svtplaydump.py

   1 #!/usr/bin/env python3
   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 bs4 import BeautifulSoup
  26 from subprocess import *
  27 import re
  28 from Crypto.Cipher import AES
  29 import struct
  30 import argparse
  31 import requests
  32 import sys, os
  33
  34 def scrape_player_page(url, title):
  35     """
  36     Try to scrape the site for video and download.
  37     """
  38     if not url.startswith('http'):
  39         url = "http://www.svtplay.se" + url
  40     video = {}
  41     soup = BeautifulSoup(requests.get(url).text)
  42     video_player = soup.body('a',{'data-json-href':True})[0]
  43     if video_player.attrs['data-json-href'].startswith("/wd"):
  44         flashvars = requests.get("http://www.svt.se/%s"%video_player.attrs['data-json-href']).json()
  45     else:
  46         flashvars = requests.get("http://www.svtplay.se/%s"%video_player.attrs['data-json-href']+"?output=json").json()
  47     video['duration'] = video_player.attrs.get('data-length',0)
  48     video['title'] = title
  49     if not title:
  50         video['title'] = soup.find('meta',{'property':'og:title'}).attrs['content'].replace('|','_').replace('/','_')
  51     if 'dynamicStreams' in flashvars:
  52         video['url'] = flashvars['dynamicStreams'][0].split('url:')[1].split('.mp4,')[0] +'.mp4'
  53         filename = video['title']+".mp4"
  54         print(Popen(["rtmpdump","-o"+filename,"-r", url], stdout=PIPE).communicate()[0])
  55     if 'pathflv' in flashvars:
  56         rtmp = flashvars['pathflv'][0]
  57         filename = video['title']+".flv"
  58         print(Popen(["mplayer","-dumpstream","-dumpfile",filename, rtmp], stdout=PIPE).communicate()[0])
  59     if 'video' in flashvars:
  60         for reference in flashvars['video']['videoReferences']:
  61             if reference['url'].endswith("m3u8"):
  62                 video['url']=reference['url']
  63                 video['filename'] = video['title']+'.ts'
  64                 if 'statistics' in flashvars:
  65                     video['category'] = flashvars['statistics']['category']
  66         download_from_playlist(video)
  67     else:
  68         print("Could not find any streams")
  69         return
  70     return video
  71
  72 def download_from_playlist(video):
  73     playlist = parse_playlist(requests.get(video['url']).text)
  74     if not playlist:
  75         return
  76     videourl = sorted(playlist, key=lambda k: int(k['BANDWIDTH']))[-1]['url']
  77     segments, metadata = parse_segment_playlist(requests.get(videourl).text)
  78     if "EXT-X-KEY" in metadata:
  79         key = requests.get(metadata["EXT-X-KEY"]['URI'].strip('"')).text
  80         decrypt=True
  81     else:
  82         decrypt=False
  83     with open("%s"%video['filename'],"wb") as ofile:
  84         segment=0
  85         size = 0
  86         for url in segments:
  87             ufile = requests.get(url, stream=True).raw
  88             print("\r{} MB".format(size/1024/1024))
  89             sys.stdout.flush()
  90             if decrypt:
  91                 iv=struct.pack("IIII",segment,0,0,0)
  92                 decryptor = AES.new(key, AES.MODE_CBC, iv)
  93             while(True):
  94                 buf = ufile.read(4096)
  95                 if not buf:
  96                     break
  97                 if decrypt:
  98                     buf = decryptor.decrypt(buf)
  99                 ofile.write(buf)
 100                 size += len(buf)
 101             segment += 1
 102
 103 def parse_playlist(playlist):
 104     if not playlist.startswith("#EXTM3U"):
 105         print(playlist)
 106         return False
 107     playlist = playlist.splitlines()[1:]
 108     items=[]
 109     for (metadata_string,url) in zip(playlist[0::2], playlist[1::2]):
 110         md = dict()
 111         assert 'EXT-X-STREAM-INF' in metadata_string.split(':')[0]
 112         for item in metadata_string.split(':')[1].split(','):
 113             if '=' in item:
 114                 md.update([item.split('='),])
 115         md['url']=url
 116         items.append(md)
 117     return items
 118
 119 def parse_segment_playlist(playlist):
 120     assert playlist.startswith("#EXTM3U")
 121     PATTERN = re.compile(r'''((?:[^,"']|"[^"]*"|'[^']*')+)''')
 122     segments = []
 123     next_is_url=False
 124     metadata = {}
 125     for row in playlist.splitlines():
 126         if next_is_url:
 127             segments.append(row)
 128             next_is_url=False
 129             continue
 130         if 'EXTINF' in row:
 131             next_is_url=True
 132         if "EXT-X-KEY" in row:
 133              row = row.split(':',1)[1] #skip first part
 134              parts = PATTERN.split(row)[1:-1] #do magic re split and keep quotes
 135              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
 136     return(segments, metadata)
 137
 138 def parse_videolist():
 139     page_num = 1
 140     soup = BeautifulSoup(requests.get("http://www.svtplay.se/ajax/videospager").text)#this call does not work for getting the pages, we use it for the page totals only
 141     page_tot = int(soup.find('a',{'data-currentpage':True}).attrs['data-lastpage'])
 142     videos_per_page = 8
 143     video_num = 0
 144     while(page_num <= page_tot):
 145         base_url = "http://www.svtplay.se/ajax/videos?sida={}".format(page_num)
 146         soup = BeautifulSoup(requests.get(base_url).text)
 147         for article in soup.findAll('article'):
 148             meta = dict(article.attrs)
 149             video = {}
 150             video['title'] = meta['data-title']
 151             video['description'] = meta['data-description']
 152             video['url'] = dict(article.find('a').attrs)['href']
 153             video['thumb-url'] = dict(article.find('img',{}).attrs)['src']
 154             video['num'] = video_num
 155             video['total'] = page_tot * videos_per_page
 156             video_num += 1
 157             yield video
 158         page_num += 1
 159
 160
 161 if __name__ == "__main__":
 162     parser = argparse.ArgumentParser()
 163     group = parser.add_mutually_exclusive_group(required=True)
 164     group.add_argument("-r", "--rss", help="Download all files in rss")
 165     group.add_argument("-u", "--url", help="Download video in url")
 166     group.add_argument("-m", "--mirror", help="Mirror all files", action="store_true")
 167     parser.add_argument("-n", "--no_act", help="Just print what would be done, don't do any downloading.", action="store_true")
 168     args = parser.parse_args()
 169     if args.rss:
 170         import feedparser
 171         d = feedparser.parse(args.rss)
 172         for e in d.entries:
 173             print(("Downloading: %s"%e.title))
 174             if args.no_act:
 175                 continue
 176             filename = scrape_player_page(e.link, e.title)
 177             print(Popen(["avconv","-i",filename,"-vcodec","copy","-acodec","copy", filename+'.mkv'], stdout=PIPE).communicate()[0])
 178         #print(e.description)
 179     if args.mirror:
 180         for video in parse_videolist():
 181             video['title'] = video['title'].replace('/','_')
 182             print(video['title']+'.mkv')
 183             print("{} of {}".format(video['num'], video['total']))
 184             if os.path.exists(video['title']+'.mkv'):
 185                 print("Skipping")
 186                 continue
 187             print("Downloading...")
 188             if args.no_act:
 189                 continue
 190             ret = scrape_player_page(video['url'], video['title'])
 191             print(ret)
 192             print(Popen(["avconv","-i",video['title']+'.ts',"-vcodec","copy","-acodec","copy", video['title']+'.mkv'], stdout=PIPE).communicate()[0])
 193             try:
 194                 os.unlink(video['title']+'.ts')
 195             except:
 196                 import pdb;pdb.set_trace()
 197     else:
 198         if not args.no_act:
 199             video = scrape_player_page(args.url, None)
 200         print(("Downloaded {}".format(args.url)))