@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/agora.py

@@ -0,0 +1,251 @@
+import functools
+import uuid
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    OnDemandPagedList,
+    int_or_none,
+    month_by_name,
+    parse_duration,
+    try_call,
+)
+
+
+class WyborczaVideoIE(InfoExtractor):
+    # this id is not an article id, it has to be extracted from the article
+    _VALID_URL = r'(?:wyborcza:video:|https?://wyborcza\.pl/(?:api-)?video/)(?P<id>\d+)'
+    IE_NAME = 'wyborcza:video'
+    _TESTS = [{
+        'url': 'wyborcza:video:26207634',
+        'info_dict': {
+            'id': '26207634',
+            'ext': 'mp4',
+            'title': '- Polska w 2020 r. jest innym państwem niż w 2015 r. Nie zmieniła się konstytucja, ale jest to już inny ustrój - mówi Adam Bodnar',
+            'description': ' ',
+            'uploader': 'Dorota Roman',
+            'duration': 2474,
+            'thumbnail': r're:https://.+\.jpg',
+        },
+    }, {
+        'url': 'https://wyborcza.pl/video/26207634',
+        'only_matching': True,
+    }, {
+        'url': 'https://wyborcza.pl/api-video/26207634',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        meta = self._download_json(f'https://wyborcza.pl/api-video/{video_id}', video_id)
+
+        formats = []
+        base_url = meta['redirector'].replace('http://', 'https://') + meta['basePath']
+        for quality in ('standard', 'high'):
+            if not meta['files'].get(quality):
+                continue
+            formats.append({
+                'url': base_url + meta['files'][quality],
+                'height': int_or_none(
+                    self._search_regex(
+                        r'p(\d+)[a-z]+\.mp4$', meta['files'][quality],
+                        'mp4 video height', default=None)),
+                'format_id': quality,
+            })
+        if meta['files'].get('dash'):
+            formats.extend(self._extract_mpd_formats(base_url + meta['files']['dash'], video_id))
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': meta.get('title'),
+            'description': meta.get('lead'),
+            'uploader': meta.get('signature'),
+            'thumbnail': meta.get('imageUrl'),
+            'duration': meta.get('duration'),
+        }
+
+
+class WyborczaPodcastIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?(?:
+            wyborcza\.pl/podcast(?:/0,172673\.html)?|
+            wysokieobcasy\.pl/wysokie-obcasy/0,176631\.html
+        )(?:\?(?:[^&#]+?&)*podcast=(?P<id>\d+))?
+    '''
+    _TESTS = [{
+        'url': 'https://wyborcza.pl/podcast/0,172673.html?podcast=100720#S.main_topic-K.C-B.6-L.1.podcast',
+        'info_dict': {
+            'id': '100720',
+            'ext': 'mp3',
+            'title': 'Cyfrodziewczyny. Kim były pionierki polskiej informatyki ',
+            'uploader': 'Michał Nogaś ',
+            'upload_date': '20210117',
+            'description': 'md5:49f0a06ffc4c1931210d3ab1416a651d',
+            'duration': 3684.0,
+            'thumbnail': r're:https://.+\.jpg',
+        },
+    }, {
+        'url': 'https://www.wysokieobcasy.pl/wysokie-obcasy/0,176631.html?podcast=100673',
+        'info_dict': {
+            'id': '100673',
+            'ext': 'mp3',
+            'title': 'Czym jest ubóstwo menstruacyjne i dlaczego dotyczy każdej i każdego z nas?',
+            'uploader': 'Agnieszka Urazińska ',
+            'upload_date': '20210115',
+            'description': 'md5:c161dc035f8dbb60077011fc41274899',
+            'duration': 1803.0,
+            'thumbnail': r're:https://.+\.jpg',
+        },
+    }, {
+        'url': 'https://wyborcza.pl/podcast',
+        'info_dict': {
+            'id': '334',
+            'title': 'Gościnnie: Wyborcza, 8:10',
+            'series': 'Gościnnie: Wyborcza, 8:10',
+        },
+        'playlist_mincount': 370,
+    }, {
+        'url': 'https://www.wysokieobcasy.pl/wysokie-obcasy/0,176631.html',
+        'info_dict': {
+            'id': '395',
+            'title': 'Gościnnie: Wysokie Obcasy',
+            'series': 'Gościnnie: Wysokie Obcasy',
+        },
+        'playlist_mincount': 12,
+    }]
+
+    def _real_extract(self, url):
+        podcast_id = self._match_id(url)
+
+        if not podcast_id:  # playlist
+            podcast_id = '395' if 'wysokieobcasy.pl/' in url else '334'
+            return self.url_result(TokFMAuditionIE._create_url(podcast_id), TokFMAuditionIE, podcast_id)
+
+        meta = self._download_json('https://wyborcza.pl/api/podcast', podcast_id,
+                                   query={'guid': podcast_id, 'type': 'wo' if 'wysokieobcasy.pl/' in url else None})
+
+        day, month, year = self._search_regex(r'^(\d\d?) (\w+) (\d{4})$', meta.get('publishedDate'),
+                                              'upload date', group=(1, 2, 3), default=(None, None, None))
+        return {
+            'id': podcast_id,
+            'url': meta['url'],
+            'title': meta.get('title'),
+            'description': meta.get('description'),
+            'thumbnail': meta.get('imageUrl'),
+            'duration': parse_duration(meta.get('duration')),
+            'uploader': meta.get('author'),
+            'upload_date': try_call(lambda: f'{year}{month_by_name(month, lang="pl"):0>2}{day:0>2}'),
+        }
+
+
+class TokFMPodcastIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://audycje\.tokfm\.pl/podcast/|tokfm:podcast:)(?P<id>\d+),?'
+    IE_NAME = 'tokfm:podcast'
+    _TESTS = [{
+        'url': 'https://audycje.tokfm.pl/podcast/91275,-Systemowy-rasizm-Czy-zamieszki-w-USA-po-morderstwie-w-Minneapolis-doprowadza-do-zmian-w-sluzbach-panstwowych',
+        'info_dict': {
+            'id': '91275',
+            'ext': 'aac',
+            'title': 'md5:a9b15488009065556900169fb8061cce',
+            'episode': 'md5:a9b15488009065556900169fb8061cce',
+            'series': 'Analizy',
+        },
+    }]
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+
+        # in case it breaks see this but it returns a lot of useless data
+        # https://api.podcast.radioagora.pl/api4/getPodcasts?podcast_id=100091&with_guests=true&with_leaders_for_mobile=true
+        metadata = self._download_json(
+            f'https://audycje.tokfm.pl/getp/3{media_id}', media_id, 'Downloading podcast metadata')
+        if not metadata:
+            raise ExtractorError('No such podcast', expected=True)
+        metadata = metadata[0]
+
+        formats = []
+        for ext in ('aac', 'mp3'):
+            url_data = self._download_json(
+                f'https://api.podcast.radioagora.pl/api4/getSongUrl?podcast_id={media_id}&device_id={uuid.uuid4()}&ppre=false&audio={ext}',
+                media_id, 'Downloading podcast %s URL' % ext)
+            # prevents inserting the mp3 (default) multiple times
+            if 'link_ssl' in url_data and f'.{ext}' in url_data['link_ssl']:
+                formats.append({
+                    'url': url_data['link_ssl'],
+                    'ext': ext,
+                    'vcodec': 'none',
+                    'acodec': ext,
+                })
+
+        return {
+            'id': media_id,
+            'formats': formats,
+            'title': metadata.get('podcast_name'),
+            'series': metadata.get('series_name'),
+            'episode': metadata.get('podcast_name'),
+        }
+
+
+class TokFMAuditionIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://audycje\.tokfm\.pl/audycja/|tokfm:audition:)(?P<id>\d+),?'
+    IE_NAME = 'tokfm:audition'
+    _TESTS = [{
+        'url': 'https://audycje.tokfm.pl/audycja/218,Analizy',
+        'info_dict': {
+            'id': '218',
+            'title': 'Analizy',
+            'series': 'Analizy',
+        },
+        'playlist_count': 1635,
+    }]
+
+    _PAGE_SIZE = 30
+    _HEADERS = {
+        'User-Agent': 'Mozilla/5.0 (Linux; Android 9; Redmi 3S Build/PQ3A.190801.002; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/87.0.4280.101 Mobile Safari/537.36',
+    }
+
+    @staticmethod
+    def _create_url(id):
+        return f'https://audycje.tokfm.pl/audycja/{id}'
+
+    def _real_extract(self, url):
+        audition_id = self._match_id(url)
+
+        data = self._download_json(
+            f'https://api.podcast.radioagora.pl/api4/getSeries?series_id={audition_id}',
+            audition_id, 'Downloading audition metadata', headers=self._HEADERS)
+        if not data:
+            raise ExtractorError('No such audition', expected=True)
+        data = data[0]
+
+        entries = OnDemandPagedList(functools.partial(
+            self._fetch_page, audition_id, data), self._PAGE_SIZE)
+
+        return {
+            '_type': 'playlist',
+            'id': audition_id,
+            'title': data.get('series_name'),
+            'series': data.get('series_name'),
+            'entries': entries,
+        }
+
+    def _fetch_page(self, audition_id, data, page):
+        for retry in self.RetryManager():
+            podcast_page = self._download_json(
+                f'https://api.podcast.radioagora.pl/api4/getPodcasts?series_id={audition_id}&limit=30&offset={page}&with_guests=true&with_leaders_for_mobile=true',
+                audition_id, f'Downloading podcast list page {page + 1}', headers=self._HEADERS)
+            if not podcast_page:
+                retry.error = ExtractorError('Agora returned empty page', expected=True)
+
+        for podcast in podcast_page:
+            yield {
+                '_type': 'url_transparent',
+                'url': podcast['podcast_sharing_url'],
+                'ie_key': TokFMPodcastIE.ie_key(),
+                'title': podcast.get('podcast_name'),
+                'episode': podcast.get('podcast_name'),
+                'description': podcast.get('podcast_description'),
+                'timestamp': int_or_none(podcast.get('podcast_timestamp')),
+                'series': data.get('series_name'),
+            }

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

@@ -0,0 +1,96 @@
+from .common import InfoExtractor
+from .youtube import YoutubeIE
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    mimetype2ext,
+    parse_iso8601,
+    traverse_obj
+)
+
+
+class AirTVIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.air\.tv/watch\?v=(?P<id>\w+)'
+    _TESTS = [{
+        # without youtube_id
+        'url': 'https://www.air.tv/watch?v=W87jcWleSn2hXZN47zJZsQ',
+        'info_dict': {
+            'id': 'W87jcWleSn2hXZN47zJZsQ',
+            'ext': 'mp4',
+            'release_date': '20221003',
+            'release_timestamp': 1664792603,
+            'channel_id': 'vgfManQlRQKgoFQ8i8peFQ',
+            'title': 'md5:c12d49ed367c3dadaa67659aff43494c',
+            'upload_date': '20221003',
+            'duration': 151,
+            'view_count': int,
+            'thumbnail': 'https://cdn-sp-gcs.air.tv/videos/W/8/W87jcWleSn2hXZN47zJZsQ/b13fc56464f47d9d62a36d110b9b5a72-4096x2160_9.jpg',
+            'timestamp': 1664792603,
+        }
+    }, {
+        # with youtube_id
+        'url': 'https://www.air.tv/watch?v=sv57EC8tRXG6h8dNXFUU1Q',
+        'info_dict': {
+            'id': '2ZTqmpee-bQ',
+            'ext': 'mp4',
+            'comment_count': int,
+            'tags': 'count:11',
+            'channel_follower_count': int,
+            'like_count': int,
+            'uploader': 'Newsflare',
+            'thumbnail': 'https://i.ytimg.com/vi_webp/2ZTqmpee-bQ/maxresdefault.webp',
+            'availability': 'public',
+            'title': 'Geese Chase Alligator Across Golf Course',
+            'uploader_id': 'NewsflareBreaking',
+            'channel_url': 'https://www.youtube.com/channel/UCzSSoloGEz10HALUAbYhngQ',
+            'description': 'md5:99b21d9cea59330149efbd9706e208f5',
+            'age_limit': 0,
+            'channel_id': 'UCzSSoloGEz10HALUAbYhngQ',
+            'uploader_url': 'http://www.youtube.com/user/NewsflareBreaking',
+            'view_count': int,
+            'categories': ['News & Politics'],
+            'live_status': 'not_live',
+            'playable_in_embed': True,
+            'channel': 'Newsflare',
+            'duration': 37,
+            'upload_date': '20180511',
+        }
+    }]
+
+    def _get_formats_and_subtitle(self, json_data, video_id):
+        formats, subtitles = [], {}
+        for source in traverse_obj(json_data, 'sources', 'sources_desktop', ...):
+            ext = determine_ext(source.get('src'), mimetype2ext(source.get('type')))
+            if ext == 'm3u8':
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(source.get('src'), video_id)
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
+            else:
+                formats.append({'url': source.get('src'), 'ext': ext})
+        return formats, subtitles
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        nextjs_json = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['initialState']['videos'][display_id]
+        if nextjs_json.get('youtube_id'):
+            return self.url_result(
+                f'https://www.youtube.com/watch?v={nextjs_json.get("youtube_id")}', YoutubeIE)
+
+        formats, subtitles = self._get_formats_and_subtitle(nextjs_json, display_id)
+        return {
+            'id': display_id,
+            'title': nextjs_json.get('title') or self._html_search_meta('og:title', webpage),
+            'formats': formats,
+            'subtitles': subtitles,
+            'description': nextjs_json.get('description') or None,
+            'duration': int_or_none(nextjs_json.get('duration')),
+            'thumbnails': [
+                {'url': thumbnail}
+                for thumbnail in traverse_obj(nextjs_json, ('default_thumbnails', ...))],
+            'channel_id': traverse_obj(nextjs_json, 'channel', 'channel_slug'),
+            'timestamp': parse_iso8601(nextjs_json.get('created')),
+            'release_timestamp': parse_iso8601(nextjs_json.get('published')),
+            'view_count': int_or_none(nextjs_json.get('views')),
+        }

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

@@ -0,0 +1,60 @@
+from .common import InfoExtractor
+from ..utils import int_or_none, merge_dicts
+
+
+class AitubeKZVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://aitube\.kz/(?:video|embed/)\?(?:[^\?]+)?id=(?P<id>[\w-]+)'
+    _TESTS = [{
+        # id paramater as first parameter
+        'url': 'https://aitube.kz/video?id=9291d29b-c038-49a1-ad42-3da2051d353c&playlistId=d55b1f5f-ef2a-4f23-b646-2a86275b86b7&season=1',
+        'info_dict': {
+            'id': '9291d29b-c038-49a1-ad42-3da2051d353c',
+            'ext': 'mp4',
+            'duration': 2174.0,
+            'channel_id': '94962f73-013b-432c-8853-1bd78ca860fe',
+            'like_count': int,
+            'channel': 'ASTANA TV',
+            'comment_count': int,
+            'view_count': int,
+            'description': 'Смотреть любимые сериалы и видео, поделиться видео и сериалами с друзьями и близкими',
+            'thumbnail': 'https://cdn.static02.aitube.kz/kz.aitudala.aitube.staticaccess/files/ddf2a2ff-bee3-409b-b5f2-2a8202bba75b',
+            'upload_date': '20221102',
+            'timestamp': 1667370519,
+            'title': 'Ангел хранитель 1 серия',
+            'channel_follower_count': int,
+        }
+    }, {
+        # embed url
+        'url': 'https://aitube.kz/embed/?id=9291d29b-c038-49a1-ad42-3da2051d353c',
+        'only_matching': True,
+    }, {
+        # id parameter is not as first paramater
+        'url': 'https://aitube.kz/video?season=1&id=9291d29b-c038-49a1-ad42-3da2051d353c&playlistId=d55b1f5f-ef2a-4f23-b646-2a86275b86b7',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        nextjs_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['videoInfo']
+        json_ld_data = self._search_json_ld(webpage, video_id)
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            f'https://api-http.aitube.kz/kz.aitudala.aitube.staticaccess/video/{video_id}/video', video_id)
+
+        return merge_dicts({
+            'id': video_id,
+            'title': nextjs_data.get('title') or self._html_search_meta(['name', 'og:title'], webpage),
+            'description': nextjs_data.get('description'),
+            'formats': formats,
+            'subtitles': subtitles,
+            'view_count': (nextjs_data.get('viewCount')
+                           or int_or_none(self._html_search_meta('ya:ovs:views_total', webpage))),
+            'like_count': nextjs_data.get('likeCount'),
+            'channel': nextjs_data.get('channelTitle'),
+            'channel_id': nextjs_data.get('channelId'),
+            'thumbnail': nextjs_data.get('coverUrl'),
+            'comment_count': nextjs_data.get('commentCount'),
+            'channel_follower_count': int_or_none(nextjs_data.get('channelSubscriberCount')),
+        }, json_ld_data)

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

@@ -0,0 +1,50 @@
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    float_or_none,
+    try_get,
+)
+
+
+class AliExpressLiveIE(InfoExtractor):
+    _VALID_URL = r'https?://live\.aliexpress\.com/live/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://live.aliexpress.com/live/2800002704436634',
+        'md5': 'e729e25d47c5e557f2630eaf99b740a5',
+        'info_dict': {
+            'id': '2800002704436634',
+            'ext': 'mp4',
+            'title': 'CASIMA7.22',
+            'thumbnail': r're:https?://.*\.jpg',
+            'uploader': 'CASIMA Official Store',
+            'timestamp': 1500717600,
+            'upload_date': '20170722',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        data = self._parse_json(
+            self._search_regex(
+                r'(?s)runParams\s*=\s*({.+?})\s*;?\s*var',
+                webpage, 'runParams'),
+            video_id)
+
+        title = data['title']
+
+        formats = self._extract_m3u8_formats(
+            data['replyStreamUrl'], video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': data.get('coverUrl'),
+            'uploader': try_get(
+                data, lambda x: x['followBar']['name'], compat_str),
+            'timestamp': float_or_none(data.get('startTimeLong'), scale=1000),
+            'formats': formats,
+        }

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

@@ -0,0 +1,83 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    try_get,
+)
+
+
+class AlJazeeraIE(InfoExtractor):
+    _VALID_URL = r'https?://(?P<base>\w+\.aljazeera\.\w+)/(?P<type>programs?/[^/]+|(?:feature|video|new)s)?/\d{4}/\d{1,2}/\d{1,2}/(?P<id>[^/?&#]+)'
+
+    _TESTS = [{
+        'url': 'https://balkans.aljazeera.net/videos/2021/11/6/pojedini-domovi-u-sarajevu-jos-pod-vodom-mjestanima-se-dostavlja-hrana',
+        'info_dict': {
+            'id': '6280641530001',
+            'ext': 'mp4',
+            'title': 'Pojedini domovi u Sarajevu još pod vodom, mještanima se dostavlja hrana',
+            'timestamp': 1636219149,
+            'description': 'U sarajevskim naseljima Rajlovac i Reljevo stambeni objekti, ali i industrijska postrojenja i dalje su pod vodom.',
+            'upload_date': '20211106',
+        }
+    }, {
+        'url': 'https://balkans.aljazeera.net/videos/2021/11/6/djokovic-usao-u-finale-mastersa-u-parizu',
+        'info_dict': {
+            'id': '6280654936001',
+            'ext': 'mp4',
+            'title': 'Đoković ušao u finale Mastersa u Parizu',
+            'timestamp': 1636221686,
+            'description': 'Novak Đoković je u polufinalu Mastersa u Parizu nakon preokreta pobijedio Poljaka Huberta Hurkacza.',
+            'upload_date': '20211106',
+        },
+    }]
+    BRIGHTCOVE_URL_RE = r'https?://players.brightcove.net/(?P<account>\d+)/(?P<player_id>[a-zA-Z0-9]+)_(?P<embed>[^/]+)/index.html\?videoId=(?P<id>\d+)'
+
+    def _real_extract(self, url):
+        base, post_type, id = self._match_valid_url(url).groups()
+        wp = {
+            'balkans.aljazeera.net': 'ajb',
+            'chinese.aljazeera.net': 'chinese',
+            'mubasher.aljazeera.net': 'ajm',
+        }.get(base) or 'aje'
+        post_type = {
+            'features': 'post',
+            'program': 'episode',
+            'programs': 'episode',
+            'videos': 'video',
+            'news': 'news',
+        }[post_type.split('/')[0]]
+        video = self._download_json(
+            f'https://{base}/graphql', id, query={
+                'wp-site': wp,
+                'operationName': 'ArchipelagoSingleArticleQuery',
+                'variables': json.dumps({
+                    'name': id,
+                    'postType': post_type,
+                }),
+            }, headers={
+                'wp-site': wp,
+            })
+        video = try_get(video, lambda x: x['data']['article']['video']) or {}
+        video_id = video.get('id')
+        account = video.get('accountId') or '911432371001'
+        player_id = video.get('playerId') or 'csvTfAlKW'
+        embed = 'default'
+
+        if video_id is None:
+            webpage = self._download_webpage(url, id)
+
+            account, player_id, embed, video_id = self._search_regex(self.BRIGHTCOVE_URL_RE, webpage, 'video id',
+                                                                     group=(1, 2, 3, 4), default=(None, None, None, None))
+
+            if video_id is None:
+                return {
+                    '_type': 'url_transparent',
+                    'url': url,
+                    'ie_key': 'Generic'
+                }
+
+        return {
+            '_type': 'url_transparent',
+            'url': f'https://players.brightcove.net/{account}/{player_id}_{embed}/index.html?videoId={video_id}',
+            'ie_key': 'BrightcoveNew'
+        }

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

@@ -0,0 +1,125 @@
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    qualities,
+    remove_end,
+    strip_or_none,
+    try_get,
+    unified_timestamp,
+    url_basename,
+)
+
+
+class AllocineIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?:article|video|film)/(?:fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
+
+    _TESTS = [{
+        'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
+        'md5': '0c9fcf59a841f65635fa300ac43d8269',
+        'info_dict': {
+            'id': '19546517',
+            'display_id': '18635087',
+            'ext': 'mp4',
+            'title': 'Astérix - Le Domaine des Dieux Teaser VF',
+            'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
+            'thumbnail': r're:http://.*\.jpg',
+            'duration': 39,
+            'timestamp': 1404273600,
+            'upload_date': '20140702',
+            'view_count': int,
+        },
+    }, {
+        'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
+        'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
+        'info_dict': {
+            'id': '19540403',
+            'display_id': '19540403',
+            'ext': 'mp4',
+            'title': 'Planes 2 Bande-annonce VF',
+            'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
+            'thumbnail': r're:http://.*\.jpg',
+            'duration': 69,
+            'timestamp': 1385659800,
+            'upload_date': '20131128',
+            'view_count': int,
+        },
+    }, {
+        'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
+        'md5': '101250fb127ef9ca3d73186ff22a47ce',
+        'info_dict': {
+            'id': '19544709',
+            'display_id': '19544709',
+            'ext': 'mp4',
+            'title': 'Dragons 2 - Bande annonce finale VF',
+            'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a',
+            'thumbnail': r're:http://.*\.jpg',
+            'duration': 144,
+            'timestamp': 1397589900,
+            'upload_date': '20140415',
+            'view_count': int,
+        },
+    }, {
+        'url': 'http://www.allocine.fr/video/video-19550147/',
+        'md5': '3566c0668c0235e2d224fd8edb389f67',
+        'info_dict': {
+            'id': '19550147',
+            'ext': 'mp4',
+            'title': 'Faux Raccord N°123 - Les gaffes de Cliffhanger',
+            'description': 'md5:bc734b83ffa2d8a12188d9eb48bb6354',
+            'thumbnail': r're:http://.*\.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        formats = []
+        quality = qualities(['ld', 'md', 'hd'])
+
+        model = self._html_search_regex(
+            r'data-model="([^"]+)"', webpage, 'data model', default=None)
+        if model:
+            model_data = self._parse_json(model, display_id)
+            video = model_data['videos'][0]
+            title = video['title']
+            for video_url in video['sources'].values():
+                video_id, format_id = url_basename(video_url).split('_')[:2]
+                formats.append({
+                    'format_id': format_id,
+                    'quality': quality(format_id),
+                    'url': video_url,
+                })
+            duration = int_or_none(video.get('duration'))
+            view_count = int_or_none(video.get('view_count'))
+            timestamp = unified_timestamp(try_get(
+                video, lambda x: x['added_at']['date'], compat_str))
+        else:
+            video_id = display_id
+            media_data = self._download_json(
+                'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
+            title = remove_end(strip_or_none(self._html_extract_title(webpage), ' - AlloCiné'))
+            for key, value in media_data['video'].items():
+                if not key.endswith('Path'):
+                    continue
+                format_id = key[:-len('Path')]
+                formats.append({
+                    'format_id': format_id,
+                    'quality': quality(format_id),
+                    'url': value,
+                })
+            duration, view_count, timestamp = [None] * 3
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'duration': duration,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'formats': formats,
+        }