Fix "invalid escape sequences" error on Python 3.6
[youtube-dl] / 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     _WORKING = False
75     _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P<id>[^/]+)/(?:player|preview)'
76
77     _TESTS = [{
78         # rtl
79         'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/player',
80         'info_dict': {
81             'id': '203519',
82             'display_id': 'bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit',
83             'ext': 'flv',
84             'title': 'Inka Bause stellt die neuen Bauern vor',
85             'description': 'md5:e234e1ed6d63cf06be5c070442612e7e',
86             'thumbnail': r're:^https?://.*\.jpg$',
87             'timestamp': 1432580700,
88             'upload_date': '20150525',
89             'duration': 2786,
90         },
91         'params': {
92             # rtmp download
93             'skip_download': True,
94         },
95     }, {
96         # rtl2
97         'url': 'http://www.nowtv.de/rtl2/berlin-tag-nacht/berlin-tag-nacht-folge-934/player',
98         'info_dict': {
99             'id': '203481',
100             'display_id': 'berlin-tag-nacht/berlin-tag-nacht-folge-934',
101             'ext': 'flv',
102             'title': 'Berlin - Tag & Nacht (Folge 934)',
103             'description': 'md5:c85e88c2e36c552dfe63433bc9506dd0',
104             'thumbnail': r're:^https?://.*\.jpg$',
105             'timestamp': 1432666800,
106             'upload_date': '20150526',
107             'duration': 2641,
108         },
109         'params': {
110             # rtmp download
111             'skip_download': True,
112         },
113     }, {
114         # rtlnitro
115         'url': 'http://www.nowtv.de/rtlnitro/alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00/player',
116         'info_dict': {
117             'id': '165780',
118             'display_id': 'alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00',
119             'ext': 'flv',
120             'title': 'Hals- und Beinbruch',
121             'description': 'md5:b50d248efffe244e6f56737f0911ca57',
122             'thumbnail': r're:^https?://.*\.jpg$',
123             'timestamp': 1432415400,
124             'upload_date': '20150523',
125             'duration': 2742,
126         },
127         'params': {
128             # rtmp download
129             'skip_download': True,
130         },
131     }, {
132         # superrtl
133         'url': 'http://www.nowtv.de/superrtl/medicopter-117/angst/player',
134         'info_dict': {
135             'id': '99205',
136             'display_id': 'medicopter-117/angst',
137             'ext': 'flv',
138             'title': 'Angst!',
139             'description': 'md5:30cbc4c0b73ec98bcd73c9f2a8c17c4e',
140             'thumbnail': r're:^https?://.*\.jpg$',
141             'timestamp': 1222632900,
142             'upload_date': '20080928',
143             'duration': 3025,
144         },
145         'params': {
146             # rtmp download
147             'skip_download': True,
148         },
149     }, {
150         # ntv
151         'url': 'http://www.nowtv.de/ntv/ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch/player',
152         'info_dict': {
153             'id': '203521',
154             'display_id': 'ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch',
155             'ext': 'flv',
156             'title': 'Thema u.a.: Der erste Blick: Die Apple Watch',
157             'description': 'md5:4312b6c9d839ffe7d8caf03865a531af',
158             'thumbnail': r're:^https?://.*\.jpg$',
159             'timestamp': 1432751700,
160             'upload_date': '20150527',
161             'duration': 1083,
162         },
163         'params': {
164             # rtmp download
165             'skip_download': True,
166         },
167     }, {
168         # vox
169         'url': 'http://www.nowtv.de/vox/der-hundeprofi/buero-fall-chihuahua-joel/player',
170         'info_dict': {
171             'id': '128953',
172             'display_id': 'der-hundeprofi/buero-fall-chihuahua-joel',
173             'ext': 'flv',
174             'title': "Büro-Fall / Chihuahua 'Joel'",
175             'description': 'md5:e62cb6bf7c3cc669179d4f1eb279ad8d',
176             'thumbnail': r're:^https?://.*\.jpg$',
177             'timestamp': 1432408200,
178             'upload_date': '20150523',
179             'duration': 3092,
180         },
181         'params': {
182             # rtmp download
183             'skip_download': True,
184         },
185     }, {
186         'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/preview',
187         'only_matching': True,
188     }, {
189         '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',
190         'only_matching': True,
191     }, {
192         'url': 'http://www.nowtv.de/rtl2/echtzeit/list/aktuell/schnelles-geld-am-ende-der-welt/player',
193         'only_matching': True,
194     }, {
195         'url': 'http://www.nowtv.de/rtl2/zuhause-im-glueck/jahr/2015/11/eine-erschuetternde-diagnose/player',
196         'only_matching': True,
197     }]
198
199     def _real_extract(self, url):
200         mobj = re.match(self._VALID_URL, url)
201         display_id = '%s/%s' % (mobj.group('show_id'), mobj.group('id'))
202
203         info = self._download_json(
204             'https://api.nowtv.de/v3/movies/%s?fields=%s'
205             % (display_id, ','.join(self._VIDEO_FIELDS)), display_id)
206
207         return self._extract_video(info, display_id)
208
209
210 class NowTVListIE(NowTVBaseIE):
211     _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/list/(?P<id>[^?/#&]+)$'
212
213     _SHOW_FIELDS = ('title', )
214     _SEASON_FIELDS = ('id', 'headline', 'seoheadline', )
215
216     _TESTS = [{
217         'url': 'http://www.nowtv.at/rtl/stern-tv/list/aktuell',
218         'info_dict': {
219             'id': '17006',
220             'title': 'stern TV - Aktuell',
221         },
222         'playlist_count': 1,
223     }, {
224         'url': 'http://www.nowtv.at/rtl/das-supertalent/list/free-staffel-8',
225         'info_dict': {
226             'id': '20716',
227             'title': 'Das Supertalent - FREE Staffel 8',
228         },
229         'playlist_count': 14,
230     }]
231
232     def _real_extract(self, url):
233         mobj = re.match(self._VALID_URL, url)
234         show_id = mobj.group('show_id')
235         season_id = mobj.group('id')
236
237         fields = []
238         fields.extend(self._SHOW_FIELDS)
239         fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS)
240         fields.extend(
241             'formatTabs.formatTabPages.container.movies.%s' % field
242             for field in self._VIDEO_FIELDS)
243
244         list_info = self._download_json(
245             'https://api.nowtv.de/v3/formats/seo?fields=%s&name=%s.php'
246             % (','.join(fields), show_id),
247             season_id)
248
249         season = next(
250             season for season in list_info['formatTabs']['items']
251             if season.get('seoheadline') == season_id)
252
253         title = '%s - %s' % (list_info['title'], season['headline'])
254
255         entries = []
256         for container in season['formatTabPages']['items']:
257             for info in ((container.get('container') or {}).get('movies') or {}).get('items') or []:
258                 entries.append(self._extract_video(info))
259
260         return self.playlist_result(
261             entries, compat_str(season.get('id') or season_id), title)