Merge pull request #1 from ytdl-org/master

Merge from 04/28

youtube_dl/extractor/adn.py

@@ -65,14 +65,15 @@ class ADNIE(InfoExtractor):
         if subtitle_location:
             enc_subtitles = self._download_webpage(
                 urljoin(self._BASE_URL, subtitle_location),
-                video_id, 'Downloading subtitles data', fatal=False)
+                video_id, 'Downloading subtitles data', fatal=False,
+                headers={'Origin': 'https://animedigitalnetwork.fr'})
         if not enc_subtitles:
             return None
 
         # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
         dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
             bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
-            bytes_to_intlist(binascii.unhexlify(self._K + '4421de0a5f0814ba')),
+            bytes_to_intlist(binascii.unhexlify(self._K + '4b8ef13ec1872730')),
             bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
         ))
         subtitles_json = self._parse_json(

youtube_dl/extractor/ccc.py

@@ -1,9 +1,12 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     parse_iso8601,
+    try_get,
+    url_or_none,
 )
 
 
@@ -18,11 +21,13 @@ class CCCIE(InfoExtractor):
             'id': '1839',
             'ext': 'mp4',
             'title': 'Introduction to Processor Design',
+            'creator': 'byterazor',
             'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac',
             'thumbnail': r're:^https?://.*\.jpg$',
             'upload_date': '20131228',
             'timestamp': 1388188800,
             'duration': 3710,
+            'tags': list,
         }
     }, {
         'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
@@ -68,6 +73,7 @@ class CCCIE(InfoExtractor):
             'id': event_id,
             'display_id': display_id,
             'title': event_data['title'],
+            'creator': try_get(event_data, lambda x: ', '.join(x['persons'])),
             'description': event_data.get('description'),
             'thumbnail': event_data.get('thumb_url'),
             'timestamp': parse_iso8601(event_data.get('date')),
@@ -75,3 +81,31 @@ class CCCIE(InfoExtractor):
             'tags': event_data.get('tags'),
             'formats': formats,
         }
+
+
+class CCCPlaylistIE(InfoExtractor):
+    IE_NAME = 'media.ccc.de:lists'
+    _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/c/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://media.ccc.de/c/30c3',
+        'info_dict': {
+            'title': '30C3',
+            'id': '30c3',
+        },
+        'playlist_count': 135,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url).lower()
+
+        conf = self._download_json(
+            'https://media.ccc.de/public/conferences/' + playlist_id,
+            playlist_id)
+
+        entries = []
+        for e in conf['events']:
+            event_url = url_or_none(e.get('frontend_link'))
+            if event_url:
+                entries.append(self.url_result(event_url, ie=CCCIE.ie_key()))
+
+        return self.playlist_result(entries, playlist_id, conf.get('title'))

youtube_dl/extractor/dramafever.py

@@ -1,266 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import itertools
-import json
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_HTTPError,
-    compat_urlparse,
-)
-from ..utils import (
-    clean_html,
-    ExtractorError,
-    int_or_none,
-    parse_age_limit,
-    parse_duration,
-    unified_timestamp,
-    url_or_none,
-)
-
-
-class DramaFeverBaseIE(InfoExtractor):
-    _NETRC_MACHINE = 'dramafever'
-
-    _CONSUMER_SECRET = 'DA59dtVXYLxajktV'
-
-    _consumer_secret = None
-
-    def _get_consumer_secret(self):
-        mainjs = self._download_webpage(
-            'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js',
-            None, 'Downloading main.js', fatal=False)
-        if not mainjs:
-            return self._CONSUMER_SECRET
-        return self._search_regex(
-            r"var\s+cs\s*=\s*'([^']+)'", mainjs,
-            'consumer secret', default=self._CONSUMER_SECRET)
-
-    def _real_initialize(self):
-        self._consumer_secret = self._get_consumer_secret()
-        self._login()
-
-    def _login(self):
-        username, password = self._get_login_info()
-        if username is None:
-            return
-
-        login_form = {
-            'username': username,
-            'password': password,
-        }
-
-        try:
-            response = self._download_json(
-                'https://www.dramafever.com/api/users/login', None, 'Logging in',
-                data=json.dumps(login_form).encode('utf-8'), headers={
-                    'x-consumer-key': self._consumer_secret,
-                })
-        except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError) and e.cause.code in (403, 404):
-                response = self._parse_json(
-                    e.cause.read().decode('utf-8'), None)
-            else:
-                raise
-
-        # Successful login
-        if response.get('result') or response.get('guid') or response.get('user_guid'):
-            return
-
-        errors = response.get('errors')
-        if errors and isinstance(errors, list):
-            error = errors[0]
-            message = error.get('message') or error['reason']
-            raise ExtractorError('Unable to login: %s' % message, expected=True)
-        raise ExtractorError('Unable to log in')
-
-
-class DramaFeverIE(DramaFeverBaseIE):
-    IE_NAME = 'dramafever'
-    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
-    _TESTS = [{
-        'url': 'https://www.dramafever.com/drama/4274/1/Heirs/',
-        'info_dict': {
-            'id': '4274.1',
-            'ext': 'wvm',
-            'title': 'Heirs - Episode 1',
-            'description': 'md5:362a24ba18209f6276e032a651c50bc2',
-            'thumbnail': r're:^https?://.*\.jpg',
-            'duration': 3783,
-            'timestamp': 1381354993,
-            'upload_date': '20131009',
-            'series': 'Heirs',
-            'season_number': 1,
-            'episode': 'Episode 1',
-            'episode_number': 1,
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.dramafever.com/drama/4826/4/Mnet_Asian_Music_Awards_2015/?ap=1',
-        'info_dict': {
-            'id': '4826.4',
-            'ext': 'flv',
-            'title': 'Mnet Asian Music Awards 2015',
-            'description': 'md5:3ff2ee8fedaef86e076791c909cf2e91',
-            'episode': 'Mnet Asian Music Awards 2015 - Part 3',
-            'episode_number': 4,
-            'thumbnail': r're:^https?://.*\.jpg',
-            'timestamp': 1450213200,
-            'upload_date': '20151215',
-            'duration': 5359,
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }, {
-        'url': 'https://www.dramafever.com/zh-cn/drama/4972/15/Doctor_Romantic/',
-        'only_matching': True,
-    }]
-
-    def _call_api(self, path, video_id, note, fatal=False):
-        return self._download_json(
-            'https://www.dramafever.com/api/5/' + path,
-            video_id, note=note, headers={
-                'x-consumer-key': self._consumer_secret,
-            }, fatal=fatal)
-
-    def _get_subtitles(self, video_id):
-        subtitles = {}
-        subs = self._call_api(
-            'video/%s/subtitles/webvtt/' % video_id, video_id,
-            'Downloading subtitles JSON', fatal=False)
-        if not subs or not isinstance(subs, list):
-            return subtitles
-        for sub in subs:
-            if not isinstance(sub, dict):
-                continue
-            sub_url = url_or_none(sub.get('url'))
-            if not sub_url:
-                continue
-            subtitles.setdefault(
-                sub.get('code') or sub.get('language') or 'en', []).append({
-                    'url': sub_url
-                })
-        return subtitles
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url).replace('/', '.')
-
-        series_id, episode_number = video_id.split('.')
-
-        video = self._call_api(
-            'series/%s/episodes/%s/' % (series_id, episode_number), video_id,
-            'Downloading video JSON')
-
-        formats = []
-        download_assets = video.get('download_assets')
-        if download_assets and isinstance(download_assets, dict):
-            for format_id, format_dict in download_assets.items():
-                if not isinstance(format_dict, dict):
-                    continue
-                format_url = url_or_none(format_dict.get('url'))
-                if not format_url:
-                    continue
-                formats.append({
-                    'url': format_url,
-                    'format_id': format_id,
-                    'filesize': int_or_none(video.get('filesize')),
-                })
-
-        stream = self._call_api(
-            'video/%s/stream/' % video_id, video_id, 'Downloading stream JSON',
-            fatal=False)
-        if stream:
-            stream_url = stream.get('stream_url')
-            if stream_url:
-                formats.extend(self._extract_m3u8_formats(
-                    stream_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls', fatal=False))
-        self._sort_formats(formats)
-
-        title = video.get('title') or 'Episode %s' % episode_number
-        description = video.get('description')
-        thumbnail = video.get('thumbnail')
-        timestamp = unified_timestamp(video.get('release_date'))
-        duration = parse_duration(video.get('duration'))
-        age_limit = parse_age_limit(video.get('tv_rating'))
-        series = video.get('series_title')
-        season_number = int_or_none(video.get('season'))
-
-        if series:
-            title = '%s - %s' % (series, title)
-
-        subtitles = self.extract_subtitles(video_id)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'timestamp': timestamp,
-            'age_limit': age_limit,
-            'series': series,
-            'season_number': season_number,
-            'episode_number': int_or_none(episode_number),
-            'formats': formats,
-            'subtitles': subtitles,
-        }
-
-
-class DramaFeverSeriesIE(DramaFeverBaseIE):
-    IE_NAME = 'dramafever:series'
-    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
-    _TESTS = [{
-        'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
-        'info_dict': {
-            'id': '4512',
-            'title': 'Cooking with Shin',
-            'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
-        },
-        'playlist_count': 4,
-    }, {
-        'url': 'http://www.dramafever.com/drama/124/IRIS/',
-        'info_dict': {
-            'id': '124',
-            'title': 'IRIS',
-            'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
-        },
-        'playlist_count': 20,
-    }]
-
-    _PAGE_SIZE = 60  # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
-
-    def _real_extract(self, url):
-        series_id = self._match_id(url)
-
-        series = self._download_json(
-            'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
-            % (self._consumer_secret, series_id),
-            series_id, 'Downloading series JSON')['series'][series_id]
-
-        title = clean_html(series['name'])
-        description = clean_html(series.get('description') or series.get('description_short'))
-
-        entries = []
-        for page_num in itertools.count(1):
-            episodes = self._download_json(
-                'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
-                % (self._consumer_secret, series_id, self._PAGE_SIZE, page_num),
-                series_id, 'Downloading episodes JSON page #%d' % page_num)
-            for episode in episodes.get('value', []):
-                episode_url = episode.get('episode_url')
-                if not episode_url:
-                    continue
-                entries.append(self.url_result(
-                    compat_urlparse.urljoin(url, episode_url),
-                    'DramaFever', episode.get('guid')))
-            if page_num == episodes['num_pages']:
-                break
-
-        return self.playlist_result(entries, series_id, title, description)

youtube_dl/extractor/extractors.py

@@ -177,7 +177,10 @@ from .cbsnews import (
     CBSNewsLiveVideoIE,
 )
 from .cbssports import CBSSportsIE
-from .ccc import CCCIE
+from .ccc import (
+    CCCIE,
+    CCCPlaylistIE,
+)
 from .ccma import CCMAIE
 from .cctv import CCTVIE
 from .cda import CDAIE
@@ -284,10 +287,6 @@ from .dplay import (
     DPlayIE,
     DPlayItIE,
 )
-from .dramafever import (
-    DramaFeverIE,
-    DramaFeverSeriesIE,
-)
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
@@ -1098,6 +1097,10 @@ from .streetvoice import StreetVoiceIE
 from .stretchinternet import StretchInternetIE
 from .stv import STVPlayerIE
 from .sunporno import SunPornoIE
+from .sverigesradio import (
+    SverigesRadioEpisodeIE,
+    SverigesRadioPublicationIE,
+)
 from .svt import (
     SVTIE,
     SVTPageIE,

youtube_dl/extractor/sverigesradio.py

@@ -0,0 +1,115 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    str_or_none,
+)
+
+
+class SverigesRadioBaseIE(InfoExtractor):
+    _BASE_URL = 'https://sverigesradio.se/sida/playerajax/'
+    _QUALITIES = ['low', 'medium', 'high']
+    _EXT_TO_CODEC_MAP = {
+        'mp3': 'mp3',
+        'm4a': 'aac',
+    }
+    _CODING_FORMAT_TO_ABR_MAP = {
+        5: 128,
+        11: 192,
+        12: 32,
+        13: 96,
+    }
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+        query = {
+            'id': audio_id,
+            'type': self._AUDIO_TYPE,
+        }
+
+        item = self._download_json(
+            self._BASE_URL + 'audiometadata', audio_id,
+            'Downloading audio JSON metadata', query=query)['items'][0]
+        title = item['subtitle']
+
+        query['format'] = 'iis'
+        urls = []
+        formats = []
+        for quality in self._QUALITIES:
+            query['quality'] = quality
+            audio_url_data = self._download_json(
+                self._BASE_URL + 'getaudiourl', audio_id,
+                'Downloading %s format JSON metadata' % quality,
+                fatal=False, query=query) or {}
+            audio_url = audio_url_data.get('audioUrl')
+            if not audio_url or audio_url in urls:
+                continue
+            urls.append(audio_url)
+            ext = determine_ext(audio_url)
+            coding_format = audio_url_data.get('codingFormat')
+            abr = int_or_none(self._search_regex(
+                r'_a(\d+)\.m4a', audio_url, 'audio bitrate',
+                default=None)) or self._CODING_FORMAT_TO_ABR_MAP.get(coding_format)
+            formats.append({
+                'abr': abr,
+                'acodec': self._EXT_TO_CODEC_MAP.get(ext),
+                'ext': ext,
+                'format_id': str_or_none(coding_format),
+                'vcodec': 'none',
+                'url': audio_url,
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': audio_id,
+            'title': title,
+            'formats': formats,
+            'series': item.get('title'),
+            'duration': int_or_none(item.get('duration')),
+            'thumbnail': item.get('displayimageurl'),
+            'description': item.get('description'),
+        }
+
+
+class SverigesRadioPublicationIE(SverigesRadioBaseIE):
+    IE_NAME = 'sverigesradio:publication'
+    _VALID_URL = r'https?://(?:www\.)?sverigesradio\.se/sida/(?:artikel|gruppsida)\.aspx\?.*?\bartikel=(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://sverigesradio.se/sida/artikel.aspx?programid=83&artikel=7038546',
+        'md5': '6a4917e1923fccb080e5a206a5afa542',
+        'info_dict': {
+            'id': '7038546',
+            'ext': 'm4a',
+            'duration': 132,
+            'series': 'Nyheter (Ekot)',
+            'title': 'Esa Teittinen: Sanningen har inte kommit fram',
+            'description': 'md5:daf7ce66a8f0a53d5465a5984d3839df',
+            'thumbnail': r're:^https?://.*\.jpg',
+        },
+    }, {
+        'url': 'https://sverigesradio.se/sida/gruppsida.aspx?programid=3304&grupp=6247&artikel=7146887',
+        'only_matching': True,
+    }]
+    _AUDIO_TYPE = 'publication'
+
+
+class SverigesRadioEpisodeIE(SverigesRadioBaseIE):
+    IE_NAME = 'sverigesradio:episode'
+    _VALID_URL = r'https?://(?:www\.)?sverigesradio\.se/(?:sida/)?avsnitt/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://sverigesradio.se/avsnitt/1140922?programid=1300',
+        'md5': '20dc4d8db24228f846be390b0c59a07c',
+        'info_dict': {
+            'id': '1140922',
+            'ext': 'mp3',
+            'duration': 3307,
+            'series': 'Konflikt',
+            'title': 'Metoo och valen',
+            'description': 'md5:fcb5c1f667f00badcc702b196f10a27e',
+            'thumbnail': r're:^https?://.*\.jpg',
+        }
+    }
+    _AUDIO_TYPE = 'episode'

youtube_dl/extractor/youtube.py

@@ -908,6 +908,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'creator': 'Todd Haberman,  Daniel Law Heath and Aaron Kaplan',
                 'track': 'Dark Walk - Position Music',
                 'artist': 'Todd Haberman,  Daniel Law Heath and Aaron Kaplan',
+                'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
             },
             'params': {
                 'skip_download': True,
@@ -2161,9 +2162,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         track = extract_meta('Song')
         artist = extract_meta('Artist')
+        album = extract_meta('Album')
 
         # Youtube Music Auto-generated description
-        album = release_date = release_year = None
+        release_date = release_year = None
         if video_description:
             mobj = re.search(r'(?s)Provided to YouTube by [^\n]+\n+(?P<track>[^·]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?', video_description)
             if mobj:
@@ -2171,7 +2173,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     track = mobj.group('track').strip()
                 if not artist:
                     artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·'))
-                album = mobj.group('album'.strip())
+                if not album:
+                    album = mobj.group('album'.strip())
                 release_year = mobj.group('release_year')
                 release_date = mobj.group('release_date')
                 if release_date: