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     int_or_none,
  11     parse_iso8601,
  12     parse_duration,
  13     remove_start,
  14 )
  15
  16
  17 class NowTVIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?nowtv\.de/(?P<station>rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<id>.+?)/player'
  19
  20     _TESTS = [{
  21         # rtl
  22         'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/player',
  23         'info_dict': {
  24             'id': '203519',
  25             'display_id': 'bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit',
  26             'ext': 'mp4',
  27             'title': 'Die neuen Bauern und eine Hochzeit',
  28             'description': 'md5:e234e1ed6d63cf06be5c070442612e7e',
  29             'thumbnail': 're:^https?://.*\.jpg$',
  30             'timestamp': 1432580700,
  31             'upload_date': '20150525',
  32             'duration': 2786,
  33         },
  34         'params': {
  35             # m3u8 download
  36             'skip_download': True,
  37         },
  38     }, {
  39         # rtl2
  40         'url': 'http://www.nowtv.de/rtl2/berlin-tag-nacht/berlin-tag-nacht-folge-934/player',
  41         'info_dict': {
  42             'id': '203481',
  43             'display_id': 'berlin-tag-nacht/berlin-tag-nacht-folge-934',
  44             'ext': 'mp4',
  45             'title': 'Berlin - Tag & Nacht (Folge 934)',
  46             'description': 'md5:c85e88c2e36c552dfe63433bc9506dd0',
  47             'thumbnail': 're:^https?://.*\.jpg$',
  48             'timestamp': 1432666800,
  49             'upload_date': '20150526',
  50             'duration': 2641,
  51         },
  52         'params': {
  53             # m3u8 download
  54             'skip_download': True,
  55         },
  56     }, {
  57         # rtlnitro
  58         'url': 'http://www.nowtv.de/rtlnitro/alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00/player',
  59         'info_dict': {
  60             'id': '165780',
  61             'display_id': 'alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00',
  62             'ext': 'mp4',
  63             'title': 'Hals- und Beinbruch',
  64             'description': 'md5:b50d248efffe244e6f56737f0911ca57',
  65             'thumbnail': 're:^https?://.*\.jpg$',
  66             'timestamp': 1432415400,
  67             'upload_date': '20150523',
  68             'duration': 2742,
  69         },
  70         'params': {
  71             # m3u8 download
  72             'skip_download': True,
  73         },
  74     }, {
  75         # superrtl
  76         'url': 'http://www.nowtv.de/superrtl/medicopter-117/angst/player',
  77         'info_dict': {
  78             'id': '99205',
  79             'display_id': 'medicopter-117/angst',
  80             'ext': 'mp4',
  81             'title': 'Angst!',
  82             'description': 'md5:30cbc4c0b73ec98bcd73c9f2a8c17c4e',
  83             'thumbnail': 're:^https?://.*\.jpg$',
  84             'timestamp': 1222632900,
  85             'upload_date': '20080928',
  86             'duration': 3025,
  87         },
  88         'params': {
  89             # m3u8 download
  90             'skip_download': True,
  91         },
  92     }, {
  93         # ntv
  94         'url': 'http://www.nowtv.de/ntv/ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch/player',
  95         'info_dict': {
  96             'id': '203521',
  97             'display_id': 'ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch',
  98             'ext': 'mp4',
  99             'title': 'Thema u.a.: Der erste Blick: Die Apple Watch',
 100             'description': 'md5:4312b6c9d839ffe7d8caf03865a531af',
 101             'thumbnail': 're:^https?://.*\.jpg$',
 102             'timestamp': 1432751700,
 103             'upload_date': '20150527',
 104             'duration': 1083,
 105         },
 106         'params': {
 107             # m3u8 download
 108             'skip_download': True,
 109         },
 110     }, {
 111         # vox
 112         'url': 'http://www.nowtv.de/vox/der-hundeprofi/buero-fall-chihuahua-joel/player',
 113         'info_dict': {
 114             'id': '128953',
 115             'display_id': 'der-hundeprofi/buero-fall-chihuahua-joel',
 116             'ext': 'mp4',
 117             'title': "Büro-Fall / Chihuahua 'Joel'",
 118             'description': 'md5:e62cb6bf7c3cc669179d4f1eb279ad8d',
 119             'thumbnail': 're:^https?://.*\.jpg$',
 120             'timestamp': 1432408200,
 121             'upload_date': '20150523',
 122             'duration': 3092,
 123         },
 124         'params': {
 125             # m3u8 download
 126             'skip_download': True,
 127         },
 128     }]
 129
 130     def _real_extract(self, url):
 131         mobj = re.match(self._VALID_URL, url)
 132         display_id = mobj.group('id')
 133         station = mobj.group('station')
 134
 135         info = self._download_json(
 136             'https://api.nowtv.de/v3/movies/%s?fields=*,format,files' % display_id,
 137             display_id)
 138
 139         video_id = compat_str(info['id'])
 140
 141         files = info['files']
 142         if not files:
 143             if info.get('geoblocked', False):
 144                 raise ExtractorError(
 145                     'Video %s is not available from your location due to geo restriction' % video_id,
 146                     expected=True)
 147             if not info.get('free', True):
 148                 raise ExtractorError(
 149                     'Video %s is not available for free' % video_id, expected=True)
 150
 151         f = info.get('format', {})
 152         station = f.get('station') or station
 153
 154         STATIONS = {
 155             'rtl': 'rtlnow',
 156             'rtl2': 'rtl2now',
 157             'vox': 'voxnow',
 158             'nitro': 'rtlnitronow',
 159             'ntv': 'n-tvnow',
 160             'superrtl': 'superrtlnow'
 161         }
 162
 163         formats = []
 164         for item in files['items']:
 165             item_path = remove_start(item['path'], '/')
 166             tbr = int_or_none(item['bitrate'])
 167             m3u8_url = 'http://hls.fra.%s.de/hls-vod-enc/%s.m3u8' % (STATIONS[station], item_path)
 168             m3u8_url = m3u8_url.replace('now/', 'now/videos/')
 169             formats.append({
 170                 'url': m3u8_url,
 171                 'format_id': '%s-%sk' % (item['id'], tbr),
 172                 'ext': 'mp4',
 173                 'tbr': tbr,
 174             })
 175         self._sort_formats(formats)
 176
 177         title = info['title']
 178         description = info.get('articleLong') or info.get('articleShort')
 179         timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ')
 180         duration = parse_duration(info.get('duration'))
 181         thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo')
 182
 183         return {
 184             'id': video_id,
 185             'display_id': display_id,
 186             'title': title,
 187             'description': description,
 188             'thumbnail': thumbnail,
 189             'timestamp': timestamp,
 190             'duration': duration,
 191             'formats': formats,
 192         }