85         decrypt=True
  86     else:
  87         decrypt=False
  88     with open("%s"%video['filename'],"w") as ofile:
  89         segment=0
  90         size = 0
  91         for url in segments:
  92             ufile = urllib2.urlopen(url)
  93             print "\r{} MB".format(size/1024/1024),
  94             sys.stdout.flush()
  95             if decrypt:
  96                 iv=struct.pack("IIII",segment,0,0,0)
  97                 decryptor = AES.new(key, AES.MODE_CBC, iv)
  98             while(True):
  99                 buf = ufile.read(1024)
 100                 if buf:
 101                     if decrypt:
 102                         buf = decryptor.decrypt(buf)
 103                     ofile.write(buf)
 104                     size += len(buf)
 105                 else:
 106                     ufile.close()
 107                     break
 108             segment += 1
 109
 110 def parse_playlist(playlist):
 111     if not playlist.startswith("#EXTM3U"):
 112         print playlist
 113         return False
 114     playlist = playlist.splitlines()[1:]
 115     items=[]
 116     for (metadata_string,url) in zip(playlist[0::2], playlist[1::2]):
 117         md = dict()
 118         assert 'EXT-X-STREAM-INF' in metadata_string.split(':')[0]
 119         for item in metadata_string.split(':')[1].split(','):
 120             if '=' in item:
 121                 md.update([item.split('='),])
 122         md['url']=url
 123         items.append(md)
 124     return items
 125
 126 def parse_segment_playlist(playlist):
 127     assert playlist.startswith("#EXTM3U")
 128     PATTERN = re.compile(r'''((?:[^,"']|"[^"]*"|'[^']*')+)''')
 129     segments = []
 130     next_is_url=False
 131     metadata = {}
 132     for row in playlist.splitlines():
 133         if next_is_url:
 134             segments.append(row)
 135             next_is_url=False
 136             continue
 137         if 'EXTINF' in row:
 138             next_is_url=True
 139         if "EXT-X-KEY" in row:
 140              row = row.split(':',1)[1] #skip first part
 141              parts = PATTERN.split(row)[1:-1] #do magic re split and keep quotes
 142              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
 143     return(segments, metadata)
 144 def parse_videolist():
 145     page = urllib2.urlopen("http://www.svtplay.se/ajax/videos?antal=100").read()
 146     soup = BeautifulSoup(page,convertEntities=BeautifulSoup.HTML_ENTITIES)
 147     videos = []
 148     for article in soup.findAll('article'):
 149         meta = dict(article.attrs)
 150         video = {}
 151         video['title'] = meta['data-title']
 152         video['description'] = meta['data-description']
 153         video['url'] = dict(article.find('a').attrs)['href']
 154         videos.append(video)
 155     return videos
 156
 157 if __name__ == "__main__":
 158     parser = argparse.ArgumentParser()
 159     parser.add_argument("-r", "--rss", help="Download all files in rss")
 160     parser.add_argument("-u", "--url", help="Download video in url")
 161     parser.add_argument("-m", "--mirror", help="Mirror all files", action="store_true")
 162
 163     args = parser.parse_args()
 164
 165     if args.rss:
 166         d = feedparser.parse(args.url)
 167         for e in d.entries:
 168             print("Downloading: %s"%e.title)
 169             filename = main(e.link, e.title)
 170             print Popen(["avconv","-i",filename,"-vcodec","copy","-acodec","copy", filename+'.mkv'], stdout=PIPE).communicate()[0]
 171         #print(e.description)
 172     if args.mirror:
 173         for video in parse_videolist():
 174             video['title'] = video['title'].replace('/','_')
 175             print video['title']+'.mkv',
 176             if os.path.exists(video['title']+'.mkv'):
 177                 print "Skipping"
 178                 continue
 179             print("Downloading...")
 180             ret = main(video['url'], video['title'])
 181
 182             print Popen(["avconv","-i",video['title']+'.ts',"-vcodec","copy","-acodec","copy", video['title']+'.mkv'], stdout=PIPE).communicate()[0]
 183             try:
 184                 os.unlink(video['title']+'.ts')
 185             except:
 186                 import pdb;pdb.set_trace()
 187     else:
 188         video = main(args.url, None)
 189         print("Downloaded {}".format(video['title']))