yt_dlp/extractor/_extractors.py

@@ -354,6 +354,7 @@ from .clipchamp import ClipchampIE
 from .cliphunter import CliphunterIE
 from .clippit import ClippitIE
 from .cliprs import ClipRsIE
+from .clipsyndicate import ClipsyndicateIE
 from .closertotruth import CloserToTruthIE
 from .cloudflarestream import CloudflareStreamIE
 from .clubic import ClubicIE
@@ -642,6 +643,7 @@ from .funimation import (
 )
 from .funk import FunkIE
 from .funker530 import Funker530IE
+from .fusion import FusionIE
 from .fuyintv import FuyinTVIE
 from .gab import (
     GabTVIE,
@@ -721,6 +723,7 @@ from .hgtv import HGTVComShowIE
 from .hketv import HKETVIE
 from .hidive import HiDiveIE
 from .historicfilms import HistoricFilmsIE
+from .hitbox import HitboxIE, HitboxLiveIE
 from .hitrecord import HitRecordIE
 from .hollywoodreporter import (
     HollywoodReporterIE,
@@ -1076,6 +1079,7 @@ from .mlb import (
     MLBArticleIE,
 )
 from .mlssoccer import MLSSoccerIE
+from .mnet import MnetIE
 from .mocha import MochaVideoIE
 from .mojvideo import MojvideoIE
 from .monstercat import MonstercatIE
@@ -2255,6 +2259,7 @@ from .wasdtv import (
     WASDTVClipIE,
 )
 from .wat import WatIE
+from .watchbox import WatchBoxIE
 from .wdr import (
     WDRIE,
     WDRPageIE,

yt_dlp/extractor/clipsyndicate.py

@@ -0,0 +1,52 @@
+from .common import InfoExtractor
+from ..utils import (
+    find_xpath_attr,
+    fix_xml_ampersands
+)
+
+
+class ClipsyndicateIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
+        'md5': '4d7d549451bad625e0ff3d7bd56d776c',
+        'info_dict': {
+            'id': '4629301',
+            'ext': 'mp4',
+            'title': 'Brick Briscoe',
+            'duration': 612,
+            'thumbnail': r're:^https?://.+\.jpg',
+        },
+    }, {
+        'url': 'http://chic.clipsyndicate.com/video/play/5844117/shark_attack',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        js_player = self._download_webpage(
+            'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
+            video_id, 'Downlaoding player')
+        # it includes a required token
+        flvars = self._search_regex(r'flvars: "(.*?)"', js_player, 'flvars')
+
+        pdoc = self._download_xml(
+            'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars,
+            video_id, 'Downloading video info',
+            transform_source=fix_xml_ampersands)
+
+        track_doc = pdoc.find('trackList/track')
+
+        def find_param(name):
+            node = find_xpath_attr(track_doc, './/param', 'name', name)
+            if node is not None:
+                return node.attrib['value']
+
+        return {
+            'id': video_id,
+            'title': find_param('title'),
+            'url': track_doc.find('location').text,
+            'thumbnail': find_param('thumbnail'),
+            'duration': int(find_param('duration')),
+        }

yt_dlp/extractor/fusion.py

@@ -0,0 +1,81 @@
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    mimetype2ext,
+    parse_iso8601,
+)
+
+
+class FusionIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?fusion\.(?:net|tv)/(?:video/|show/.+?\bvideo=)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://fusion.tv/video/201781/u-s-and-panamanian-forces-work-together-to-stop-a-vessel-smuggling-drugs/',
+        'info_dict': {
+            'id': '3145868',
+            'ext': 'mp4',
+            'title': 'U.S. and Panamanian forces work together to stop a vessel smuggling drugs',
+            'description': 'md5:0cc84a9943c064c0f46b128b41b1b0d7',
+            'duration': 140.0,
+            'timestamp': 1442589635,
+            'uploader': 'UNIVISON',
+            'upload_date': '20150918',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['Anvato'],
+    }, {
+        'url': 'http://fusion.tv/video/201781',
+        'only_matching': True,
+    }, {
+        'url': 'https://fusion.tv/show/food-exposed-with-nelufar-hedayat/?ancla=full-episodes&video=588644',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video = self._download_json(
+            'https://platform.fusion.net/wp-json/fusiondotnet/v1/video/' + video_id, video_id)
+
+        info = {
+            'id': video_id,
+            'title': video['title'],
+            'description': video.get('excerpt'),
+            'timestamp': parse_iso8601(video.get('published')),
+            'series': video.get('show'),
+        }
+
+        formats = []
+        src = video.get('src') or {}
+        for f_id, f in src.items():
+            for q_id, q in f.items():
+                q_url = q.get('url')
+                if not q_url:
+                    continue
+                ext = determine_ext(q_url, mimetype2ext(q.get('type')))
+                if ext == 'smil':
+                    formats.extend(self._extract_smil_formats(q_url, video_id, fatal=False))
+                elif f_id == 'm3u8-variant' or (ext == 'm3u8' and q_id == 'Variant'):
+                    formats.extend(self._extract_m3u8_formats(
+                        q_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+                else:
+                    formats.append({
+                        'format_id': '-'.join([f_id, q_id]),
+                        'url': q_url,
+                        'width': int_or_none(q.get('width')),
+                        'height': int_or_none(q.get('height')),
+                        'tbr': int_or_none(self._search_regex(r'_(\d+)\.m(?:p4|3u8)', q_url, 'bitrate')),
+                        'ext': 'mp4' if ext == 'm3u8' else ext,
+                        'protocol': 'm3u8_native' if ext == 'm3u8' else 'https',
+                    })
+        if formats:
+            info['formats'] = formats
+        else:
+            info.update({
+                '_type': 'url',
+                'url': 'anvato:uni:' + video['video_ids']['anvato'],
+                'ie_key': 'Anvato',
+            })
+
+        return info

yt_dlp/extractor/hitbox.py

@@ -0,0 +1,209 @@
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    clean_html,
+    determine_ext,
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class HitboxIE(InfoExtractor):
+    IE_NAME = 'hitbox'
+    _VALID_URL = r'https?://(?:www\.)?(?:hitbox|smashcast)\.tv/(?:[^/]+/)*videos?/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.hitbox.tv/video/203213',
+        'info_dict': {
+            'id': '203213',
+            'title': 'hitbox @ gamescom, Sub Button Hype extended, Giveaway - hitbox News Update with Oxy',
+            'alt_title': 'hitboxlive - Aug 9th #6',
+            'description': '',
+            'ext': 'mp4',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 215.1666,
+            'resolution': 'HD 720p',
+            'uploader': 'hitboxlive',
+            'view_count': int,
+            'timestamp': 1407576133,
+            'upload_date': '20140809',
+            'categories': ['Live Show'],
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.smashcast.tv/hitboxlive/videos/203213',
+        'only_matching': True,
+    }]
+
+    def _extract_metadata(self, url, video_id):
+        thumb_base = 'https://edge.sf.hitbox.tv'
+        metadata = self._download_json(
+            '%s/%s' % (url, video_id), video_id, 'Downloading metadata JSON')
+
+        date = 'media_live_since'
+        media_type = 'livestream'
+        if metadata.get('media_type') == 'video':
+            media_type = 'video'
+            date = 'media_date_added'
+
+        video_meta = metadata.get(media_type, [])[0]
+        title = video_meta.get('media_status')
+        alt_title = video_meta.get('media_title')
+        description = clean_html(
+            video_meta.get('media_description')
+            or video_meta.get('media_description_md'))
+        duration = float_or_none(video_meta.get('media_duration'))
+        uploader = video_meta.get('media_user_name')
+        views = int_or_none(video_meta.get('media_views'))
+        timestamp = parse_iso8601(video_meta.get(date), ' ')
+        categories = [video_meta.get('category_name')]
+        thumbs = [{
+            'url': thumb_base + video_meta.get('media_thumbnail'),
+            'width': 320,
+            'height': 180
+        }, {
+            'url': thumb_base + video_meta.get('media_thumbnail_large'),
+            'width': 768,
+            'height': 432
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'alt_title': alt_title,
+            'description': description,
+            'ext': 'mp4',
+            'thumbnails': thumbs,
+            'duration': duration,
+            'uploader': uploader,
+            'view_count': views,
+            'timestamp': timestamp,
+            'categories': categories,
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        player_config = self._download_json(
+            'https://www.smashcast.tv/api/player/config/video/%s' % video_id,
+            video_id, 'Downloading video JSON')
+
+        formats = []
+        for video in player_config['clip']['bitrates']:
+            label = video.get('label')
+            if label == 'Auto':
+                continue
+            video_url = video.get('url')
+            if not video_url:
+                continue
+            bitrate = int_or_none(video.get('bitrate'))
+            if determine_ext(video_url) == 'm3u8':
+                if not video_url.startswith('http'):
+                    continue
+                formats.append({
+                    'url': video_url,
+                    'ext': 'mp4',
+                    'tbr': bitrate,
+                    'format_note': label,
+                    'protocol': 'm3u8_native',
+                })
+            else:
+                formats.append({
+                    'url': video_url,
+                    'tbr': bitrate,
+                    'format_note': label,
+                })
+
+        metadata = self._extract_metadata(
+            'https://www.smashcast.tv/api/media/video', video_id)
+        metadata['formats'] = formats
+
+        return metadata
+
+
+class HitboxLiveIE(HitboxIE):  # XXX: Do not subclass from concrete IE
+    IE_NAME = 'hitbox:live'
+    _VALID_URL = r'https?://(?:www\.)?(?:hitbox|smashcast)\.tv/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://www.hitbox.tv/dimak',
+        'info_dict': {
+            'id': 'dimak',
+            'ext': 'mp4',
+            'description': 'md5:c9f80fa4410bc588d7faa40003fc7d0e',
+            'timestamp': int,
+            'upload_date': compat_str,
+            'title': compat_str,
+            'uploader': 'Dimak',
+        },
+        'params': {
+            # live
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.smashcast.tv/dimak',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if HitboxIE.suitable(url) else super(HitboxLiveIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        player_config = self._download_json(
+            'https://www.smashcast.tv/api/player/config/live/%s' % video_id,
+            video_id)
+
+        formats = []
+        cdns = player_config.get('cdns')
+        servers = []
+        for cdn in cdns:
+            # Subscribe URLs are not playable
+            if cdn.get('rtmpSubscribe') is True:
+                continue
+            base_url = cdn.get('netConnectionUrl')
+            host = re.search(r'.+\.([^\.]+\.[^\./]+)/.+', base_url).group(1)
+            if base_url not in servers:
+                servers.append(base_url)
+                for stream in cdn.get('bitrates'):
+                    label = stream.get('label')
+                    if label == 'Auto':
+                        continue
+                    stream_url = stream.get('url')
+                    if not stream_url:
+                        continue
+                    bitrate = int_or_none(stream.get('bitrate'))
+                    if stream.get('provider') == 'hls' or determine_ext(stream_url) == 'm3u8':
+                        if not stream_url.startswith('http'):
+                            continue
+                        formats.append({
+                            'url': stream_url,
+                            'ext': 'mp4',
+                            'tbr': bitrate,
+                            'format_note': label,
+                            'rtmp_live': True,
+                        })
+                    else:
+                        formats.append({
+                            'url': '%s/%s' % (base_url, stream_url),
+                            'ext': 'mp4',
+                            'tbr': bitrate,
+                            'rtmp_live': True,
+                            'format_note': host,
+                            'page_url': url,
+                            'player_url': 'http://www.hitbox.tv/static/player/flowplayer/flowplayer.commercial-3.2.16.swf',
+                        })
+
+        metadata = self._extract_metadata(
+            'https://www.smashcast.tv/api/media/live', video_id)
+        metadata['formats'] = formats
+        metadata['is_live'] = True
+        metadata['title'] = metadata.get('title')
+
+        return metadata

yt_dlp/extractor/mnet.py

@@ -0,0 +1,85 @@
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+)
+
+
+class MnetIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?mnet\.(?:com|interest\.me)/tv/vod/(?:.*?\bclip_id=)?(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.mnet.com/tv/vod/171008',
+        'info_dict': {
+            'id': '171008',
+            'title': 'SS_이해인@히든박스',
+            'description': 'md5:b9efa592c3918b615ba69fe9f8a05c55',
+            'duration': 88,
+            'upload_date': '20151231',
+            'timestamp': 1451564040,
+            'age_limit': 0,
+            'thumbnails': 'mincount:5',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'ext': 'flv',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://mnet.interest.me/tv/vod/172790',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.mnet.com/tv/vod/vod_view.asp?clip_id=172790&tabMenu=',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        # TODO: extract rtmp formats
+        # no stype -> rtmp url
+        # stype=H -> m3u8 url
+        # stype=M -> mpd url
+        info = self._download_json(
+            'http://content.api.mnet.com/player/vodConfig',
+            video_id, 'Downloading vod config JSON', query={
+                'id': video_id,
+                'ctype': 'CLIP',
+                'stype': 'H',
+            })['data']['info']
+
+        title = info['title']
+
+        cdn_data = self._download_json(
+            info['cdn'], video_id, 'Downloading vod cdn JSON')['data'][0]
+        m3u8_url = cdn_data['url']
+        token = cdn_data.get('token')
+        if token and token != '-':
+            m3u8_url += '?' + token
+        formats = self._extract_wowza_formats(
+            m3u8_url, video_id, skip_protocols=['rtmp', 'rtsp', 'f4m'])
+
+        description = info.get('ment')
+        duration = parse_duration(info.get('time'))
+        timestamp = parse_iso8601(info.get('date'), delimiter=' ')
+        age_limit = info.get('adult')
+        if age_limit is not None:
+            age_limit = 0 if age_limit == 'N' else 18
+        thumbnails = [{
+            'id': thumb_format,
+            'url': thumb['url'],
+            'width': int_or_none(thumb.get('width')),
+            'height': int_or_none(thumb.get('height')),
+        } for thumb_format, thumb in info.get('cover', {}).items() if thumb.get('url')]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'age_limit': age_limit,
+            'thumbnails': thumbnails,
+            'formats': formats,
+        }

yt_dlp/extractor/watchbox.py

@@ -0,0 +1,153 @@
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    js_to_json,
+    strip_or_none,
+    try_get,
+    unescapeHTML,
+    unified_timestamp,
+)
+
+
+class WatchBoxIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?watchbox\.de/(?P<kind>serien|filme)/(?:[^/]+/)*[^/]+-(?P<id>\d+)'
+    _TESTS = [{
+        # film
+        'url': 'https://www.watchbox.de/filme/free-jimmy-12325.html',
+        'info_dict': {
+            'id': '341368',
+            'ext': 'mp4',
+            'title': 'Free Jimmy',
+            'description': 'md5:bcd8bafbbf9dc0ef98063d344d7cc5f6',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 4890,
+            'age_limit': 16,
+            'release_year': 2009,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'expected_warnings': ['Failed to download m3u8 information'],
+    }, {
+        # episode
+        'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-1/date-in-der-hoelle-328286.html',
+        'info_dict': {
+            'id': '328286',
+            'ext': 'mp4',
+            'title': 'S01 E01 - Date in der Hölle',
+            'description': 'md5:2f31c74a8186899f33cb5114491dae2b',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 1291,
+            'age_limit': 12,
+            'release_year': 2010,
+            'series': 'Ugly Americans',
+            'season_number': 1,
+            'episode': 'Date in der Hölle',
+            'episode_number': 1,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'expected_warnings': ['Failed to download m3u8 information'],
+    }, {
+        'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-2/der-ring-des-powers-328270',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        kind, video_id = mobj.group('kind', 'id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        player_config = self._parse_json(
+            self._search_regex(
+                r'data-player-conf=(["\'])(?P<data>{.+?})\1', webpage,
+                'player config', default='{}', group='data'),
+            video_id, transform_source=unescapeHTML, fatal=False)
+
+        if not player_config:
+            player_config = self._parse_json(
+                self._search_regex(
+                    r'playerConf\s*=\s*({.+?})\s*;', webpage, 'player config',
+                    default='{}'),
+                video_id, transform_source=js_to_json, fatal=False) or {}
+
+        source = player_config.get('source') or {}
+
+        video_id = compat_str(source.get('videoId') or video_id)
+
+        devapi = self._download_json(
+            'http://api.watchbox.de/devapi/id/%s' % video_id, video_id, query={
+                'format': 'json',
+                'apikey': 'hbbtv',
+            }, fatal=False)
+
+        item = try_get(devapi, lambda x: x['items'][0], dict) or {}
+
+        title = item.get('title') or try_get(
+            item, lambda x: x['movie']['headline_movie'],
+            compat_str) or source['title']
+
+        formats = []
+        hls_url = item.get('media_videourl_hls') or source.get('hls')
+        if hls_url:
+            formats.extend(self._extract_m3u8_formats(
+                hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+        dash_url = item.get('media_videourl_wv') or source.get('dash')
+        if dash_url:
+            formats.extend(self._extract_mpd_formats(
+                dash_url, video_id, mpd_id='dash', fatal=False))
+        mp4_url = item.get('media_videourl')
+        if mp4_url:
+            formats.append({
+                'url': mp4_url,
+                'format_id': 'mp4',
+                'width': int_or_none(item.get('width')),
+                'height': int_or_none(item.get('height')),
+                'tbr': int_or_none(item.get('bitrate')),
+            })
+
+        description = strip_or_none(item.get('descr'))
+        thumbnail = item.get('media_content_thumbnail_large') or source.get('poster') or item.get('media_thumbnail')
+        duration = int_or_none(item.get('media_length') or source.get('length'))
+        timestamp = unified_timestamp(item.get('pubDate'))
+        view_count = int_or_none(item.get('media_views'))
+        age_limit = int_or_none(try_get(item, lambda x: x['movie']['fsk']))
+        release_year = int_or_none(try_get(item, lambda x: x['movie']['rel_year']))
+
+        info = {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'age_limit': age_limit,
+            'release_year': release_year,
+            'formats': formats,
+        }
+
+        if kind.lower() == 'serien':
+            series = try_get(
+                item, lambda x: x['special']['title'],
+                compat_str) or source.get('format')
+            season_number = int_or_none(self._search_regex(
+                r'^S(\d{1,2})\s*E\d{1,2}', title, 'season number',
+                default=None) or self._search_regex(
+                    r'/staffel-(\d+)/', url, 'season number', default=None))
+            episode = source.get('title')
+            episode_number = int_or_none(self._search_regex(
+                r'^S\d{1,2}\s*E(\d{1,2})', title, 'episode number',
+                default=None))
+            info.update({
+                'series': series,
+                'season_number': season_number,
+                'episode': episode,
+                'episode_number': episode_number,
+            })
+
+        return info