@tushar-br/desktop 1.0.282 → 1.0.283

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/drbonanza.py

@@ -0,0 +1,54 @@
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    parse_duration,
+    unescapeHTML,
+)
+
+
+class DRBonanzaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/[^/]+/\d+/[^/]+/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
+    _TEST = {
+        'url': 'http://www.dr.dk/bonanza/serie/154/matador/40312/matador---0824-komme-fremmede-',
+        'info_dict': {
+            'id': '40312',
+            'display_id': 'matador---0824-komme-fremmede-',
+            'ext': 'mp4',
+            'title': 'MATADOR - 08:24. "Komme fremmede".',
+            'description': 'md5:77b4c1ac4d4c1b9d610ab4395212ff84',
+            'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
+            'duration': 4613,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        video_id, display_id = mobj.group('id', 'display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        info = self._parse_html5_media_entries(
+            url, webpage, display_id, m3u8_id='hls',
+            m3u8_entry_protocol='m3u8_native')[0]
+
+        asset = self._parse_json(
+            self._search_regex(
+                r'(?s)currentAsset\s*=\s*({.+?})\s*</script', webpage, 'asset'),
+            display_id, transform_source=js_to_json)
+
+        title = unescapeHTML(asset['AssetTitle']).strip()
+
+        def extract(field):
+            return self._search_regex(
+                r'<div[^>]+>\s*<p>%s:<p>\s*</div>\s*<div[^>]+>\s*<p>([^<]+)</p>' % field,
+                webpage, field, default=None)
+
+        info.update({
+            'id': asset.get('AssetId') or video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': extract('Programinfo'),
+            'duration': parse_duration(extract('Tid')),
+            'thumbnail': asset.get('AssetImageUrl'),
+        })
+        return info

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/dreisat.py

@@ -0,0 +1,41 @@
+from .zdf import ZDFIE
+
+
+class DreiSatIE(ZDFIE):  # XXX: Do not subclass from concrete IE
+    IE_NAME = '3sat'
+    _VALID_URL = r'https?://(?:www\.)?3sat\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)\.html'
+    _TESTS = [{
+        # Same as https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html
+        'url': 'https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html',
+        'md5': '0aff3e7bc72c8813f5e0fae333316a1d',
+        'info_dict': {
+            'id': '141007_ab18_10wochensommer_film',
+            'ext': 'mp4',
+            'title': 'Ab 18! - 10 Wochen Sommer',
+            'description': 'md5:8253f41dc99ce2c3ff892dac2d65fe26',
+            'duration': 2660,
+            'timestamp': 1608604200,
+            'upload_date': '20201222',
+        },
+    }, {
+        'url': 'https://www.3sat.de/gesellschaft/schweizweit/waidmannsheil-100.html',
+        'info_dict': {
+            'id': '140913_sendung_schweizweit',
+            'ext': 'mp4',
+            'title': 'Waidmannsheil',
+            'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
+            'timestamp': 1410623100,
+            'upload_date': '20140913'
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        # Same as https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html
+        'url': 'https://www.3sat.de/film/spielfilm/der-hauptmann-100.html',
+        'only_matching': True,
+    }, {
+        # Same as https://www.zdf.de/wissen/nano/nano-21-mai-2019-102.html, equal media ids
+        'url': 'https://www.3sat.de/wissen/nano/nano-21-mai-2019-102.html',
+        'only_matching': True,
+    }]

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/drooble.py

@@ -0,0 +1,113 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    try_get,
+)
+
+
+class DroobleIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://drooble\.com/(?:
+        (?:(?P<user>[^/]+)/)?(?P<kind>song|videos|music/albums)/(?P<id>\d+)|
+        (?P<user_2>[^/]+)/(?P<kind_2>videos|music))
+    '''
+    _TESTS = [{
+        'url': 'https://drooble.com/song/2858030',
+        'md5': '5ffda90f61c7c318dc0c3df4179eb064',
+        'info_dict': {
+            'id': '2858030',
+            'ext': 'mp3',
+            'title': 'Skankocillin',
+            'upload_date': '20200801',
+            'timestamp': 1596241390,
+            'uploader_id': '95894',
+            'uploader': 'Bluebeat Shelter',
+        }
+    }, {
+        'url': 'https://drooble.com/karl340758/videos/2859183',
+        'info_dict': {
+            'id': 'J6QCQY_I5Tk',
+            'ext': 'mp4',
+            'title': 'Skankocillin',
+            'uploader_id': 'UCrSRoI5vVyeYihtWEYua7rg',
+            'description': 'md5:ffc0bd8ba383db5341a86a6cd7d9bcca',
+            'upload_date': '20200731',
+            'uploader': 'Bluebeat Shelter',
+        }
+    }, {
+        'url': 'https://drooble.com/karl340758/music/albums/2858031',
+        'info_dict': {
+            'id': '2858031',
+        },
+        'playlist_mincount': 8,
+    }, {
+        'url': 'https://drooble.com/karl340758/music',
+        'info_dict': {
+            'id': 'karl340758',
+        },
+        'playlist_mincount': 8,
+    }, {
+        'url': 'https://drooble.com/karl340758/videos',
+        'info_dict': {
+            'id': 'karl340758',
+        },
+        'playlist_mincount': 8,
+    }]
+
+    def _call_api(self, method, video_id, data=None):
+        response = self._download_json(
+            f'https://drooble.com/api/dt/{method}', video_id, data=json.dumps(data).encode())
+        if not response[0]:
+            raise ExtractorError('Unable to download JSON metadata')
+        return response[1]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        user = mobj.group('user') or mobj.group('user_2')
+        kind = mobj.group('kind') or mobj.group('kind_2')
+        display_id = mobj.group('id') or user
+
+        if mobj.group('kind_2') == 'videos':
+            data = {'from_user': display_id, 'album': -1, 'limit': 18, 'offset': 0, 'order': 'new2old', 'type': 'video'}
+        elif kind in ('music/albums', 'music'):
+            data = {'user': user, 'public_only': True, 'individual_limit': {'singles': 1, 'albums': 1, 'playlists': 1}}
+        else:
+            data = {'url_slug': display_id, 'children': 10, 'order': 'old2new'}
+
+        method = 'getMusicOverview' if kind in ('music/albums', 'music') else 'getElements'
+        json_data = self._call_api(method, display_id, data=data)
+        if kind in ('music/albums', 'music'):
+            json_data = json_data['singles']['list']
+
+        entites = []
+        for media in json_data:
+            url = media.get('external_media_url') or media.get('link')
+            if url.startswith('https://www.youtube.com'):
+                entites.append({
+                    '_type': 'url',
+                    'url': url,
+                    'ie_key': 'Youtube'
+                })
+                continue
+            is_audio = (media.get('type') or '').lower() == 'audio'
+            entites.append({
+                'url': url,
+                'id': media['id'],
+                'title': media['title'],
+                'duration': int_or_none(media.get('duration')),
+                'timestamp': int_or_none(media.get('timestamp')),
+                'album': try_get(media, lambda x: x['album']['title']),
+                'uploader': try_get(media, lambda x: x['creator']['display_name']),
+                'uploader_id': try_get(media, lambda x: x['creator']['id']),
+                'thumbnail': media.get('image_comment'),
+                'like_count': int_or_none(media.get('likes')),
+                'vcodec': 'none' if is_audio else None,
+                'ext': 'mp3' if is_audio else None,
+            })
+
+        if len(entites) > 1:
+            return self.playlist_result(entites, display_id)
+
+        return entites[0]

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/dropbox.py

@@ -0,0 +1,90 @@
+import base64
+import os.path
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
+from ..utils import (
+    ExtractorError,
+    update_url_query,
+    url_basename,
+)
+
+
+class DropboxIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?dropbox\.com/(?:(?:e/)?scl/fi|sh?)/(?P<id>\w+)'
+    _TESTS = [
+        {
+            'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0',
+            'info_dict': {
+                'id': 'nelirfsxnmcfbfh',
+                'ext': 'mp4',
+                'title': 'youtube-dl test video \'ä"BaW_jenozKc'
+            }
+        }, {
+            'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh',
+            'only_matching': True,
+        }, {
+            'url': 'https://www.dropbox.com/sh/2mgpiuq7kv8nqdf/AABy-fW4dkydT4GmWi2mdOUDa?dl=0&preview=Drone+Shot.mp4',
+            'only_matching': True,
+        }, {
+            'url': 'https://www.dropbox.com/scl/fi/r2kd2skcy5ylbbta5y1pz/DJI_0003.MP4?dl=0&rlkey=wcdgqangn7t3lnmmv6li9mu9h',
+            'only_matching': True,
+        }, {
+            'url': 'https://www.dropbox.com/e/scl/fi/r2kd2skcy5ylbbta5y1pz/DJI_0003.MP4?dl=0&rlkey=wcdgqangn7t3lnmmv6li9mu9h',
+            'only_matching': True,
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        fn = compat_urllib_parse_unquote(url_basename(url))
+        title = os.path.splitext(fn)[0]
+
+        password = self.get_param('videopassword')
+        if (self._og_search_title(webpage) == 'Dropbox - Password Required'
+                or 'Enter the password for this link' in webpage):
+
+            if password:
+                content_id = self._search_regex(r'content_id=(.*?)["\']', webpage, 'content_id')
+                payload = f'is_xhr=true&t={self._get_cookies("https://www.dropbox.com").get("t").value}&content_id={content_id}&password={password}&url={url}'
+                response = self._download_json(
+                    'https://www.dropbox.com/sm/auth', video_id, 'POSTing video password', data=payload.encode('UTF-8'),
+                    headers={'content-type': 'application/x-www-form-urlencoded; charset=UTF-8'})
+
+                if response.get('status') != 'authed':
+                    raise ExtractorError('Authentication failed!', expected=True)
+                webpage = self._download_webpage(url, video_id)
+            elif self._get_cookies('https://dropbox.com').get('sm_auth'):
+                webpage = self._download_webpage(url, video_id)
+            else:
+                raise ExtractorError('Password protected video, use --video-password <password>', expected=True)
+
+        formats, subtitles, has_anonymous_download = [], {}, False
+        for encoded in reversed(re.findall(r'registerStreamedPrefetch\s*\(\s*"[\w/+=]+"\s*,\s*"([\w/+=]+)"', webpage)):
+            decoded = base64.b64decode(encoded).decode('utf-8', 'ignore')
+            transcode_url = self._search_regex(
+                r'\n.(https://[^\x03\x08\x12\n]+\.m3u8)', decoded, 'transcode url', default=None)
+            if not transcode_url:
+                continue
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(transcode_url, video_id, 'mp4')
+            has_anonymous_download = self._search_regex(r'(anonymous:\tanonymous)', decoded, 'anonymous', default=False)
+            break
+
+        # downloads enabled we can get the original file
+        if has_anonymous_download:
+            formats.append({
+                'url': update_url_query(url, {'dl': '1'}),
+                'format_id': 'original',
+                'format_note': 'Original',
+                'quality': 1
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'subtitles': subtitles
+        }

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/dropout.py

@@ -0,0 +1,224 @@
+import functools
+
+from .common import InfoExtractor
+from .vimeo import VHXEmbedIE
+from ..utils import (
+    ExtractorError,
+    OnDemandPagedList,
+    clean_html,
+    extract_attributes,
+    get_element_by_class,
+    get_element_by_id,
+    get_elements_html_by_class,
+    int_or_none,
+    traverse_obj,
+    unified_strdate,
+    urlencode_postdata,
+)
+
+
+class DropoutIE(InfoExtractor):
+    _LOGIN_URL = 'https://www.dropout.tv/login'
+    _NETRC_MACHINE = 'dropout'
+
+    _VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
+    _TESTS = [
+        {
+            'url': 'https://www.dropout.tv/game-changer/season:2/videos/yes-or-no',
+            'note': 'Episode in a series',
+            'md5': '5e000fdfd8d8fa46ff40456f1c2af04a',
+            'info_dict': {
+                'id': '738153',
+                'display_id': 'yes-or-no',
+                'ext': 'mp4',
+                'title': 'Yes or No',
+                'description': 'Ally, Brennan, and Zac are asked a simple question, but is there a correct answer?',
+                'release_date': '20200508',
+                'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/351e3f24-c4a3-459a-8b79-dc80f1e5b7fd.jpg',
+                'series': 'Game Changer',
+                'season_number': 2,
+                'season': 'Season 2',
+                'episode_number': 6,
+                'episode': 'Yes or No',
+                'duration': 1180,
+                'uploader_id': 'user80538407',
+                'uploader_url': 'https://vimeo.com/user80538407',
+                'uploader': 'OTT Videos'
+            },
+            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest']
+        },
+        {
+            'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1/videos/episode-1',
+            'note': 'Episode in a series (missing release_date)',
+            'md5': '712caf7c191f1c47c8f1879520c2fa5c',
+            'info_dict': {
+                'id': '320562',
+                'display_id': 'episode-1',
+                'ext': 'mp4',
+                'title': 'The Beginning Begins',
+                'description': 'The cast introduces their PCs, including a neurotic elf, a goblin PI, and a corn-worshipping cleric.',
+                'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/4421ed0d-f630-4c88-9004-5251b2b8adfa.jpg',
+                'series': 'Dimension 20: Fantasy High',
+                'season_number': 1,
+                'season': 'Season 1',
+                'episode_number': 1,
+                'episode': 'The Beginning Begins',
+                'duration': 6838,
+                'uploader_id': 'user80538407',
+                'uploader_url': 'https://vimeo.com/user80538407',
+                'uploader': 'OTT Videos'
+            },
+            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest']
+        },
+        {
+            'url': 'https://www.dropout.tv/videos/misfits-magic-holiday-special',
+            'note': 'Episode not in a series',
+            'md5': 'c30fa18999c5880d156339f13c953a26',
+            'info_dict': {
+                'id': '1915774',
+                'display_id': 'misfits-magic-holiday-special',
+                'ext': 'mp4',
+                'title': 'Misfits & Magic Holiday Special',
+                'description': 'The magical misfits spend Christmas break at Gowpenny, with an unwelcome visitor.',
+                'release_date': '20211215',
+                'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/d91ea8a6-b250-42ed-907e-b30fb1c65176-8e24b8e5.jpg',
+                'duration': 11698,
+                'uploader_id': 'user80538407',
+                'uploader_url': 'https://vimeo.com/user80538407',
+                'uploader': 'OTT Videos'
+            },
+            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest']
+        }
+    ]
+
+    def _get_authenticity_token(self, display_id):
+        signin_page = self._download_webpage(
+            self._LOGIN_URL, display_id, note='Getting authenticity token')
+        return self._html_search_regex(
+            r'name=["\']authenticity_token["\'] value=["\'](.+?)["\']',
+            signin_page, 'authenticity_token')
+
+    def _login(self, display_id):
+        username, password = self._get_login_info()
+        if not username:
+            return True
+
+        response = self._download_webpage(
+            self._LOGIN_URL, display_id, note='Logging in', fatal=False,
+            data=urlencode_postdata({
+                'email': username,
+                'password': password,
+                'authenticity_token': self._get_authenticity_token(display_id),
+                'utf8': True
+            }))
+
+        user_has_subscription = self._search_regex(
+            r'user_has_subscription:\s*["\'](.+?)["\']', response, 'subscription status', default='none')
+        if user_has_subscription.lower() == 'true':
+            return
+        elif user_has_subscription.lower() == 'false':
+            return 'Account is not subscribed'
+        else:
+            return 'Incorrect username/password'
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = None
+        if self._get_cookies('https://www.dropout.tv').get('_session'):
+            webpage = self._download_webpage(url, display_id)
+        if not webpage or '<div id="watch-unauthorized"' in webpage:
+            login_err = self._login(display_id)
+            webpage = self._download_webpage(url, display_id)
+            if login_err and '<div id="watch-unauthorized"' in webpage:
+                if login_err is True:
+                    self.raise_login_required(method='any')
+                raise ExtractorError(login_err, expected=True)
+
+        embed_url = self._search_regex(r'embed_url:\s*["\'](.+?)["\']', webpage, 'embed url')
+        thumbnail = self._og_search_thumbnail(webpage)
+        watch_info = get_element_by_id('watch-info', webpage) or ''
+
+        title = clean_html(get_element_by_class('video-title', watch_info))
+        season_episode = get_element_by_class(
+            'site-font-secondary-color', get_element_by_class('text', watch_info))
+        episode_number = int_or_none(self._search_regex(
+            r'Episode (\d+)', season_episode or '', 'episode', default=None))
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': VHXEmbedIE.ie_key(),
+            'url': VHXEmbedIE._smuggle_referrer(embed_url, 'https://www.dropout.tv'),
+            'id': self._search_regex(r'embed\.vhx\.tv/videos/(.+?)\?', embed_url, 'id'),
+            'display_id': display_id,
+            'title': title,
+            'description': self._html_search_meta('description', webpage, fatal=False),
+            'thumbnail': thumbnail.split('?')[0] if thumbnail else None,  # Ignore crop/downscale
+            'series': clean_html(get_element_by_class('series-title', watch_info)),
+            'episode_number': episode_number,
+            'episode': title if episode_number else None,
+            'season_number': int_or_none(self._search_regex(
+                r'Season (\d+),', season_episode or '', 'season', default=None)),
+            'release_date': unified_strdate(self._search_regex(
+                r'data-meta-field-name=["\']release_dates["\'] data-meta-field-value=["\'](.+?)["\']',
+                watch_info, 'release date', default=None)),
+        }
+
+
+class DropoutSeasonIE(InfoExtractor):
+    _PAGE_SIZE = 24
+    _VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
+    _TESTS = [
+        {
+            'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1',
+            'note': 'Multi-season series with the season in the url',
+            'playlist_count': 24,
+            'info_dict': {
+                'id': 'dimension-20-fantasy-high-season-1',
+                'title': 'Dimension 20 Fantasy High - Season 1'
+            }
+        },
+        {
+            'url': 'https://www.dropout.tv/dimension-20-fantasy-high',
+            'note': 'Multi-season series with the season not in the url',
+            'playlist_count': 24,
+            'info_dict': {
+                'id': 'dimension-20-fantasy-high-season-1',
+                'title': 'Dimension 20 Fantasy High - Season 1'
+            }
+        },
+        {
+            'url': 'https://www.dropout.tv/dimension-20-shriek-week',
+            'note': 'Single-season series',
+            'playlist_count': 4,
+            'info_dict': {
+                'id': 'dimension-20-shriek-week-season-1',
+                'title': 'Dimension 20 Shriek Week - Season 1'
+            }
+        },
+        {
+            'url': 'https://www.dropout.tv/breaking-news-no-laugh-newsroom/season:3',
+            'note': 'Multi-season series with season in the url that requires pagination',
+            'playlist_count': 25,
+            'info_dict': {
+                'id': 'breaking-news-no-laugh-newsroom-season-3',
+                'title': 'Breaking News No Laugh Newsroom - Season 3'
+            }
+        }
+    ]
+
+    def _fetch_page(self, url, season_id, page):
+        page += 1
+        webpage = self._download_webpage(
+            f'{url}?page={page}', season_id, note=f'Downloading page {page}', expected_status={400})
+        yield from [self.url_result(item_url, DropoutIE) for item_url in traverse_obj(
+            get_elements_html_by_class('browse-item-link', webpage), (..., {extract_attributes}, 'href'))]
+
+    def _real_extract(self, url):
+        season_id = self._match_id(url)
+        season_num = self._match_valid_url(url).group('season') or 1
+        season_title = season_id.replace('-', ' ').title()
+
+        return self.playlist_result(
+            OnDemandPagedList(functools.partial(self._fetch_page, url, season_id), self._PAGE_SIZE),
+            f'{season_id}-season-{season_num}', f'{season_title} - Season {season_num}')

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/drtuber.py

@@ -0,0 +1,104 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    NO_DEFAULT,
+    parse_duration,
+    str_to_int,
+)
+
+
+class DrTuberIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
+    _EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)']
+    _TESTS = [{
+        'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
+        'md5': '93e680cf2536ad0dfb7e74d94a89facd',
+        'info_dict': {
+            'id': '1740434',
+            'display_id': 'hot-perky-blonde-naked-golf',
+            'ext': 'mp4',
+            'title': 'hot perky blonde naked golf',
+            'like_count': int,
+            'comment_count': int,
+            'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
+            'thumbnail': r're:https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }, {
+        'url': 'http://www.drtuber.com/embed/489939',
+        'only_matching': True,
+    }, {
+        'url': 'http://m.drtuber.com/video/3893529/lingerie-blowjob-from-beautiful-teen',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
+
+        webpage = self._download_webpage(
+            'http://www.drtuber.com/video/%s' % video_id, display_id)
+
+        video_data = self._download_json(
+            'http://www.drtuber.com/player_config_json/', video_id, query={
+                'vid': video_id,
+                'embed': 0,
+                'aid': 0,
+                'domain_id': 0,
+            })
+
+        formats = []
+        for format_id, video_url in video_data['files'].items():
+            if video_url:
+                formats.append({
+                    'format_id': format_id,
+                    'quality': 2 if format_id == 'hq' else 1,
+                    'url': video_url
+                })
+
+        duration = int_or_none(video_data.get('duration')) or parse_duration(
+            video_data.get('duration_format'))
+
+        title = self._html_search_regex(
+            (r'<h1[^>]+class=["\']title[^>]+>([^<]+)',
+             r'<title>([^<]+)\s*@\s+DrTuber',
+             r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
+             r'<p[^>]+class="title_substrate">([^<]+)</p>',
+             r'<title>([^<]+) - \d+'),
+            webpage, 'title')
+
+        thumbnail = self._html_search_regex(
+            r'poster="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        def extract_count(id_, name, default=NO_DEFAULT):
+            return str_to_int(self._html_search_regex(
+                r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
+                webpage, '%s count' % name, default=default, fatal=False))
+
+        like_count = extract_count('rate_likes', 'like')
+        dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
+        comment_count = extract_count('comments_count', 'comment')
+
+        cats_str = self._search_regex(
+            r'<div[^>]+class="categories_list">(.+?)</div>',
+            webpage, 'categories', fatal=False)
+        categories = [] if not cats_str else re.findall(
+            r'<a title="([^"]+)"', cats_str)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'formats': formats,
+            'title': title,
+            'thumbnail': thumbnail,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'comment_count': comment_count,
+            'categories': categories,
+            'age_limit': self._rta_search(webpage),
+            'duration': duration,
+        }