@tushar-br/desktop 1.0.283 → 1.0.284

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

@@ -1,167 +0,0 @@
-import math
-
-from .common import InfoExtractor
-from ..utils import InAdvancePagedList, str_or_none, traverse_obj, try_call
-
-
-class XimalayaBaseIE(InfoExtractor):
-    _GEO_COUNTRIES = ['CN']
-
-
-class XimalayaIE(XimalayaBaseIE):
-    IE_NAME = 'ximalaya'
-    IE_DESC = '喜马拉雅FM'
-    _VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(:?(?P<uid>\d+)/)?sound/(?P<id>[0-9]+)'
-    _TESTS = [
-        {
-            'url': 'http://www.ximalaya.com/sound/47740352/',
-            'info_dict': {
-                'id': '47740352',
-                'ext': 'm4a',
-                'uploader': '小彬彬爱听书',
-                'uploader_id': '61425525',
-                'uploader_url': 'http://www.ximalaya.com/zhubo/61425525/',
-                'title': '261.唐诗三百首.卷八.送孟浩然之广陵.李白',
-                'description': "contains:《送孟浩然之广陵》\n作者：李白\n故人西辞黄鹤楼，烟花三月下扬州。\n孤帆远影碧空尽，惟见长江天际流。",
-                'thumbnail': r're:^https?://.*\.jpg',
-                'thumbnails': [
-                    {
-                        'name': 'cover_url',
-                        'url': r're:^https?://.*\.jpg',
-                    },
-                    {
-                        'name': 'cover_url_142',
-                        'url': r're:^https?://.*\.jpg',
-                        'width': 180,
-                        'height': 180
-                    }
-                ],
-                'categories': ['其他'],
-                'duration': 93,
-                'view_count': int,
-                'like_count': int,
-            }
-        },
-        {
-            'url': 'http://m.ximalaya.com/61425525/sound/47740352/',
-            'info_dict': {
-                'id': '47740352',
-                'ext': 'm4a',
-                'uploader': '小彬彬爱听书',
-                'uploader_id': '61425525',
-                'uploader_url': 'http://www.ximalaya.com/zhubo/61425525/',
-                'title': '261.唐诗三百首.卷八.送孟浩然之广陵.李白',
-                'description': "contains:《送孟浩然之广陵》\n作者：李白\n故人西辞黄鹤楼，烟花三月下扬州。\n孤帆远影碧空尽，惟见长江天际流。",
-                'thumbnail': r're:^https?://.*\.jpg',
-                'thumbnails': [
-                    {
-                        'name': 'cover_url',
-                        'url': r're:^https?://.*\.jpg',
-                    },
-                    {
-                        'name': 'cover_url_142',
-                        'url': r're:^https?://.*\.jpg',
-                        'width': 180,
-                        'height': 180
-                    }
-                ],
-                'categories': ['人文'],
-                'duration': 93,
-                'view_count': int,
-                'like_count': int,
-            }
-        }
-    ]
-
-    def _real_extract(self, url):
-        scheme = 'https' if url.startswith('https') else 'http'
-
-        audio_id = self._match_id(url)
-        audio_info_file = '%s://m.ximalaya.com/tracks/%s.json' % (scheme, audio_id)
-        audio_info = self._download_json(audio_info_file, audio_id,
-                                         'Downloading info json %s' % audio_info_file,
-                                         'Unable to download info file')
-
-        formats = [{
-            'format_id': f'{bps}k',
-            'url': audio_info[k],
-            'abr': bps,
-            'vcodec': 'none'
-        } for bps, k in ((24, 'play_path_32'), (64, 'play_path_64')) if audio_info.get(k)]
-
-        thumbnails = []
-        for k in audio_info.keys():
-            # cover pics kyes like: cover_url', 'cover_url_142'
-            if k.startswith('cover_url'):
-                thumbnail = {'name': k, 'url': audio_info[k]}
-                if k == 'cover_url_142':
-                    thumbnail['width'] = 180
-                    thumbnail['height'] = 180
-                thumbnails.append(thumbnail)
-
-        audio_uploader_id = audio_info.get('uid')
-
-        audio_description = try_call(
-            lambda: audio_info['intro'].replace('\r\n\r\n\r\n ', '\n').replace('\r\n', '\n'))
-
-        return {
-            'id': audio_id,
-            'uploader': audio_info.get('nickname'),
-            'uploader_id': str_or_none(audio_uploader_id),
-            'uploader_url': f'{scheme}://www.ximalaya.com/zhubo/{audio_uploader_id}/' if audio_uploader_id else None,
-            'title': audio_info['title'],
-            'thumbnails': thumbnails,
-            'description': audio_description,
-            'categories': list(filter(None, [audio_info.get('category_name')])),
-            'duration': audio_info.get('duration'),
-            'view_count': audio_info.get('play_count'),
-            'like_count': audio_info.get('favorites_count'),
-            'formats': formats,
-        }
-
-
-class XimalayaAlbumIE(XimalayaBaseIE):
-    IE_NAME = 'ximalaya:album'
-    IE_DESC = '喜马拉雅FM 专辑'
-    _VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(?:\d+/)?album/(?P<id>[0-9]+)'
-    _TESTS = [{
-        'url': 'http://www.ximalaya.com/61425525/album/5534601/',
-        'info_dict': {
-            'title': '唐诗三百首（含赏析）',
-            'id': '5534601',
-        },
-        'playlist_mincount': 323,
-    }, {
-        'url': 'https://www.ximalaya.com/album/6912905',
-        'info_dict': {
-            'title': '埃克哈特《修炼当下的力量》',
-            'id': '6912905',
-        },
-        'playlist_mincount': 41,
-    }]
-
-    def _real_extract(self, url):
-        playlist_id = self._match_id(url)
-
-        first_page = self._fetch_page(playlist_id, 1)
-        page_count = math.ceil(first_page['trackTotalCount'] / first_page['pageSize'])
-
-        entries = InAdvancePagedList(
-            lambda idx: self._get_entries(self._fetch_page(playlist_id, idx + 1) if idx else first_page),
-            page_count, first_page['pageSize'])
-
-        title = traverse_obj(first_page, ('tracks', 0, 'albumTitle'), expected_type=str)
-
-        return self.playlist_result(entries, playlist_id, title)
-
-    def _fetch_page(self, playlist_id, page_idx):
-        return self._download_json(
-            'https://www.ximalaya.com/revision/album/v1/getTracksList',
-            playlist_id, note=f'Downloading tracks list page {page_idx}',
-            query={'albumId': playlist_id, 'pageNum': page_idx})['data']
-
-    def _get_entries(self, page_data):
-        for e in page_data['tracks']:
-            yield self.url_result(
-                self._proto_relative_url(f'//www.ximalaya.com{e["url"]}'),
-                XimalayaIE, e.get('trackId'), e.get('title'))

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

@@ -1,92 +0,0 @@
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    str_or_none,
-    try_get,
-    update_url_query,
-    url_or_none,
-)
-
-
-class XinpianchangIE(InfoExtractor):
-    _WORKING = False
-    _VALID_URL = r'https?://www\.xinpianchang\.com/(?P<id>[^/]+?)(?:\D|$)'
-    IE_NAME = 'xinpianchang'
-    IE_DESC = 'xinpianchang.com'
-    _TESTS = [{
-        'url': 'https://www.xinpianchang.com/a11766551',
-        'info_dict': {
-            'id': 'a11766551',
-            'ext': 'mp4',
-            'title': '北京2022冬奥会闭幕式再见短片-冰墩墩下班了',
-            'description': 'md5:4a730c10639a82190fabe921c0fa4b87',
-            'duration': 151,
-            'thumbnail': r're:^https?://oss-xpc0\.xpccdn\.com.+/assets/',
-            'uploader': '正时文创',
-            'uploader_id': '10357277',
-            'categories': ['宣传片', '国家城市', '广告', '其他'],
-            'tags': ['北京冬奥会', '冰墩墩', '再见', '告别', '冰墩墩哭了', '感动', '闭幕式', '熄火']
-        },
-    }, {
-        'url': 'https://www.xinpianchang.com/a11762904',
-        'info_dict': {
-            'id': 'a11762904',
-            'ext': 'mp4',
-            'title': '冬奥会决胜时刻《法国派出三只鸡？》',
-            'description': 'md5:55cb139ef8f48f0c877932d1f196df8b',
-            'duration': 136,
-            'thumbnail': r're:^https?://oss-xpc0\.xpccdn\.com.+/assets/',
-            'uploader': '精品动画',
-            'uploader_id': '10858927',
-            'categories': ['动画', '三维CG'],
-            'tags': ['France Télévisions', '法国3台', '蠢萌', '冬奥会']
-        },
-    }, {
-        'url': 'https://www.xinpianchang.com/a11779743?from=IndexPick&part=%E7%BC%96%E8%BE%91%E7%B2%BE%E9%80%89&index=2',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id=video_id)
-        domain = self.find_value_with_regex(var='requireNewDomain', webpage=webpage)
-        vid = self.find_value_with_regex(var='vid', webpage=webpage)
-        app_key = self.find_value_with_regex(var='modeServerAppKey', webpage=webpage)
-        api = update_url_query(f'{domain}/mod/api/v2/media/{vid}', {'appKey': app_key})
-        data = self._download_json(api, video_id=video_id)['data']
-        formats, subtitles = [], {}
-        for k, v in data.get('resource').items():
-            if k in ('dash', 'hls'):
-                v_url = v.get('url')
-                if not v_url:
-                    continue
-                if k == 'dash':
-                    fmts, subs = self._extract_mpd_formats_and_subtitles(v_url, video_id=video_id)
-                elif k == 'hls':
-                    fmts, subs = self._extract_m3u8_formats_and_subtitles(v_url, video_id=video_id)
-                formats.extend(fmts)
-                subtitles = self._merge_subtitles(subtitles, subs)
-            elif k == 'progressive':
-                formats.extend([{
-                    'url': url_or_none(prog.get('url')),
-                    'width': int_or_none(prog.get('width')),
-                    'height': int_or_none(prog.get('height')),
-                    'ext': 'mp4',
-                } for prog in v if prog.get('url') or []])
-
-        return {
-            'id': video_id,
-            'title': data.get('title'),
-            'description': data.get('description'),
-            'duration': int_or_none(data.get('duration')),
-            'categories': data.get('categories'),
-            'tags': data.get('keywords'),
-            'thumbnail': data.get('cover'),
-            'uploader': try_get(data, lambda x: x['owner']['username']),
-            'uploader_id': str_or_none(try_get(data, lambda x: x['owner']['id'])),
-            'formats': formats,
-            'subtitles': subtitles,
-        }
-
-    def find_value_with_regex(self, var, webpage):
-        return self._search_regex(rf'var\s{var}\s=\s\"(?P<vid>[^\"]+)\"', webpage, name=var)

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

@@ -1,77 +0,0 @@
-import re
-import time
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_ord,
-)
-from ..utils import (
-    int_or_none,
-    parse_duration,
-)
-
-
-class XMinusIE(InfoExtractor):
-    _WORKING = False
-    _VALID_URL = r'https?://(?:www\.)?x-minus\.org/track/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://x-minus.org/track/4542/%D0%BF%D0%B5%D1%81%D0%B5%D0%BD%D0%BA%D0%B0-%D1%88%D0%BE%D1%84%D0%B5%D1%80%D0%B0.html',
-        'md5': '401a15f2d2dcf6d592cb95528d72a2a8',
-        'info_dict': {
-            'id': '4542',
-            'ext': 'mp3',
-            'title': 'Леонид Агутин-Песенка шофёра',
-            'duration': 156,
-            'tbr': 320,
-            'filesize_approx': 5900000,
-            'view_count': int,
-            'description': 'md5:03238c5b663810bc79cf42ef3c03e371',
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        artist = self._html_search_regex(
-            r'<a[^>]+href="/artist/\d+">([^<]+)</a>', webpage, 'artist')
-        title = artist + '-' + self._html_search_regex(
-            r'<span[^>]+class="minustrack-full-title(?:\s+[^"]+)?"[^>]*>([^<]+)', webpage, 'title')
-        duration = parse_duration(self._html_search_regex(
-            r'<span[^>]+class="player-duration(?:\s+[^"]+)?"[^>]*>([^<]+)',
-            webpage, 'duration', fatal=False))
-        mobj = re.search(
-            r'<div[^>]+class="dw-info(?:\s+[^"]+)?"[^>]*>(?P<tbr>\d+)\s*кбит/c\s+(?P<filesize>[0-9.]+)\s*мб</div>',
-            webpage)
-        tbr = filesize_approx = None
-        if mobj:
-            filesize_approx = float(mobj.group('filesize')) * 1000000
-            tbr = float(mobj.group('tbr'))
-        view_count = int_or_none(self._html_search_regex(
-            r'<span><[^>]+class="icon-chart-bar".*?>(\d+)</span>',
-            webpage, 'view count', fatal=False))
-        description = self._html_search_regex(
-            r'(?s)<pre[^>]+id="lyrics-original"[^>]*>(.*?)</pre>',
-            webpage, 'song lyrics', fatal=False)
-        if description:
-            description = re.sub(' *\r *', '\n', description)
-
-        k = self._search_regex(
-            r'<div[^>]+id="player-bottom"[^>]+data-k="([^"]+)">', webpage,
-            'encoded data')
-        h = time.time() / 3600
-        a = sum(map(int, [compat_ord(c) for c in k])) + int(video_id) + h
-        video_url = 'http://x-minus.me/dl/minus?id=%s&tkn2=%df%d' % (video_id, a, h)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'url': video_url,
-            # The extension is unknown until actual downloading
-            'ext': 'mp3',
-            'duration': duration,
-            'filesize_approx': filesize_approx,
-            'tbr': tbr,
-            'view_count': view_count,
-            'description': description,
-        }

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

@@ -1,83 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    determine_ext,
-    int_or_none,
-    NO_DEFAULT,
-    str_to_int,
-)
-
-
-class XNXXIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:video|www)\.xnxx3?\.com/video-?(?P<id>[0-9a-z]+)/'
-    _TESTS = [{
-        'url': 'http://www.xnxx.com/video-55awb78/skyrim_test_video',
-        'md5': '7583e96c15c0f21e9da3453d9920fbba',
-        'info_dict': {
-            'id': '55awb78',
-            'ext': 'mp4',
-            'title': 'Skyrim Test Video',
-            'thumbnail': r're:^https?://.*\.jpg',
-            'duration': 469,
-            'view_count': int,
-            'age_limit': 18,
-        },
-    }, {
-        'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.xnxx.com/video-55awb78/',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.xnxx3.com/video-55awb78/',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        def get(meta, default=NO_DEFAULT, fatal=True):
-            return self._search_regex(
-                r'set%s\s*\(\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % meta,
-                webpage, meta, default=default, fatal=fatal, group='value')
-
-        title = self._og_search_title(
-            webpage, default=None) or get('VideoTitle')
-
-        formats = []
-        for mobj in re.finditer(
-                r'setVideo(?:Url(?P<id>Low|High)|HLS)\s*\(\s*(?P<q>["\'])(?P<url>(?:https?:)?//.+?)(?P=q)', webpage):
-            format_url = mobj.group('url')
-            if determine_ext(format_url) == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    format_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                    quality=1, m3u8_id='hls', fatal=False))
-            else:
-                format_id = mobj.group('id')
-                if format_id:
-                    format_id = format_id.lower()
-                formats.append({
-                    'url': format_url,
-                    'format_id': format_id,
-                    'quality': -1 if format_id == 'low' else 0,
-                })
-
-        thumbnail = self._og_search_thumbnail(webpage, default=None) or get(
-            'ThumbUrl', fatal=False) or get('ThumbUrl169', fatal=False)
-        duration = int_or_none(self._og_search_property('duration', webpage))
-        view_count = str_to_int(self._search_regex(
-            r'id=["\']nb-views-number[^>]+>([\d,.]+)', webpage, 'view count',
-            default=None))
-
-        return {
-            'id': video_id,
-            'title': title,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'view_count': view_count,
-            'age_limit': 18,
-            'formats': formats,
-        }

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

@@ -1,115 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    parse_iso8601,
-    xpath_with_ns,
-    xpath_text,
-    find_xpath_attr,
-)
-
-
-class XstreamIE(InfoExtractor):
-    _VALID_URL = r'''(?x)
-                    (?:
-                        xstream:|
-                        https?://frontend\.xstream\.(?:dk|net)/
-                    )
-                    (?P<partner_id>[^/]+)
-                    (?:
-                        :|
-                        /feed/video/\?.*?\bid=
-                    )
-                    (?P<id>\d+)
-                    '''
-    _TESTS = [{
-        'url': 'http://frontend.xstream.dk/btno/feed/video/?platform=web&id=86588',
-        'md5': 'd7d17e3337dc80de6d3a540aefbe441b',
-        'info_dict': {
-            'id': '86588',
-            'ext': 'mov',
-            'title': 'Otto Wollertsen',
-            'description': 'Vestlendingen Otto Fredrik Wollertsen',
-            'timestamp': 1430473209,
-            'upload_date': '20150501',
-        },
-    }, {
-        'url': 'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=21039',
-        'only_matching': True,
-    }]
-
-    def _extract_video_info(self, partner_id, video_id):
-        data = self._download_xml(
-            'http://frontend.xstream.dk/%s/feed/video/?platform=web&id=%s'
-            % (partner_id, video_id),
-            video_id)
-
-        NS_MAP = {
-            'atom': 'http://www.w3.org/2005/Atom',
-            'xt': 'http://xstream.dk/',
-            'media': 'http://search.yahoo.com/mrss/',
-        }
-
-        entry = data.find(xpath_with_ns('./atom:entry', NS_MAP))
-
-        title = xpath_text(
-            entry, xpath_with_ns('./atom:title', NS_MAP), 'title')
-        description = xpath_text(
-            entry, xpath_with_ns('./atom:summary', NS_MAP), 'description')
-        timestamp = parse_iso8601(xpath_text(
-            entry, xpath_with_ns('./atom:published', NS_MAP), 'upload date'))
-
-        formats = []
-        media_group = entry.find(xpath_with_ns('./media:group', NS_MAP))
-        for media_content in media_group.findall(xpath_with_ns('./media:content', NS_MAP)):
-            media_url = media_content.get('url')
-            if not media_url:
-                continue
-            tbr = int_or_none(media_content.get('bitrate'))
-            mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', media_url)
-            if mobj:
-                formats.append({
-                    'url': mobj.group('url'),
-                    'play_path': 'mp4:%s' % mobj.group('playpath'),
-                    'app': mobj.group('app'),
-                    'ext': 'flv',
-                    'tbr': tbr,
-                    'format_id': 'rtmp-%d' % tbr,
-                })
-            else:
-                formats.append({
-                    'url': media_url,
-                    'tbr': tbr,
-                })
-
-        link = find_xpath_attr(
-            entry, xpath_with_ns('./atom:link', NS_MAP), 'rel', 'original')
-        if link is not None:
-            formats.append({
-                'url': link.get('href'),
-                'format_id': link.get('rel'),
-                'quality': 1,
-            })
-
-        thumbnails = [{
-            'url': splash.get('url'),
-            'width': int_or_none(splash.get('width')),
-            'height': int_or_none(splash.get('height')),
-        } for splash in media_group.findall(xpath_with_ns('./xt:splash', NS_MAP))]
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'timestamp': timestamp,
-            'formats': formats,
-            'thumbnails': thumbnails,
-        }
-
-    def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
-        partner_id = mobj.group('partner_id')
-        video_id = mobj.group('id')
-
-        return self._extract_video_info(partner_id, video_id)