@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/zoom.py

@@ -0,0 +1,164 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    js_to_json,
+    parse_filesize,
+    parse_resolution,
+    str_or_none,
+    traverse_obj,
+    url_basename,
+    urlencode_postdata,
+    urljoin,
+)
+
+
+class ZoomIE(InfoExtractor):
+    IE_NAME = 'zoom'
+    _VALID_URL = r'(?P<base_url>https?://(?:[^.]+\.)?zoom\.us/)rec(?:ording)?/(?P<type>play|share)/(?P<id>[\w.-]+)'
+    _TESTS = [{
+        'url': 'https://economist.zoom.us/rec/play/dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
+        'md5': 'ab445e8c911fddc4f9adc842c2c5d434',
+        'info_dict': {
+            'id': 'dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
+            'ext': 'mp4',
+            'title': 'China\'s "two sessions" and the new five-year plan',
+        },
+        'skip': 'Recording requires email authentication to access',
+    }, {
+        # play URL
+        'url': 'https://ffgolf.zoom.us/rec/play/qhEhXbrxq1Zoucx8CMtHzq1Z_2YZRPVCqWK_K-2FkEGRsSLDeOX8Tu4P6jtjZcRry8QhIbvKZdtr4UNo.QcPn2debFskI9whJ',
+        'md5': '2c4b1c4e5213ebf9db293e88d9385bee',
+        'info_dict': {
+            'id': 'qhEhXbrxq1Zoucx8CMtHzq1Z_2YZRPVCqWK_K-2FkEGRsSLDeOX8Tu4P6jtjZcRry8QhIbvKZdtr4UNo.QcPn2debFskI9whJ',
+            'ext': 'mp4',
+            'title': 'Prépa AF2023 - Séance 5 du 11 avril - R20/VM/GO',
+        },
+    }, {
+        # share URL
+        'url': 'https://us02web.zoom.us/rec/share/hkUk5Zxcga0nkyNGhVCRfzkA2gX_mzgS3LpTxEEWJz9Y_QpIQ4mZFOUx7KZRZDQA.9LGQBdqmDAYgiZ_8',
+        'md5': '90fdc7cfcaee5d52d1c817fc03c43c9b',
+        'info_dict': {
+            'id': 'hkUk5Zxcga0nkyNGhVCRfzkA2gX_mzgS3LpTxEEWJz9Y_QpIQ4mZFOUx7KZRZDQA.9LGQBdqmDAYgiZ_8',
+            'ext': 'mp4',
+            'title': 'Timea Andrea Lelik\'s Personal Meeting Room',
+        },
+        'skip': 'This recording has expired',
+    }, {
+        # view_with_share URL
+        'url': 'https://cityofdetroit.zoom.us/rec/share/VjE-5kW3xmgbEYqR5KzRgZ1OFZvtMtiXk5HyRJo5kK4m5PYE6RF4rF_oiiO_9qaM.UTAg1MI7JSnF3ZjX',
+        'md5': 'bdc7867a5934c151957fb81321b3c024',
+        'info_dict': {
+            'id': 'VjE-5kW3xmgbEYqR5KzRgZ1OFZvtMtiXk5HyRJo5kK4m5PYE6RF4rF_oiiO_9qaM.UTAg1MI7JSnF3ZjX',
+            'ext': 'mp4',
+            'title': 'February 2022 Detroit Revenue Estimating Conference',
+            'duration': 7299,
+            'formats': 'mincount:3',
+        },
+    }]
+
+    def _get_page_data(self, webpage, video_id):
+        return self._search_json(
+            r'window\.__data__\s*=', webpage, 'data', video_id, transform_source=js_to_json)
+
+    def _get_real_webpage(self, url, base_url, video_id, url_type):
+        webpage = self._download_webpage(url, video_id, note=f'Downloading {url_type} webpage')
+        try:
+            form = self._form_hidden_inputs('password_form', webpage)
+        except ExtractorError:
+            return webpage
+
+        password = self.get_param('videopassword')
+        if not password:
+            raise ExtractorError(
+                'This video is protected by a passcode, use the --video-password option', expected=True)
+        is_meeting = form.get('useWhichPasswd') == 'meeting'
+        validation = self._download_json(
+            base_url + 'rec/validate%s_passwd' % ('_meet' if is_meeting else ''),
+            video_id, 'Validating passcode', 'Wrong passcode', data=urlencode_postdata({
+                'id': form[('meet' if is_meeting else 'file') + 'Id'],
+                'passwd': password,
+                'action': form.get('action'),
+            }))
+        if not validation.get('status'):
+            raise ExtractorError(validation['errorMessage'], expected=True)
+        return self._download_webpage(url, video_id, note=f'Re-downloading {url_type} webpage')
+
+    def _real_extract(self, url):
+        base_url, url_type, video_id = self._match_valid_url(url).group('base_url', 'type', 'id')
+        query = {}
+
+        if url_type == 'share':
+            webpage = self._get_real_webpage(url, base_url, video_id, 'share')
+            meeting_id = self._get_page_data(webpage, video_id)['meetingId']
+            redirect_path = self._download_json(
+                f'{base_url}nws/recording/1.0/play/share-info/{meeting_id}',
+                video_id, note='Downloading share info JSON')['result']['redirectUrl']
+            url = urljoin(base_url, redirect_path)
+            query['continueMode'] = 'true'
+
+        webpage = self._get_real_webpage(url, base_url, video_id, 'play')
+        file_id = self._get_page_data(webpage, video_id)['fileId']
+        if not file_id:
+            # When things go wrong, file_id can be empty string
+            raise ExtractorError('Unable to extract file ID')
+
+        data = self._download_json(
+            f'{base_url}nws/recording/1.0/play/info/{file_id}', video_id, query=query,
+            note='Downloading play info JSON')['result']
+
+        subtitles = {}
+        for _type in ('transcript', 'cc', 'chapter'):
+            if data.get('%sUrl' % _type):
+                subtitles[_type] = [{
+                    'url': urljoin(base_url, data['%sUrl' % _type]),
+                    'ext': 'vtt',
+                }]
+
+        formats = []
+
+        if data.get('viewMp4Url'):
+            formats.append({
+                'format_note': 'Camera stream',
+                'url': data['viewMp4Url'],
+                'width': int_or_none(traverse_obj(data, ('viewResolvtions', 0))),
+                'height': int_or_none(traverse_obj(data, ('viewResolvtions', 1))),
+                'format_id': 'view',
+                'ext': 'mp4',
+                'filesize_approx': parse_filesize(str_or_none(traverse_obj(data, ('recording', 'fileSizeInMB')))),
+                'preference': 0
+            })
+
+        if data.get('shareMp4Url'):
+            formats.append({
+                'format_note': 'Screen share stream',
+                'url': data['shareMp4Url'],
+                'width': int_or_none(traverse_obj(data, ('shareResolvtions', 0))),
+                'height': int_or_none(traverse_obj(data, ('shareResolvtions', 1))),
+                'format_id': 'share',
+                'ext': 'mp4',
+                'preference': -1
+            })
+
+        view_with_share_url = data.get('viewMp4WithshareUrl')
+        if view_with_share_url:
+            formats.append({
+                **parse_resolution(self._search_regex(
+                    r'_(\d+x\d+)\.mp4', url_basename(view_with_share_url), 'resolution', default=None)),
+                'format_note': 'Screen share with camera',
+                'url': view_with_share_url,
+                'format_id': 'view_with_share',
+                'ext': 'mp4',
+                'preference': 1
+            })
+
+        return {
+            'id': video_id,
+            'title': str_or_none(traverse_obj(data, ('meet', 'topic'))),
+            'duration': int_or_none(data.get('duration')),
+            'subtitles': subtitles,
+            'formats': formats,
+            'http_headers': {
+                'Referer': base_url,
+            },
+        }

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

@@ -0,0 +1,135 @@
+import re
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    dict_get,
+    ExtractorError,
+    int_or_none,
+    js_to_json,
+    parse_iso8601,
+)
+
+
+class ZypeIE(InfoExtractor):
+    _ID_RE = r'[\da-fA-F]+'
+    _COMMON_RE = r'//player\.zype\.com/embed/%s\.(?:js|json|html)\?.*?(?:access_token|(?:ap[ip]|player)_key)='
+    _VALID_URL = r'https?:%s[^&]+' % (_COMMON_RE % ('(?P<id>%s)' % _ID_RE))
+    _EMBED_REGEX = [fr'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?{_COMMON_RE % _ID_RE}.+?)\1']
+    _TEST = {
+        'url': 'https://player.zype.com/embed/5b400b834b32992a310622b9.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ&autoplay=false&controls=true&da=false',
+        'md5': 'eaee31d474c76a955bdaba02a505c595',
+        'info_dict': {
+            'id': '5b400b834b32992a310622b9',
+            'ext': 'mp4',
+            'title': 'Smoky Barbecue Favorites',
+            'thumbnail': r're:^https?://.*\.jpe?g',
+            'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
+            'timestamp': 1504915200,
+            'upload_date': '20170909',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        try:
+            response = self._download_json(re.sub(
+                r'\.(?:js|html)\?', '.json?', url), video_id)['response']
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status in (400, 401, 403):
+                raise ExtractorError(self._parse_json(
+                    e.cause.response.read().decode(), video_id)['message'], expected=True)
+            raise
+
+        body = response['body']
+        video = response['video']
+        title = video['title']
+
+        subtitles = {}
+
+        if isinstance(body, dict):
+            formats = []
+            for output in body.get('outputs', []):
+                output_url = output.get('url')
+                if not output_url:
+                    continue
+                name = output.get('name')
+                if name == 'm3u8':
+                    formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+                        output_url, video_id, 'mp4',
+                        'm3u8_native', m3u8_id='hls', fatal=False)
+                else:
+                    f = {
+                        'format_id': name,
+                        'tbr': int_or_none(output.get('bitrate')),
+                        'url': output_url,
+                    }
+                    if name in ('m4a', 'mp3'):
+                        f['vcodec'] = 'none'
+                    else:
+                        f.update({
+                            'height': int_or_none(output.get('height')),
+                            'width': int_or_none(output.get('width')),
+                        })
+                    formats.append(f)
+            text_tracks = body.get('subtitles') or []
+        else:
+            m3u8_url = self._search_regex(
+                r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1',
+                body, 'm3u8 url', group='url', default=None)
+            if not m3u8_url:
+                source = self._search_regex(
+                    r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', body, 'source')
+
+                def get_attr(key):
+                    return self._search_regex(
+                        r'\b%s\s*:\s*([\'"])(?P<val>(?:(?!\1).)+)\1' % key,
+                        source, key, group='val')
+
+                if get_attr('integration') == 'verizon-media':
+                    m3u8_url = 'https://content.uplynk.com/%s.m3u8' % get_attr('id')
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+                m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
+            text_tracks = self._search_regex(
+                r'textTracks\s*:\s*(\[[^]]+\])',
+                body, 'text tracks', default=None)
+            if text_tracks:
+                text_tracks = self._parse_json(
+                    text_tracks, video_id, js_to_json, False)
+
+        if text_tracks:
+            for text_track in text_tracks:
+                tt_url = dict_get(text_track, ('file', 'src'))
+                if not tt_url:
+                    continue
+                subtitles.setdefault(text_track.get('label') or 'English', []).append({
+                    'url': tt_url,
+                })
+
+        thumbnails = []
+        for thumbnail in video.get('thumbnails', []):
+            thumbnail_url = thumbnail.get('url')
+            if not thumbnail_url:
+                continue
+            thumbnails.append({
+                'url': thumbnail_url,
+                'width': int_or_none(thumbnail.get('width')),
+                'height': int_or_none(thumbnail.get('height')),
+            })
+
+        return {
+            'id': video_id,
+            'display_id': video.get('friendly_title'),
+            'title': title,
+            'thumbnails': thumbnails,
+            'description': dict_get(video, ('description', 'ott_description', 'short_description')),
+            'timestamp': parse_iso8601(video.get('published_at')),
+            'duration': int_or_none(video.get('duration')),
+            'view_count': int_or_none(video.get('request_count')),
+            'average_rating': int_or_none(video.get('rating')),
+            'season_number': int_or_none(video.get('season')),
+            'episode_number': int_or_none(video.get('episode')),
+            'formats': formats,
+            'subtitles': subtitles,
+        }