Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/nowtv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     ExtractorError,
  10     determine_ext,
  11     int_or_none,
  12     parse_iso8601,
  13     parse_duration,
  14     remove_start,
  15 )
  16
  17
  18 class NowTVBaseIE(InfoExtractor):
  19     _VIDEO_FIELDS = (
  20         'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort',
  21         'broadcastStartDate', 'seoUrl', 'duration', 'files',
  22         'format.defaultImage169Format', 'format.defaultImage169Logo')
  23
  24     def _extract_video(self, info, display_id=None):
  25         video_id = compat_str(info['id'])
  26
  27         files = info['files']
  28         if not files:
  29             if info.get('geoblocked', False):
  30                 raise ExtractorError(
  31                     'Video %s is not available from your location due to geo restriction' % video_id,
  32                     expected=True)
  33             if not info.get('free', True):
  34                 raise ExtractorError(
  35                     'Video %s is not available for free' % video_id, expected=True)
  36
  37         formats = []
  38         for item in files['items']:
  39             if determine_ext(item['path']) != 'f4v':
  40                 continue
  41             app, play_path = remove_start(item['path'], '/').split('/', 1)
  42             formats.append({
  43                 'url': 'rtmpe://fms.rtl.de',
  44                 'app': app,
  45                 'play_path': 'mp4:%s' % play_path,
  46                 'ext': 'flv',
  47                 'page_url': 'http://rtlnow.rtl.de',
  48                 'player_url': 'http://cdn.static-fra.de/now/vodplayer.swf',
  49                 'tbr': int_or_none(item.get('bitrate')),
  50             })
  51         self._sort_formats(formats)
  52
  53         title = info['title']
  54         description = info.get('articleLong') or info.get('articleShort')
  55         timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ')
  56         duration = parse_duration(info.get('duration'))
  57
  58         f = info.get('format', {})
  59         thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo')
  60
  61         return {
  62             'id': video_id,
  63             'display_id': display_id or info.get('seoUrl'),
  64             'title': title,
  65             'description': description,
  66             'thumbnail': thumbnail,
  67             'timestamp': timestamp,
  68             'duration': duration,
  69             'formats': formats,
  70         }
  71
  72
  73 class NowTVIE(NowTVBaseIE):
  74     _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:list/[^/]+/)?(?P<id>[^/]+)/(?:player|preview)'
  75
  76     _TESTS = [{
  77         # rtl
  78         'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/player',
  79         'info_dict': {
  80             'id': '203519',
  81             'display_id': 'bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit',
  82             'ext': 'flv',
  83             'title': 'Inka Bause stellt die neuen Bauern vor',
  84             'description': 'md5:e234e1ed6d63cf06be5c070442612e7e',
  85             'thumbnail': 're:^https?://.*\.jpg$',
  86             'timestamp': 1432580700,
  87             'upload_date': '20150525',
  88             'duration': 2786,
  89         },
  90         'params': {
  91             # rtmp download
  92             'skip_download': True,
  93         },
  94     }, {
  95         # rtl2
  96         'url': 'http://www.nowtv.de/rtl2/berlin-tag-nacht/berlin-tag-nacht-folge-934/player',
  97         'info_dict': {
  98             'id': '203481',
  99             'display_id': 'berlin-tag-nacht/berlin-tag-nacht-folge-934',
 100             'ext': 'flv',
 101             'title': 'Berlin - Tag & Nacht (Folge 934)',
 102             'description': 'md5:c85e88c2e36c552dfe63433bc9506dd0',
 103             'thumbnail': 're:^https?://.*\.jpg$',
 104             'timestamp': 1432666800,
 105             'upload_date': '20150526',
 106             'duration': 2641,
 107         },
 108         'params': {
 109             # rtmp download
 110             'skip_download': True,
 111         },
 112     }, {
 113         # rtlnitro
 114         'url': 'http://www.nowtv.de/rtlnitro/alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00/player',
 115         'info_dict': {
 116             'id': '165780',
 117             'display_id': 'alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00',
 118             'ext': 'flv',
 119             'title': 'Hals- und Beinbruch',
 120             'description': 'md5:b50d248efffe244e6f56737f0911ca57',
 121             'thumbnail': 're:^https?://.*\.jpg$',
 122             'timestamp': 1432415400,
 123             'upload_date': '20150523',
 124             'duration': 2742,
 125         },
 126         'params': {
 127             # rtmp download
 128             'skip_download': True,
 129         },
 130     }, {
 131         # superrtl
 132         'url': 'http://www.nowtv.de/superrtl/medicopter-117/angst/player',
 133         'info_dict': {
 134             'id': '99205',
 135             'display_id': 'medicopter-117/angst',
 136             'ext': 'flv',
 137             'title': 'Angst!',
 138             'description': 'md5:30cbc4c0b73ec98bcd73c9f2a8c17c4e',
 139             'thumbnail': 're:^https?://.*\.jpg$',
 140             'timestamp': 1222632900,
 141             'upload_date': '20080928',
 142             'duration': 3025,
 143         },
 144         'params': {
 145             # rtmp download
 146             'skip_download': True,
 147         },
 148     }, {
 149         # ntv
 150         'url': 'http://www.nowtv.de/ntv/ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch/player',
 151         'info_dict': {
 152             'id': '203521',
 153             'display_id': 'ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch',
 154             'ext': 'flv',
 155             'title': 'Thema u.a.: Der erste Blick: Die Apple Watch',
 156             'description': 'md5:4312b6c9d839ffe7d8caf03865a531af',
 157             'thumbnail': 're:^https?://.*\.jpg$',
 158             'timestamp': 1432751700,
 159             'upload_date': '20150527',
 160             'duration': 1083,
 161         },
 162         'params': {
 163             # rtmp download
 164             'skip_download': True,
 165         },
 166     }, {
 167         # vox
 168         'url': 'http://www.nowtv.de/vox/der-hundeprofi/buero-fall-chihuahua-joel/player',
 169         'info_dict': {
 170             'id': '128953',
 171             'display_id': 'der-hundeprofi/buero-fall-chihuahua-joel',
 172             'ext': 'flv',
 173             'title': "Büro-Fall / Chihuahua 'Joel'",
 174             'description': 'md5:e62cb6bf7c3cc669179d4f1eb279ad8d',
 175             'thumbnail': 're:^https?://.*\.jpg$',
 176             'timestamp': 1432408200,
 177             'upload_date': '20150523',
 178             'duration': 3092,
 179         },
 180         'params': {
 181             # rtmp download
 182             'skip_download': True,
 183         },
 184     }, {
 185         'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/preview',
 186         'only_matching': True,
 187     }, {
 188         'url': 'http://www.nowtv.at/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/preview?return=/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit',
 189         'only_matching': True,
 190     }, {
 191         'url': 'http://www.nowtv.de/rtl2/echtzeit/list/aktuell/schnelles-geld-am-ende-der-welt/player',
 192         'only_matching': True,
 193     }]
 194
 195     def _real_extract(self, url):
 196         mobj = re.match(self._VALID_URL, url)
 197         display_id = '%s/%s' % (mobj.group('show_id'), mobj.group('id'))
 198
 199         info = self._download_json(
 200             'https://api.nowtv.de/v3/movies/%s?fields=%s'
 201             % (display_id, ','.join(self._VIDEO_FIELDS)), display_id)
 202
 203         return self._extract_video(info, display_id)
 204
 205
 206 class NowTVListIE(NowTVBaseIE):
 207     _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/list/(?P<id>[^?/#&]+)$'
 208
 209     _SHOW_FIELDS = ('title', )
 210     _SEASON_FIELDS = ('id', 'headline', 'seoheadline', )
 211
 212     _TESTS = [{
 213         'url': 'http://www.nowtv.at/rtl/stern-tv/list/aktuell',
 214         'info_dict': {
 215             'id': '17006',
 216             'title': 'stern TV - Aktuell',
 217         },
 218         'playlist_count': 1,
 219     }, {
 220         'url': 'http://www.nowtv.at/rtl/das-supertalent/list/free-staffel-8',
 221         'info_dict': {
 222             'id': '20716',
 223             'title': 'Das Supertalent - FREE Staffel 8',
 224         },
 225         'playlist_count': 14,
 226     }]
 227
 228     def _real_extract(self, url):
 229         mobj = re.match(self._VALID_URL, url)
 230         show_id = mobj.group('show_id')
 231         season_id = mobj.group('id')
 232
 233         fields = []
 234         fields.extend(self._SHOW_FIELDS)
 235         fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS)
 236         fields.extend(
 237             'formatTabs.formatTabPages.container.movies.%s' % field
 238             for field in self._VIDEO_FIELDS)
 239
 240         list_info = self._download_json(
 241             'https://api.nowtv.de/v3/formats/seo?fields=%s&name=%s.php'
 242             % (','.join(fields), show_id),
 243             season_id)
 244
 245         season = next(
 246             season for season in list_info['formatTabs']['items']
 247             if season.get('seoheadline') == season_id)
 248
 249         title = '%s - %s' % (list_info['title'], season['headline'])
 250
 251         entries = []
 252         for container in season['formatTabPages']['items']:
 253             for info in ((container.get('container') or {}).get('movies') or {}).get('items') or []:
 254                 entries.append(self._extract_video(info))
 255
 256         return self.playlist_result(
 257             entries, compat_str(season.get('id') or season_id), title)