]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/viewster.py
Rapsys Git / youtubedl / blobdiff
? search:
summary | shortlog | log | commit | commitdiff | tree
raw | inline | side by side
Fine tune the changelog.
[youtubedl] / youtube_dl / extractor / viewster.py
diff --git a/youtube_dl/extractor/viewster.py b/youtube_dl/extractor/viewster.py
index 1742e66f481c91477ae41e5c42a262e35b7adc47..fe94a479339035dfd9a70386e903e5c3770fdfea 100644 (file)
--- a/youtube_dl/extractor/viewster.py
+++ b/youtube_dl/extractor/viewster.py
@@ -1,129 +1,172 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_request
+from ..compat import (
+    compat_HTTPError,
+    compat_urllib_parse,
+    compat_urllib_parse_unquote,
+)
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    int_or_none,
+    parse_iso8601,
+    sanitized_Request,
+    HEADRequest,
+)
 
 
 class ViewsterIE(InfoExtractor):
 
 
 class ViewsterIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?viewster\.com/movie/(?P<id>\d+-\d+-\d+)'
+    _VALID_URL = r'https?://(?:www\.)?viewster\.com/(?:serie|movie)/(?P<id>\d+-\d+-\d+)'
     _TESTS = [{
     _TESTS = [{
-        # movielink, paymethod=fre
-        'url': 'http://www.viewster.com/movie/1293-19341-000/hout-wood/',
-        'playlist': [{
-            'md5': '8f9d94b282d80c42b378dffdbb11caf3',
-            'info_dict': {
-                'id': '1293-19341-000-movie',
-                'ext': 'flv',
-                'title': "'Hout' (Wood) - Movie",
-            },
-        }],
-        'info_dict': {
-            'id': '1293-19341-000',
-            'title': "'Hout' (Wood)",
-            'description': 'md5:925733185a9242ef96f436937683f33b',
-        }
-    }, {
-        # movielink, paymethod=adv
+        # movie, Type=Movie
         'url': 'http://www.viewster.com/movie/1140-11855-000/the-listening-project/',
         'url': 'http://www.viewster.com/movie/1140-11855-000/the-listening-project/',
-        'playlist': [{
-            'md5': '77a005453ca7396cbe3d35c9bea30aef',
-            'info_dict': {
-                'id': '1140-11855-000-movie',
-                'ext': 'flv',
-                'title': "THE LISTENING PROJECT - Movie",
-            },
-        }],
+        'md5': 'e642d1b27fcf3a4ffa79f194f5adde36',
         'info_dict': {
             'id': '1140-11855-000',
         'info_dict': {
             'id': '1140-11855-000',
-            'title': "THE LISTENING PROJECT",
-            'description': 'md5:714421ae9957e112e672551094bf3b08',
-        }
+            'ext': 'mp4',
+            'title': 'The listening Project',
+            'description': 'md5:bac720244afd1a8ea279864e67baa071',
+            'timestamp': 1214870400,
+            'upload_date': '20080701',
+            'duration': 4680,
+        },
     }, {
     }, {
-        # direct links, no movielink
-        'url': 'http://www.viewster.com/movie/1198-56411-000/sinister/',
-        'playlist': [{
-            'md5': '0307b7eac6bfb21ab0577a71f6eebd8f',
-            'info_dict': {
-                'id': '1198-56411-000-trailer',
-                'ext': 'mp4',
-                'title': "Sinister - Trailer",
-            },
-        }, {
-            'md5': '80b9ee3ad69fb368f104cb5d9732ae95',
-            'info_dict': {
-                'id': '1198-56411-000-behind-scenes',
-                'ext': 'mp4',
-                'title': "Sinister - Behind Scenes",
-            },
-        }, {
-            'md5': '3b3ea897ecaa91fca57a8a94ac1b15c5',
-            'info_dict': {
-                'id': '1198-56411-000-scene-from-movie',
-                'ext': 'mp4',
-                'title': "Sinister - Scene from movie",
-            },
-        }],
+        # series episode, Type=Episode
+        'url': 'http://www.viewster.com/serie/1284-19427-001/the-world-and-a-wall/',
+        'md5': '9243079a8531809efe1b089db102c069',
         'info_dict': {
         'info_dict': {
-            'id': '1198-56411-000',
-            'title': "Sinister",
-            'description': 'md5:014c40b0488848de9683566a42e33372',
-        }
+            'id': '1284-19427-001',
+            'ext': 'mp4',
+            'title': 'The World and a Wall',
+            'description': 'md5:24814cf74d3453fdf5bfef9716d073e3',
+            'timestamp': 1428192000,
+            'upload_date': '20150405',
+            'duration': 1500,
+        },
+    }, {
+        # serie, Type=Serie
+        'url': 'http://www.viewster.com/serie/1303-19426-000/',
+        'info_dict': {
+            'id': '1303-19426-000',
+            'title': 'Is It Wrong to Try to Pick up Girls in a Dungeon?',
+            'description': 'md5:eeda9bef25b0d524b3a29a97804c2f11',
+        },
+        'playlist_count': 13,
+    }, {
+        # unfinished serie, no Type
+        'url': 'http://www.viewster.com/serie/1284-19427-000/baby-steps-season-2/',
+        'info_dict': {
+            'id': '1284-19427-000',
+            'title': 'Baby Steps—Season 2',
+            'description': 'md5:e7097a8fc97151e25f085c9eb7a1cdb1',
+        },
+        'playlist_mincount': 16,
+    }, {
+        # geo restricted series
+        'url': 'https://www.viewster.com/serie/1280-18794-002/',
+        'only_matching': True,
+    }, {
+        # geo restricted video
+        'url': 'https://www.viewster.com/serie/1280-18794-002/what-is-extraterritoriality-lawo/',
+        'only_matching': True,
     }]
 
     _ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01'
 
     }]
 
     _ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01'
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        request = compat_urllib_request.Request(
-            'http://api.live.viewster.com/api/v1/movie/%s' % video_id)
+    def _download_json(self, url, video_id, note='Downloading JSON metadata', fatal=True):
+        request = sanitized_Request(url)
         request.add_header('Accept', self._ACCEPT_HEADER)
         request.add_header('Accept', self._ACCEPT_HEADER)
+        request.add_header('Auth-token', self._AUTH_TOKEN)
+        return super(ViewsterIE, self)._download_json(request, video_id, note, fatal=fatal)
 
 
-        movie = self._download_json(
-            request, video_id, 'Downloading movie metadata JSON')
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        # Get 'api_token' cookie
+        self._request_webpage(HEADRequest('http://www.viewster.com/'), video_id)
+        cookies = self._get_cookies('http://www.viewster.com/')
+        self._AUTH_TOKEN = compat_urllib_parse_unquote(cookies['api_token'].value)
 
 
-        title = movie.get('title') or movie['original_title']
-        description = movie.get('synopsis')
-        thumbnail = movie.get('large_artwork') or movie.get('artwork')
+        info = self._download_json(
+            'https://public-api.viewster.com/search/%s' % video_id,
+            video_id, 'Downloading entry JSON')
 
 
-        entries = []
-        for clip in movie['play_list']:
-            entry = None
+        entry_id = info.get('Id') or info['id']
 
 
-            # movielink api
-            link_request = clip.get('link_request')
-            if link_request:
-                request = compat_urllib_request.Request(
-                    'http://api.live.viewster.com/api/v1/movielink?movieid=%(movieid)s&action=%(action)s&paymethod=%(paymethod)s&price=%(price)s&currency=%(currency)s&language=%(language)s&subtitlelanguage=%(subtitlelanguage)s&ischromecast=%(ischromecast)s'
-                    % link_request)
-                request.add_header('Accept', self._ACCEPT_HEADER)
+        # unfinished serie has no Type
+        if info.get('Type') in ('Serie', None):
+            try:
+                episodes = self._download_json(
+                    'https://public-api.viewster.com/series/%s/episodes' % entry_id,
+                    video_id, 'Downloading series JSON')
+            except ExtractorError as e:
+                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
+                    self.raise_geo_restricted()
+                else:
+                    raise
+            entries = [
+                self.url_result(
+                    'http://www.viewster.com/movie/%s' % episode['OriginId'], 'Viewster')
+                for episode in episodes]
+            title = (info.get('Title') or info['Synopsis']['Title']).strip()
+            description = info.get('Synopsis', {}).get('Detailed')
+            return self.playlist_result(entries, video_id, title, description)
 
 
-                movie_link = self._download_json(
-                    request, video_id, 'Downloading movie link JSON', fatal=False)
+        formats = []
+        for media_type in ('application/f4m+xml', 'application/x-mpegURL', 'video/mp4'):
+            media = self._download_json(
+                'https://public-api.viewster.com/movies/%s/video?mediaType=%s'
+                % (entry_id, compat_urllib_parse.quote(media_type)),
+                video_id, 'Downloading %s JSON' % media_type, fatal=False)
+            if not media:
+                continue
+            video_url = media.get('Uri')
+            if not video_url:
+                continue
+            ext = determine_ext(video_url)
+            if ext == 'f4m':
+                video_url += '&' if '?' in video_url else '?'
+                video_url += 'hdcore=3.2.0&plugin=flowplayer-3.2.0.1'
+                formats.extend(self._extract_f4m_formats(
+                    video_url, video_id, f4m_id='hds'))
+            elif ext == 'm3u8':
+                m3u8_formats = self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4', m3u8_id='hls',
+                    fatal=False)  # m3u8 sometimes fail
+                if m3u8_formats:
+                    formats.extend(m3u8_formats)
+            else:
+                format_id = media.get('Bitrate')
+                f = {
+                    'url': video_url,
+                    'format_id': 'mp4-%s' % format_id,
+                    'height': int_or_none(media.get('Height')),
+                    'width': int_or_none(media.get('Width')),
+                    'preference': 1,
+                }
+                if format_id and not f['height']:
+                    f['height'] = int_or_none(self._search_regex(
+                        r'^(\d+)[pP]$', format_id, 'height', default=None))
+                formats.append(f)
 
 
-                if movie_link:
-                    formats = self._extract_f4m_formats(
-                        movie_link['url'] + '&hdcore=3.2.0&plugin=flowplayer-3.2.0.1', video_id)
-                    self._sort_formats(formats)
-                    entry = {
-                        'formats': formats,
-                    }
+        if not formats and not info.get('LanguageSets') and not info.get('VODSettings'):
+            self.raise_geo_restricted()
 
 
-            # direct link
-            clip_url = clip.get('clip_data', {}).get('url')
-            if clip_url:
-                entry = {
-                    'url': clip_url,
-                    'ext': 'mp4',
-                }
+        self._sort_formats(formats)
 
 
-            if entry:
-                entry.update({
-                    'id': '%s-%s' % (video_id, clip['canonical_title']),
-                    'title': '%s - %s' % (title, clip['title']),
-                })
-                entries.append(entry)
+        synopsis = info.get('Synopsis') or {}
+        # Prefer title outside synopsis since it's less messy
+        title = (info.get('Title') or synopsis['Title']).strip()
+        description = synopsis.get('Detailed') or (info.get('Synopsis') or {}).get('Short')
+        duration = int_or_none(info.get('Duration'))
+        timestamp = parse_iso8601(info.get('ReleaseDate'))
 
 
-        playlist = self.playlist_result(entries, video_id, title, description)
-        playlist['thumbnail'] = thumbnail
-        return playlist
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
+        }
Backup clone of https://github.com/ytdl-org unavailable since RIAA fucking raid...