@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/bandcamp.py

@@ -0,0 +1,485 @@
+import random
+import re
+import time
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    KNOWN_EXTENSIONS,
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    parse_filesize,
+    str_or_none,
+    try_get,
+    unified_strdate,
+    unified_timestamp,
+    update_url_query,
+    url_or_none,
+    urljoin,
+)
+
+
+class BandcampIE(InfoExtractor):
+    _VALID_URL = r'https?://(?P<uploader>[^/]+)\.bandcamp\.com/track/(?P<id>[^/?#&]+)'
+    _EMBED_REGEX = [r'<meta property="og:url"[^>]*?content="(?P<url>.*?bandcamp\.com.*?)"']
+    _TESTS = [{
+        'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
+        'md5': 'c557841d5e50261777a6585648adf439',
+        'info_dict': {
+            'id': '1812978515',
+            'ext': 'mp3',
+            'title': 'youtube-dl "\'/\\ä↭ - youtube-dl "\'/\\ä↭ - youtube-dl test song "\'/\\ä↭',
+            'duration': 9.8485,
+            'uploader': 'youtube-dl "\'/\\ä↭',
+            'upload_date': '20121129',
+            'timestamp': 1354224127,
+            'track': 'youtube-dl "\'/\\ä↭ - youtube-dl test song "\'/\\ä↭',
+            'album_artist': 'youtube-dl "\'/\\ä↭',
+            'track_id': '1812978515',
+            'artist': 'youtube-dl "\'/\\ä↭',
+            'uploader_url': 'https://youtube-dl.bandcamp.com',
+            'uploader_id': 'youtube-dl',
+            'thumbnail': 'https://f4.bcbits.com/img/a3216802731_5.jpg',
+        },
+        '_skip': 'There is a limit of 200 free downloads / month for the test song'
+    }, {
+        # free download
+        'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
+        'info_dict': {
+            'id': '2650410135',
+            'ext': 'm4a',
+            'acodec': r're:[fa]lac',
+            'title': 'Ben Prunty - Lanius (Battle)',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'Ben Prunty',
+            'timestamp': 1396508491,
+            'upload_date': '20140403',
+            'release_timestamp': 1396483200,
+            'release_date': '20140403',
+            'duration': 260.877,
+            'track': 'Lanius (Battle)',
+            'track_number': 1,
+            'track_id': '2650410135',
+            'artist': 'Ben Prunty',
+            'album_artist': 'Ben Prunty',
+            'album': 'FTL: Advanced Edition Soundtrack',
+            'uploader_url': 'https://benprunty.bandcamp.com',
+            'uploader_id': 'benprunty',
+        },
+    }, {
+        # no free download, mp3 128
+        'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire',
+        'md5': 'fec12ff55e804bb7f7ebeb77a800c8b7',
+        'info_dict': {
+            'id': '2584466013',
+            'ext': 'mp3',
+            'title': 'Mastodon - Hail to Fire',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'Mastodon',
+            'timestamp': 1322005399,
+            'upload_date': '20111122',
+            'release_timestamp': 1076112000,
+            'release_date': '20040207',
+            'duration': 120.79,
+            'track': 'Hail to Fire',
+            'track_number': 5,
+            'track_id': '2584466013',
+            'artist': 'Mastodon',
+            'album_artist': 'Mastodon',
+            'album': 'Call of the Mastodon',
+            'uploader_url': 'https://relapsealumni.bandcamp.com',
+            'uploader_id': 'relapsealumni',
+        },
+    }, {
+        # track from compilation album (artist/album_artist difference)
+        'url': 'https://diskotopia.bandcamp.com/track/safehouse',
+        'md5': '19c5337bca1428afa54129f86a2f6a69',
+        'info_dict': {
+            'id': '1978174799',
+            'ext': 'mp3',
+            'title': 'submerse - submerse - Safehouse',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'submerse',
+            'timestamp': 1480779297,
+            'upload_date': '20161203',
+            'release_timestamp': 1481068800,
+            'release_date': '20161207',
+            'duration': 154.066,
+            'track': 'submerse - Safehouse',
+            'track_number': 3,
+            'track_id': '1978174799',
+            'artist': 'submerse',
+            'album_artist': 'Diskotopia',
+            'album': 'DSK F/W 2016-2017 Free Compilation',
+            'uploader_url': 'https://diskotopia.bandcamp.com',
+            'uploader_id': 'diskotopia',
+        },
+    }]
+
+    def _extract_data_attr(self, webpage, video_id, attr='tralbum', fatal=True):
+        return self._parse_json(self._html_search_regex(
+            r'data-%s=(["\'])({.+?})\1' % attr, webpage,
+            attr + ' data', group=2), video_id, fatal=fatal)
+
+    def _real_extract(self, url):
+        title, uploader = self._match_valid_url(url).group('id', 'uploader')
+        webpage = self._download_webpage(url, title)
+        tralbum = self._extract_data_attr(webpage, title)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        track_id = None
+        track = None
+        track_number = None
+        duration = None
+
+        formats = []
+        track_info = try_get(tralbum, lambda x: x['trackinfo'][0], dict)
+        if track_info:
+            file_ = track_info.get('file')
+            if isinstance(file_, dict):
+                for format_id, format_url in file_.items():
+                    if not url_or_none(format_url):
+                        continue
+                    ext, abr_str = format_id.split('-', 1)
+                    formats.append({
+                        'format_id': format_id,
+                        'url': self._proto_relative_url(format_url, 'http:'),
+                        'ext': ext,
+                        'vcodec': 'none',
+                        'acodec': ext,
+                        'abr': int_or_none(abr_str),
+                    })
+            track = track_info.get('title')
+            track_id = str_or_none(
+                track_info.get('track_id') or track_info.get('id'))
+            track_number = int_or_none(track_info.get('track_num'))
+            duration = float_or_none(track_info.get('duration'))
+
+        embed = self._extract_data_attr(webpage, title, 'embed', False)
+        current = tralbum.get('current') or {}
+        artist = embed.get('artist') or current.get('artist') or tralbum.get('artist')
+        album_artist = self._html_search_regex(
+            r'<h3 class="albumTitle">[\S\s]*?by\s*<span>\s*<a href="[^>]+">\s*([^>]+?)\s*</a>',
+            webpage, 'album artist', fatal=False)
+        timestamp = unified_timestamp(
+            current.get('publish_date') or tralbum.get('album_publish_date'))
+
+        download_link = tralbum.get('freeDownloadPage')
+        if download_link:
+            track_id = compat_str(tralbum['id'])
+
+            download_webpage = self._download_webpage(
+                download_link, track_id, 'Downloading free downloads page')
+
+            blob = self._extract_data_attr(download_webpage, track_id, 'blob')
+
+            info = try_get(
+                blob, (lambda x: x['digital_items'][0],
+                       lambda x: x['download_items'][0]), dict)
+            if info:
+                downloads = info.get('downloads')
+                if isinstance(downloads, dict):
+                    if not track:
+                        track = info.get('title')
+                    if not artist:
+                        artist = info.get('artist')
+                    if not thumbnail:
+                        thumbnail = info.get('thumb_url')
+
+                    download_formats = {}
+                    download_formats_list = blob.get('download_formats')
+                    if isinstance(download_formats_list, list):
+                        for f in blob['download_formats']:
+                            name, ext = f.get('name'), f.get('file_extension')
+                            if all(isinstance(x, compat_str) for x in (name, ext)):
+                                download_formats[name] = ext.strip('.')
+
+                    for format_id, f in downloads.items():
+                        format_url = f.get('url')
+                        if not format_url:
+                            continue
+                        # Stat URL generation algorithm is reverse engineered from
+                        # download_*_bundle_*.js
+                        stat_url = update_url_query(
+                            format_url.replace('/download/', '/statdownload/'), {
+                                '.rand': int(time.time() * 1000 * random.random()),
+                            })
+                        format_id = f.get('encoding_name') or format_id
+                        stat = self._download_json(
+                            stat_url, track_id, 'Downloading %s JSON' % format_id,
+                            transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
+                            fatal=False)
+                        if not stat:
+                            continue
+                        retry_url = url_or_none(stat.get('retry_url'))
+                        if not retry_url:
+                            continue
+                        formats.append({
+                            'url': self._proto_relative_url(retry_url, 'http:'),
+                            'ext': download_formats.get(format_id),
+                            'format_id': format_id,
+                            'format_note': f.get('description'),
+                            'filesize': parse_filesize(f.get('size_mb')),
+                            'vcodec': 'none',
+                            'acodec': format_id.split('-')[0],
+                        })
+
+        title = '%s - %s' % (artist, track) if artist else track
+
+        if not duration:
+            duration = float_or_none(self._html_search_meta(
+                'duration', webpage, default=None))
+
+        return {
+            'id': track_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'uploader': artist,
+            'uploader_id': uploader,
+            'uploader_url': f'https://{uploader}.bandcamp.com',
+            'timestamp': timestamp,
+            'release_timestamp': unified_timestamp(tralbum.get('album_release_date')),
+            'duration': duration,
+            'track': track,
+            'track_number': track_number,
+            'track_id': track_id,
+            'artist': artist,
+            'album': embed.get('album_title'),
+            'album_artist': album_artist,
+            'formats': formats,
+        }
+
+
+class BandcampAlbumIE(BandcampIE):  # XXX: Do not subclass from concrete IE
+    IE_NAME = 'Bandcamp:album'
+    _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com/album/(?P<id>[^/?#&]+)'
+
+    _TESTS = [{
+        'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
+        'playlist': [
+            {
+                'md5': '39bc1eded3476e927c724321ddf116cf',
+                'info_dict': {
+                    'id': '1353101989',
+                    'ext': 'mp3',
+                    'title': 'Blazo - Intro',
+                    'timestamp': 1311756226,
+                    'upload_date': '20110727',
+                    'uploader': 'Blazo',
+                }
+            },
+            {
+                'md5': '1a2c32e2691474643e912cc6cd4bffaa',
+                'info_dict': {
+                    'id': '38097443',
+                    'ext': 'mp3',
+                    'title': 'Blazo - Kero One - Keep It Alive (Blazo remix)',
+                    'timestamp': 1311757238,
+                    'upload_date': '20110727',
+                    'uploader': 'Blazo',
+                }
+            },
+        ],
+        'info_dict': {
+            'title': 'Jazz Format Mixtape vol.1',
+            'id': 'jazz-format-mixtape-vol-1',
+            'uploader_id': 'blazo',
+        },
+        'params': {
+            'playlistend': 2
+        },
+        'skip': 'Bandcamp imposes download limits.'
+    }, {
+        'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
+        'info_dict': {
+            'title': 'Hierophany of the Open Grave',
+            'uploader_id': 'nightbringer',
+            'id': 'hierophany-of-the-open-grave',
+        },
+        'playlist_mincount': 9,
+    }, {
+        # with escaped quote in title
+        'url': 'https://jstrecords.bandcamp.com/album/entropy-ep',
+        'info_dict': {
+            'title': '"Entropy" EP',
+            'uploader_id': 'jstrecords',
+            'id': 'entropy-ep',
+            'description': 'md5:0ff22959c943622972596062f2f366a5',
+        },
+        'playlist_mincount': 3,
+    }, {
+        # not all tracks have songs
+        'url': 'https://insulters.bandcamp.com/album/we-are-the-plague',
+        'info_dict': {
+            'id': 'we-are-the-plague',
+            'title': 'WE ARE THE PLAGUE',
+            'uploader_id': 'insulters',
+            'description': 'md5:b3cf845ee41b2b1141dc7bde9237255f',
+        },
+        'playlist_count': 2,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return (False
+                if BandcampWeeklyIE.suitable(url) or BandcampIE.suitable(url)
+                else super(BandcampAlbumIE, cls).suitable(url))
+
+    def _real_extract(self, url):
+        uploader_id, album_id = self._match_valid_url(url).groups()
+        playlist_id = album_id or uploader_id
+        webpage = self._download_webpage(url, playlist_id)
+        tralbum = self._extract_data_attr(webpage, playlist_id)
+        track_info = tralbum.get('trackinfo')
+        if not track_info:
+            raise ExtractorError('The page doesn\'t contain any tracks')
+        # Only tracks with duration info have songs
+        entries = [
+            self.url_result(
+                urljoin(url, t['title_link']), BandcampIE.ie_key(),
+                str_or_none(t.get('track_id') or t.get('id')), t.get('title'))
+            for t in track_info
+            if t.get('duration')]
+
+        current = tralbum.get('current') or {}
+
+        return {
+            '_type': 'playlist',
+            'uploader_id': uploader_id,
+            'id': playlist_id,
+            'title': current.get('title'),
+            'description': current.get('about'),
+            'entries': entries,
+        }
+
+
+class BandcampWeeklyIE(BandcampIE):  # XXX: Do not subclass from concrete IE
+    IE_NAME = 'Bandcamp:weekly'
+    _VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://bandcamp.com/?show=224',
+        'md5': 'b00df799c733cf7e0c567ed187dea0fd',
+        'info_dict': {
+            'id': '224',
+            'ext': 'opus',
+            'title': 'BC Weekly April 4th 2017 - Magic Moments',
+            'description': 'md5:5d48150916e8e02d030623a48512c874',
+            'duration': 5829.77,
+            'release_date': '20170404',
+            'series': 'Bandcamp Weekly',
+            'episode': 'Magic Moments',
+            'episode_id': '224',
+        },
+        'params': {
+            'format': 'opus-lo',
+        },
+    }, {
+        'url': 'https://bandcamp.com/?blah/blah@&show=228',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        webpage = self._download_webpage(url, show_id)
+
+        blob = self._extract_data_attr(webpage, show_id, 'blob')
+
+        show = blob['bcw_data'][show_id]
+
+        formats = []
+        for format_id, format_url in show['audio_stream'].items():
+            if not url_or_none(format_url):
+                continue
+            for known_ext in KNOWN_EXTENSIONS:
+                if known_ext in format_id:
+                    ext = known_ext
+                    break
+            else:
+                ext = None
+            formats.append({
+                'format_id': format_id,
+                'url': format_url,
+                'ext': ext,
+                'vcodec': 'none',
+            })
+
+        title = show.get('audio_title') or 'Bandcamp Weekly'
+        subtitle = show.get('subtitle')
+        if subtitle:
+            title += ' - %s' % subtitle
+
+        return {
+            'id': show_id,
+            'title': title,
+            'description': show.get('desc') or show.get('short_desc'),
+            'duration': float_or_none(show.get('audio_duration')),
+            'is_live': False,
+            'release_date': unified_strdate(show.get('published_date')),
+            'series': 'Bandcamp Weekly',
+            'episode': show.get('subtitle'),
+            'episode_id': show_id,
+            'formats': formats
+        }
+
+
+class BandcampUserIE(InfoExtractor):
+    IE_NAME = 'Bandcamp:user'
+    _VALID_URL = r'https?://(?!www\.)(?P<id>[^.]+)\.bandcamp\.com(?:/music)?/?(?:[#?]|$)'
+
+    _TESTS = [{
+        # Type 1 Bandcamp user page.
+        'url': 'https://adrianvonziegler.bandcamp.com',
+        'info_dict': {
+            'id': 'adrianvonziegler',
+            'title': 'Discography of adrianvonziegler',
+        },
+        'playlist_mincount': 23,
+    }, {
+        # Bandcamp user page with only one album
+        'url': 'http://dotscale.bandcamp.com',
+        'info_dict': {
+            'id': 'dotscale',
+            'title': 'Discography of dotscale'
+        },
+        'playlist_count': 1,
+    }, {
+        # Type 2 Bandcamp user page.
+        'url': 'https://nightcallofficial.bandcamp.com',
+        'info_dict': {
+            'id': 'nightcallofficial',
+            'title': 'Discography of nightcallofficial',
+        },
+        'playlist_count': 4,
+    }, {
+        'url': 'https://steviasphere.bandcamp.com/music',
+        'playlist_mincount': 47,
+        'info_dict': {
+            'id': 'steviasphere',
+            'title': 'Discography of steviasphere',
+        },
+    }, {
+        'url': 'https://coldworldofficial.bandcamp.com/music',
+        'playlist_mincount': 10,
+        'info_dict': {
+            'id': 'coldworldofficial',
+            'title': 'Discography of coldworldofficial',
+        },
+    }, {
+        'url': 'https://nuclearwarnowproductions.bandcamp.com/music',
+        'playlist_mincount': 399,
+        'info_dict': {
+            'id': 'nuclearwarnowproductions',
+            'title': 'Discography of nuclearwarnowproductions',
+        },
+    }]
+
+    def _real_extract(self, url):
+        uploader = self._match_id(url)
+        webpage = self._download_webpage(url, uploader)
+
+        discography_data = (re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\'](?![^"\'/]*?/merch)([^"\']+)', webpage)
+                            or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage))
+
+        return self.playlist_from_matches(
+            discography_data, uploader, f'Discography of {uploader}', getter=lambda x: urljoin(url, x))

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

@@ -0,0 +1,155 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    try_get,
+    int_or_none,
+    url_or_none,
+    float_or_none,
+    unified_timestamp,
+)
+
+
+class BannedVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?banned\.video/watch\?id=(?P<id>[0-f]{24})'
+    _TESTS = [{
+        'url': 'https://banned.video/watch?id=5e7a859644e02200c6ef5f11',
+        'md5': '14b6e81d41beaaee2215cd75c6ed56e4',
+        'info_dict': {
+            'id': '5e7a859644e02200c6ef5f11',
+            'ext': 'mp4',
+            'title': 'China Discovers Origin of Corona Virus: Issues Emergency Statement',
+            'thumbnail': r're:^https?://(?:www\.)?assets\.infowarsmedia.com/images/',
+            'description': 'md5:560d96f02abbebe6c6b78b47465f6b28',
+            'upload_date': '20200324',
+            'timestamp': 1585087895,
+        }
+    }]
+
+    _GRAPHQL_GETMETADATA_QUERY = '''
+query GetVideoAndComments($id: String!) {
+    getVideo(id: $id) {
+        streamUrl
+        directUrl
+        unlisted
+        live
+        tags {
+            name
+        }
+        title
+        summary
+        playCount
+        largeImage
+        videoDuration
+        channel {
+            _id
+            title
+        }
+        createdAt
+    }
+    getVideoComments(id: $id, limit: 999999, offset: 0) {
+        _id
+        content
+        user {
+            _id
+            username
+        }
+        voteCount {
+            positive
+        }
+        createdAt
+        replyCount
+    }
+}'''
+
+    _GRAPHQL_GETCOMMENTSREPLIES_QUERY = '''
+query GetCommentReplies($id: String!) {
+    getCommentReplies(id: $id, limit: 999999, offset: 0) {
+        _id
+        content
+        user {
+            _id
+            username
+        }
+        voteCount {
+            positive
+        }
+        createdAt
+        replyCount
+    }
+}'''
+
+    _GRAPHQL_QUERIES = {
+        'GetVideoAndComments': _GRAPHQL_GETMETADATA_QUERY,
+        'GetCommentReplies': _GRAPHQL_GETCOMMENTSREPLIES_QUERY,
+    }
+
+    def _call_api(self, video_id, id, operation, note):
+        return self._download_json(
+            'https://api.infowarsmedia.com/graphql', video_id, note=note,
+            headers={
+                'Content-Type': 'application/json; charset=utf-8'
+            }, data=json.dumps({
+                'variables': {'id': id},
+                'operationName': operation,
+                'query': self._GRAPHQL_QUERIES[operation]
+            }).encode('utf8')).get('data')
+
+    def _get_comments(self, video_id, comments, comment_data):
+        yield from comments
+        for comment in comment_data.copy():
+            comment_id = comment.get('_id')
+            if comment.get('replyCount') > 0:
+                reply_json = self._call_api(
+                    video_id, comment_id, 'GetCommentReplies',
+                    f'Downloading replies for comment {comment_id}')
+                for reply in reply_json.get('getCommentReplies'):
+                    yield self._parse_comment(reply, comment_id)
+
+    @staticmethod
+    def _parse_comment(comment_data, parent):
+        return {
+            'id': comment_data.get('_id'),
+            'text': comment_data.get('content'),
+            'author': try_get(comment_data, lambda x: x['user']['username']),
+            'author_id': try_get(comment_data, lambda x: x['user']['_id']),
+            'timestamp': unified_timestamp(comment_data.get('createdAt')),
+            'parent': parent,
+            'like_count': try_get(comment_data, lambda x: x['voteCount']['positive']),
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_json = self._call_api(video_id, video_id, 'GetVideoAndComments', 'Downloading video metadata')
+        video_info = video_json['getVideo']
+        is_live = video_info.get('live')
+        comments = [self._parse_comment(comment, 'root') for comment in video_json.get('getVideoComments')]
+
+        formats = [{
+            'format_id': 'direct',
+            'quality': 1,
+            'url': video_info.get('directUrl'),
+            'ext': 'mp4',
+        }] if url_or_none(video_info.get('directUrl')) else []
+        if video_info.get('streamUrl'):
+            formats.extend(self._extract_m3u8_formats(
+                video_info.get('streamUrl'), video_id, 'mp4',
+                entry_protocol='m3u8_native', m3u8_id='hls', live=True))
+
+        return {
+            'id': video_id,
+            'title': video_info.get('title')[:-1],
+            'formats': formats,
+            'is_live': is_live,
+            'description': video_info.get('summary'),
+            'channel': try_get(video_info, lambda x: x['channel']['title']),
+            'channel_id': try_get(video_info, lambda x: x['channel']['_id']),
+            'view_count': int_or_none(video_info.get('playCount')),
+            'thumbnail': url_or_none(video_info.get('largeImage')),
+            'duration': float_or_none(video_info.get('videoDuration')),
+            'timestamp': unified_timestamp(video_info.get('createdAt')),
+            'tags': [tag.get('name') for tag in video_info.get('tags')],
+            'availability': self._availability(is_unlisted=video_info.get('unlisted')),
+            'comments': comments,
+            '__post_extractor': self.extract_comments(video_id, comments, video_json.get('getVideoComments'))
+        }