youtube-dl

Another place where youtube-dl lives on
git clone git://git.oshgnacknak.de/youtube-dl.git
Log | Files | Refs | README | LICENSE

ruutu.py (9346B)


      1 # coding: utf-8
      2 from __future__ import unicode_literals
      3 
      4 from .common import InfoExtractor
      5 from ..compat import compat_urllib_parse_urlparse
      6 from ..utils import (
      7     determine_ext,
      8     ExtractorError,
      9     find_xpath_attr,
     10     int_or_none,
     11     unified_strdate,
     12     url_or_none,
     13     xpath_attr,
     14     xpath_text,
     15 )
     16 
     17 
     18 class RuutuIE(InfoExtractor):
     19     _VALID_URL = r'''(?x)
     20                     https?://
     21                         (?:
     22                             (?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla|audio)/|
     23                             static\.nelonenmedia\.fi/player/misc/embed_player\.html\?.*?\bnid=
     24                         )
     25                         (?P<id>\d+)
     26                     '''
     27     _TESTS = [
     28         {
     29             'url': 'http://www.ruutu.fi/video/2058907',
     30             'md5': 'ab2093f39be1ca8581963451b3c0234f',
     31             'info_dict': {
     32                 'id': '2058907',
     33                 'ext': 'mp4',
     34                 'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!',
     35                 'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6',
     36                 'thumbnail': r're:^https?://.*\.jpg$',
     37                 'duration': 114,
     38                 'age_limit': 0,
     39             },
     40         },
     41         {
     42             'url': 'http://www.ruutu.fi/video/2057306',
     43             'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
     44             'info_dict': {
     45                 'id': '2057306',
     46                 'ext': 'mp4',
     47                 'title': 'Superpesis: katso koko kausi Ruudussa',
     48                 'description': 'md5:bfb7336df2a12dc21d18fa696c9f8f23',
     49                 'thumbnail': r're:^https?://.*\.jpg$',
     50                 'duration': 40,
     51                 'age_limit': 0,
     52             },
     53         },
     54         {
     55             'url': 'http://www.supla.fi/supla/2231370',
     56             'md5': 'df14e782d49a2c0df03d3be2a54ef949',
     57             'info_dict': {
     58                 'id': '2231370',
     59                 'ext': 'mp4',
     60                 'title': 'Osa 1: Mikael Jungner',
     61                 'description': 'md5:7d90f358c47542e3072ff65d7b1bcffe',
     62                 'thumbnail': r're:^https?://.*\.jpg$',
     63                 'age_limit': 0,
     64             },
     65         },
     66         # Episode where <SourceFile> is "NOT-USED", but has other
     67         # downloadable sources available.
     68         {
     69             'url': 'http://www.ruutu.fi/video/3193728',
     70             'only_matching': True,
     71         },
     72         {
     73             # audio podcast
     74             'url': 'https://www.supla.fi/supla/3382410',
     75             'md5': 'b9d7155fed37b2ebf6021d74c4b8e908',
     76             'info_dict': {
     77                 'id': '3382410',
     78                 'ext': 'mp3',
     79                 'title': 'Mikä ihmeen poltergeist?',
     80                 'description': 'md5:bbb6963df17dfd0ecd9eb9a61bf14b52',
     81                 'thumbnail': r're:^https?://.*\.jpg$',
     82                 'age_limit': 0,
     83             },
     84             'expected_warnings': [
     85                 'HTTP Error 502: Bad Gateway',
     86                 'Failed to download m3u8 information',
     87             ],
     88         },
     89         {
     90             'url': 'http://www.supla.fi/audio/2231370',
     91             'only_matching': True,
     92         },
     93         {
     94             'url': 'https://static.nelonenmedia.fi/player/misc/embed_player.html?nid=3618790',
     95             'only_matching': True,
     96         },
     97         {
     98             # episode
     99             'url': 'https://www.ruutu.fi/video/3401964',
    100             'info_dict': {
    101                 'id': '3401964',
    102                 'ext': 'mp4',
    103                 'title': 'Temptation Island Suomi - Kausi 5 - Jakso 17',
    104                 'description': 'md5:87cf01d5e1e88adf0c8a2937d2bd42ba',
    105                 'thumbnail': r're:^https?://.*\.jpg$',
    106                 'duration': 2582,
    107                 'age_limit': 12,
    108                 'upload_date': '20190508',
    109                 'series': 'Temptation Island Suomi',
    110                 'season_number': 5,
    111                 'episode_number': 17,
    112                 'categories': ['Reality ja tositapahtumat', 'Kotimaiset suosikit', 'Romantiikka ja parisuhde'],
    113             },
    114             'params': {
    115                 'skip_download': True,
    116             },
    117         },
    118         {
    119             # premium
    120             'url': 'https://www.ruutu.fi/video/3618715',
    121             'only_matching': True,
    122         },
    123     ]
    124     _API_BASE = 'https://gatling.nelonenmedia.fi'
    125 
    126     def _real_extract(self, url):
    127         video_id = self._match_id(url)
    128 
    129         video_xml = self._download_xml(
    130             '%s/media-xml-cache' % self._API_BASE, video_id,
    131             query={'id': video_id})
    132 
    133         formats = []
    134         processed_urls = []
    135 
    136         def extract_formats(node):
    137             for child in node:
    138                 if child.tag.endswith('Files'):
    139                     extract_formats(child)
    140                 elif child.tag.endswith('File'):
    141                     video_url = child.text
    142                     if (not video_url or video_url in processed_urls
    143                             or any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
    144                         continue
    145                     processed_urls.append(video_url)
    146                     ext = determine_ext(video_url)
    147                     auth_video_url = url_or_none(self._download_webpage(
    148                         '%s/auth/access/v2' % self._API_BASE, video_id,
    149                         note='Downloading authenticated %s stream URL' % ext,
    150                         fatal=False, query={'stream': video_url}))
    151                     if auth_video_url:
    152                         processed_urls.append(auth_video_url)
    153                         video_url = auth_video_url
    154                     if ext == 'm3u8':
    155                         formats.extend(self._extract_m3u8_formats(
    156                             video_url, video_id, 'mp4',
    157                             entry_protocol='m3u8_native', m3u8_id='hls',
    158                             fatal=False))
    159                     elif ext == 'f4m':
    160                         formats.extend(self._extract_f4m_formats(
    161                             video_url, video_id, f4m_id='hds', fatal=False))
    162                     elif ext == 'mpd':
    163                         # video-only and audio-only streams are of different
    164                         # duration resulting in out of sync issue
    165                         continue
    166                         formats.extend(self._extract_mpd_formats(
    167                             video_url, video_id, mpd_id='dash', fatal=False))
    168                     elif ext == 'mp3' or child.tag == 'AudioMediaFile':
    169                         formats.append({
    170                             'format_id': 'audio',
    171                             'url': video_url,
    172                             'vcodec': 'none',
    173                         })
    174                     else:
    175                         proto = compat_urllib_parse_urlparse(video_url).scheme
    176                         if not child.tag.startswith('HTTP') and proto != 'rtmp':
    177                             continue
    178                         preference = -1 if proto == 'rtmp' else 1
    179                         label = child.get('label')
    180                         tbr = int_or_none(child.get('bitrate'))
    181                         format_id = '%s-%s' % (proto, label if label else tbr) if label or tbr else proto
    182                         if not self._is_valid_url(video_url, video_id, format_id):
    183                             continue
    184                         width, height = [int_or_none(x) for x in child.get('resolution', 'x').split('x')[:2]]
    185                         formats.append({
    186                             'format_id': format_id,
    187                             'url': video_url,
    188                             'width': width,
    189                             'height': height,
    190                             'tbr': tbr,
    191                             'preference': preference,
    192                         })
    193 
    194         extract_formats(video_xml.find('./Clip'))
    195 
    196         def pv(name):
    197             node = find_xpath_attr(
    198                 video_xml, './Clip/PassthroughVariables/variable', 'name', name)
    199             if node is not None:
    200                 return node.get('value')
    201 
    202         if not formats:
    203             drm = xpath_text(video_xml, './Clip/DRM', default=None)
    204             if drm:
    205                 raise ExtractorError('This video is DRM protected.', expected=True)
    206             ns_st_cds = pv('ns_st_cds')
    207             if ns_st_cds != 'free':
    208                 raise ExtractorError('This video is %s.' % ns_st_cds, expected=True)
    209 
    210         self._sort_formats(formats)
    211 
    212         themes = pv('themes')
    213 
    214         return {
    215             'id': video_id,
    216             'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True),
    217             'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'),
    218             'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'),
    219             'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')) or int_or_none(pv('runtime')),
    220             'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
    221             'upload_date': unified_strdate(pv('date_start')),
    222             'series': pv('series_name'),
    223             'season_number': int_or_none(pv('season_number')),
    224             'episode_number': int_or_none(pv('episode_number')),
    225             'categories': themes.split(',') if themes else [],
    226             'formats': formats,
    227         }