@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/yle_areena.py

@@ -0,0 +1,134 @@
+from .common import InfoExtractor
+from .kaltura import KalturaIE
+from ..utils import (
+    int_or_none,
+    smuggle_url,
+    traverse_obj,
+    unified_strdate,
+    url_or_none,
+)
+
+
+class YleAreenaIE(InfoExtractor):
+    _VALID_URL = r'https?://areena\.yle\.fi/(?P<id>[\d-]+)'
+    _TESTS = [
+        {
+            'url': 'https://areena.yle.fi/1-4371942',
+            'md5': '932edda0ecf5dfd6423804182d32f8ac',
+            'info_dict': {
+                'id': '0_a3tjk92c',
+                'ext': 'mp4',
+                'title': 'Pouchit',
+                'description': 'md5:d487309c3abbe5650265bbd1742d2f82',
+                'series': 'Modernit miehet',
+                'season': 'Season 1',
+                'season_number': 1,
+                'episode': 'Episode 2',
+                'episode_number': 2,
+                'thumbnail': 'http://cfvod.kaltura.com/p/1955031/sp/195503100/thumbnail/entry_id/0_a3tjk92c/version/100061',
+                'uploader_id': 'ovp@yle.fi',
+                'duration': 1435,
+                'view_count': int,
+                'upload_date': '20181204',
+                'release_date': '20190106',
+                'timestamp': 1543916210,
+                'subtitles': {'fin': [{'url': r're:^https?://', 'ext': 'srt'}]},
+                'age_limit': 7,
+                'webpage_url': 'https://areena.yle.fi/1-4371942'
+            }
+        },
+        {
+            'url': 'https://areena.yle.fi/1-2158940',
+            'md5': 'cecb603661004e36af8c5188b5212b12',
+            'info_dict': {
+                'id': '1_l38iz9ur',
+                'ext': 'mp4',
+                'title': 'Albi haluaa vessan',
+                'description': 'md5:15236d810c837bed861fae0e88663c33',
+                'series': 'Albi Lumiukko',
+                'thumbnail': 'http://cfvod.kaltura.com/p/1955031/sp/195503100/thumbnail/entry_id/1_l38iz9ur/version/100021',
+                'uploader_id': 'ovp@yle.fi',
+                'duration': 319,
+                'view_count': int,
+                'upload_date': '20211202',
+                'release_date': '20211215',
+                'timestamp': 1638448202,
+                'subtitles': {},
+                'age_limit': 0,
+                'webpage_url': 'https://areena.yle.fi/1-2158940'
+            }
+        },
+        {
+            'url': 'https://areena.yle.fi/1-64829589',
+            'info_dict': {
+                'id': '1-64829589',
+                'ext': 'mp4',
+                'title': 'HKO & Mälkki & Tanner',
+                'description': 'md5:b4f1b1af2c6569b33f75179a86eea156',
+                'series': 'Helsingin kaupunginorkesterin konsertteja',
+                'thumbnail': r're:^https?://.+\.jpg$',
+                'release_date': '20230120',
+            },
+            'params': {
+                'skip_download': 'm3u8',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        info = self._search_json_ld(self._download_webpage(url, video_id), video_id, default={})
+        video_data = self._download_json(
+            f'https://player.api.yle.fi/v1/preview/{video_id}.json?app_id=player_static_prod&app_key=8930d72170e48303cf5f3867780d549b',
+            video_id, headers={
+                'origin': 'https://areena.yle.fi',
+                'referer': 'https://areena.yle.fi/',
+                'content-type': 'application/json'
+            })
+
+        # Example title: 'K1, J2: Pouchit | Modernit miehet'
+        series, season_number, episode_number, episode = self._search_regex(
+            r'K(?P<season_no>[\d]+),\s*J(?P<episode_no>[\d]+):?\s*\b(?P<episode>[^|]+)\s*|\s*(?P<series>.+)',
+            info.get('title') or '', 'episode metadata', group=('season_no', 'episode_no', 'episode', 'series'),
+            default=(None, None, None, None))
+        description = traverse_obj(video_data, ('data', 'ongoing_ondemand', 'description', 'fin'), expected_type=str)
+
+        subtitles = {}
+        for sub in traverse_obj(video_data, ('data', 'ongoing_ondemand', 'subtitles', ...)):
+            if url_or_none(sub.get('uri')):
+                subtitles.setdefault(sub.get('language') or 'und', []).append({
+                    'url': sub['uri'],
+                    'ext': 'srt',
+                    'name': sub.get('kind'),
+                })
+
+        kaltura_id = traverse_obj(video_data, ('data', 'ongoing_ondemand', 'kaltura', 'id'), expected_type=str)
+        if kaltura_id:
+            info_dict = {
+                '_type': 'url_transparent',
+                'url': smuggle_url(f'kaltura:1955031:{kaltura_id}', {'source_url': url}),
+                'ie_key': KalturaIE.ie_key(),
+            }
+        else:
+            info_dict = {
+                'id': video_id,
+                'formats': self._extract_m3u8_formats(
+                    video_data['data']['ongoing_ondemand']['manifest_url'], video_id, 'mp4', m3u8_id='hls'),
+            }
+
+        return {
+            **info_dict,
+            'title': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'title', 'fin'), expected_type=str)
+                      or episode or info.get('title')),
+            'description': description,
+            'series': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'series', 'title', 'fin'), expected_type=str)
+                       or series),
+            'season_number': (int_or_none(self._search_regex(r'Kausi (\d+)', description, 'season number', default=None))
+                              or int_or_none(season_number)),
+            'episode_number': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'episode_number'), expected_type=int_or_none)
+                               or int_or_none(episode_number)),
+            'thumbnails': traverse_obj(info, ('thumbnails', ..., {'url': 'url'})),
+            'age_limit': traverse_obj(video_data, ('data', 'ongoing_ondemand', 'content_rating', 'age_restriction'), expected_type=int_or_none),
+            'subtitles': subtitles,
+            'release_date': unified_strdate(traverse_obj(video_data, ('data', 'ongoing_ondemand', 'start_time'), expected_type=str)),
+        }

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

@@ -0,0 +1,90 @@
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    parse_duration,
+    url_or_none,
+)
+
+
+class YouJizzIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/(?:[^/#?]*-(?P<id>\d+)\.html|embed/(?P<embed_id>\d+))'
+    _TESTS = [{
+        'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
+        'md5': 'b1e1dfaa8bb9537d8b84eeda9cf4acf4',
+        'info_dict': {
+            'id': '2189178',
+            'ext': 'mp4',
+            'title': 'Zeichentrick 1',
+            'age_limit': 18,
+            'duration': 2874,
+        }
+    }, {
+        'url': 'http://www.youjizz.com/videos/-2189178.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.youjizz.com/videos/embed/31991001',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        video_id = mobj.group('id') or mobj.group('embed_id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_extract_title(webpage)
+
+        formats = []
+
+        encodings = self._parse_json(
+            self._search_regex(
+                r'[Ee]ncodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings',
+                default='[]'),
+            video_id, fatal=False)
+        for encoding in encodings:
+            if not isinstance(encoding, dict):
+                continue
+            format_url = url_or_none(encoding.get('filename'))
+            if not format_url:
+                continue
+            if determine_ext(format_url) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            else:
+                format_id = encoding.get('name') or encoding.get('quality')
+                height = int_or_none(self._search_regex(
+                    r'^(\d+)[pP]', format_id, 'height', default=None))
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_id,
+                    'height': height,
+                })
+
+        if formats:
+            info_dict = {
+                'formats': formats,
+            }
+        else:
+            # YouJizz's HTML5 player has invalid HTML
+            webpage = webpage.replace('"controls', '" controls')
+            info_dict = self._parse_html5_media_entries(
+                url, webpage, video_id)[0]
+
+        duration = parse_duration(self._search_regex(
+            r'<strong>Runtime:</strong>([^<]+)', webpage, 'duration',
+            default=None))
+        uploader = self._search_regex(
+            r'<strong>Uploaded By:.*?<a[^>]*>([^<]+)', webpage, 'uploader',
+            default=None)
+
+        info_dict.update({
+            'id': video_id,
+            'title': title,
+            'age_limit': self._rta_search(webpage),
+            'duration': duration,
+            'uploader': uploader,
+        })
+
+        return info_dict

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

@@ -0,0 +1,290 @@
+import random
+import re
+import string
+import time
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    get_element_by_class,
+    js_to_json,
+    str_or_none,
+    strip_jsonp,
+)
+
+
+class YoukuIE(InfoExtractor):
+    IE_NAME = 'youku'
+    IE_DESC = '优酷'
+    _VALID_URL = r'''(?x)
+        (?:
+            https?://(
+                (?:v|play(?:er)?)\.(?:youku|tudou)\.com/(?:v_show/id_|player\.php/sid/)|
+                video\.tudou\.com/v/)|
+            youku:)
+        (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
+    '''
+
+    _TESTS = [{
+        'url': 'http://player.youku.com/player.php/sid/XNDgyMDQ2NTQw/v.swf',
+        'only_matching': True,
+    }, {
+        'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html',
+        'note': 'Video protected with password',
+        'info_dict': {
+            'id': 'XNjA1NzA2Njgw',
+            'ext': 'mp4',
+            'title': '邢義田复旦讲座之想象中的胡人—从“左衽孔子”说起',
+            'duration': 7264.5,
+            'thumbnail': r're:^https?://.*',
+            'uploader': 'FoxJin1006',
+            'uploader_id': '322014285',
+            'uploader_url': 'http://i.youku.com/u/UMTI4ODA1NzE0MA==',
+            'tags': list,
+        },
+        'params': {
+            'videopassword': '100600',
+        },
+        'skip': '404',
+    }, {
+        # /play/get.json contains streams with "channel_type":"tail"
+        'url': 'http://v.youku.com/v_show/id_XOTUxMzg4NDMy.html',
+        'info_dict': {
+            'id': 'XOTUxMzg4NDMy',
+            'ext': 'mp4',
+            'title': '我的世界☆明月庄主☆车震猎杀☆杀人艺术Minecraft',
+            'duration': 702.08,
+            'thumbnail': r're:^https?://.*',
+            'uploader': '明月庄主moon',
+            'uploader_id': '38465621',
+            'uploader_url': 'https://www.youku.com/profile/index/?uid=UMTUzODYyNDg0',
+            'tags': list,
+        },
+    }, {
+        'url': 'https://v.youku.com/v_show/id_XNTA2NTA0MjA1Mg==.html',
+        'info_dict': {
+            'id': 'XNTA2NTA0MjA1Mg',
+            'ext': 'mp4',
+            'title': 'Minecraft我的世界：建造超大巨型航空飞机，菜鸟vs高手vs黑客',
+            'duration': 542.13,
+            'thumbnail': r're:^https?://.*',
+            'uploader': '波哥游戏解说',
+            'uploader_id': '156688084',
+            'uploader_url': 'https://www.youku.com/profile/index/?uid=UNjI2NzUyMzM2',
+            'tags': list,
+        },
+    }, {
+        'url': 'https://v.youku.com/v_show/id_XNTE1MzczOTg4MA==.html',
+        'info_dict': {
+            'id': 'XNTE1MzczOTg4MA',
+            'ext': 'mp4',
+            'title': '国产超A特工片',
+            'duration': 362.97,
+            'thumbnail': r're:^https?://.*',
+            'uploader': '陈晓娟说历史',
+            'uploader_id': '1640913339',
+            'uploader_url': 'https://www.youku.com/profile/index/?uid=UNjU2MzY1MzM1Ng==',
+            'tags': list,
+        },
+    }, {
+        'url': 'https://play.tudou.com/v_show/id_XNjAxNjI2OTU3Ng==.html?',
+        'info_dict': {
+            'id': 'XNjAxNjI2OTU3Ng',
+            'ext': 'mp4',
+            'title': '阿斯塔意识到哈里杀了人，自己被骗了',
+            'thumbnail': 'https://m.ykimg.com/0541010164F732752794D4D7B70331D1',
+            'uploader_id': '88758207',
+            'tags': [],
+            'uploader_url': 'https://www.youku.com/profile/index/?uid=UMzU1MDMyODI4',
+            'uploader': '英美剧场',
+            'duration': 72.91,
+        },
+    }]
+
+    @staticmethod
+    def get_ysuid():
+        return '%d%s' % (int(time.time()), ''.join(
+            random.choices(string.ascii_letters, k=3)))
+
+    def get_format_name(self, fm):
+        _dict = {
+            '3gp': 'h6',
+            '3gphd': 'h5',
+            'flv': 'h4',
+            'flvhd': 'h4',
+            'mp4': 'h3',
+            'mp4hd': 'h3',
+            'mp4hd2': 'h4',
+            'mp4hd3': 'h4',
+            'hd2': 'h2',
+            'hd3': 'h1',
+        }
+        return _dict.get(fm)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        self._set_cookie('youku.com', '__ysuid', self.get_ysuid())
+        self._set_cookie('youku.com', 'xreferrer', 'http://www.youku.com')
+
+        _, urlh = self._download_webpage_handle(
+            'https://log.mmstat.com/eg.js', video_id, 'Retrieving cna info')
+        # The etag header is '"foobar"'; let's remove the double quotes
+        cna = urlh.headers['etag'][1:-1]
+
+        # request basic data
+        basic_data_params = {
+            'vid': video_id,
+            'ccode': '0524',
+            'client_ip': '192.168.1.1',
+            'utid': cna,
+            'client_ts': time.time() / 1000,
+        }
+
+        video_password = self.get_param('videopassword')
+        if video_password:
+            basic_data_params['password'] = video_password
+
+        headers = {
+            'Referer': url,
+        }
+        headers.update(self.geo_verification_headers())
+        data = self._download_json(
+            'https://ups.youku.com/ups/get.json', video_id,
+            'Downloading JSON metadata',
+            query=basic_data_params, headers=headers)['data']
+
+        error = data.get('error')
+        if error:
+            error_note = error.get('note')
+            if error_note is not None and '因版权原因无法观看此视频' in error_note:
+                raise ExtractorError(
+                    'Youku said: Sorry, this video is available in China only', expected=True)
+            elif error_note and '该视频被设为私密' in error_note:
+                raise ExtractorError(
+                    'Youku said: Sorry, this video is private', expected=True)
+            else:
+                msg = 'Youku server reported error %i' % error.get('code')
+                if error_note is not None:
+                    msg += ': ' + clean_html(error_note)
+                raise ExtractorError(msg)
+
+        # get video title
+        video_data = data['video']
+        title = video_data['title']
+
+        formats = [{
+            'url': stream['m3u8_url'],
+            'format_id': self.get_format_name(stream.get('stream_type')),
+            'ext': 'mp4',
+            'protocol': 'm3u8_native',
+            'filesize': int(stream.get('size')),
+            'width': stream.get('width'),
+            'height': stream.get('height'),
+        } for stream in data['stream'] if stream.get('channel_type') != 'tail']
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'duration': video_data.get('seconds'),
+            'thumbnail': video_data.get('logo'),
+            'uploader': video_data.get('username'),
+            'uploader_id': str_or_none(video_data.get('userid')),
+            'uploader_url': data.get('uploader', {}).get('homepage'),
+            'tags': video_data.get('tags'),
+        }
+
+
+class YoukuShowIE(InfoExtractor):
+    _VALID_URL = r'https?://list\.youku\.com/show/id_(?P<id>[0-9a-z]+)\.html'
+    IE_NAME = 'youku:show'
+
+    _TESTS = [{
+        'url': 'http://list.youku.com/show/id_zc7c670be07ff11e48b3f.html',
+        'info_dict': {
+            'id': 'zc7c670be07ff11e48b3f',
+            'title': '花千骨 DVD版',
+            'description': 'md5:a1ae6f5618571bbeb5c9821f9c81b558',
+        },
+        'playlist_count': 50,
+    }, {
+        # Episode number not starting from 1
+        'url': 'http://list.youku.com/show/id_zefbfbd70efbfbd780bef.html',
+        'info_dict': {
+            'id': 'zefbfbd70efbfbd780bef',
+            'title': '超级飞侠3',
+            'description': 'md5:275715156abebe5ccc2a1992e9d56b98',
+        },
+        'playlist_count': 24,
+    }, {
+        # Ongoing playlist. The initial page is the last one
+        'url': 'http://list.youku.com/show/id_za7c275ecd7b411e1a19e.html',
+        'only_matching': True,
+    }, {
+        #  No data-id value.
+        'url': 'http://list.youku.com/show/id_zefbfbd61237fefbfbdef.html',
+        'only_matching': True,
+    }, {
+        #  Wrong number of reload_id.
+        'url': 'http://list.youku.com/show/id_z20eb4acaf5c211e3b2ad.html',
+        'only_matching': True,
+    }]
+
+    def _extract_entries(self, playlist_data_url, show_id, note, query):
+        query['callback'] = 'cb'
+        playlist_data = self._download_json(
+            playlist_data_url, show_id, query=query, note=note,
+            transform_source=lambda s: js_to_json(strip_jsonp(s))).get('html')
+        if playlist_data is None:
+            return [None, None]
+        drama_list = (get_element_by_class('p-drama-grid', playlist_data)
+                      or get_element_by_class('p-drama-half-row', playlist_data))
+        if drama_list is None:
+            raise ExtractorError('No episodes found')
+        video_urls = re.findall(r'<a[^>]+href="([^"]+)"', drama_list)
+        return playlist_data, [
+            self.url_result(self._proto_relative_url(video_url, 'http:'), YoukuIE.ie_key())
+            for video_url in video_urls]
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        webpage = self._download_webpage(url, show_id)
+
+        entries = []
+        page_config = self._parse_json(self._search_regex(
+            r'var\s+PageConfig\s*=\s*({.+});', webpage, 'page config'),
+            show_id, transform_source=js_to_json)
+        first_page, initial_entries = self._extract_entries(
+            'http://list.youku.com/show/module', show_id,
+            note='Downloading initial playlist data page',
+            query={
+                'id': page_config['showid'],
+                'tab': 'showInfo',
+            })
+        first_page_reload_id = self._html_search_regex(
+            r'<div[^>]+id="(reload_\d+)', first_page, 'first page reload id')
+        # The first reload_id has the same items as first_page
+        reload_ids = re.findall('<li[^>]+data-id="([^"]+)">', first_page)
+        entries.extend(initial_entries)
+        for idx, reload_id in enumerate(reload_ids):
+            if reload_id == first_page_reload_id:
+                continue
+            _, new_entries = self._extract_entries(
+                'http://list.youku.com/show/episode', show_id,
+                note='Downloading playlist data page %d' % (idx + 1),
+                query={
+                    'id': page_config['showid'],
+                    'stage': reload_id,
+                })
+            if new_entries is not None:
+                entries.extend(new_entries)
+        desc = self._html_search_meta('description', webpage, fatal=False)
+        playlist_title = desc.split(',')[0] if desc else None
+        detail_li = get_element_by_class('p-intro', webpage)
+        playlist_description = get_element_by_class(
+            'intro-more', detail_li) if detail_li else None
+
+        return self.playlist_result(
+            entries, show_id, playlist_title, playlist_description)