@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/qqmusic.py

@@ -0,0 +1,365 @@
+import random
+import re
+import time
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    strip_jsonp,
+    unescapeHTML,
+)
+
+
+class QQMusicIE(InfoExtractor):
+    IE_NAME = 'qqmusic'
+    IE_DESC = 'QQ音乐'
+    _VALID_URL = r'https?://y\.qq\.com/n/yqq/song/(?P<id>[0-9A-Za-z]+)\.html'
+    _TESTS = [{
+        'url': 'https://y.qq.com/n/yqq/song/004295Et37taLD.html',
+        'md5': '5f1e6cea39e182857da7ffc5ef5e6bb8',
+        'info_dict': {
+            'id': '004295Et37taLD',
+            'ext': 'mp3',
+            'title': '可惜没如果',
+            'release_date': '20141227',
+            'creator': '林俊杰',
+            'description': 'md5:d85afb3051952ecc50a1ee8a286d1eac',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        }
+    }, {
+        'note': 'There is no mp3-320 version of this song.',
+        'url': 'https://y.qq.com/n/yqq/song/004MsGEo3DdNxV.html',
+        'md5': 'fa3926f0c585cda0af8fa4f796482e3e',
+        'info_dict': {
+            'id': '004MsGEo3DdNxV',
+            'ext': 'mp3',
+            'title': '如果',
+            'release_date': '20050626',
+            'creator': '李季美',
+            'description': 'md5:46857d5ed62bc4ba84607a805dccf437',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        }
+    }, {
+        'note': 'lyrics not in .lrc format',
+        'url': 'https://y.qq.com/n/yqq/song/001JyApY11tIp6.html',
+        'info_dict': {
+            'id': '001JyApY11tIp6',
+            'ext': 'mp3',
+            'title': 'Shadows Over Transylvania',
+            'release_date': '19970225',
+            'creator': 'Dark Funeral',
+            'description': 'md5:c9b20210587cbcd6836a1c597bab4525',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    _FORMATS = {
+        'mp3-320': {'prefix': 'M800', 'ext': 'mp3', 'preference': 40, 'abr': 320},
+        'mp3-128': {'prefix': 'M500', 'ext': 'mp3', 'preference': 30, 'abr': 128},
+        'm4a': {'prefix': 'C200', 'ext': 'm4a', 'preference': 10}
+    }
+
+    # Reference: m_r_GetRUin() in top_player.js
+    # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
+    @staticmethod
+    def m_r_get_ruin():
+        curMs = int(time.time() * 1000) % 1000
+        return int(round(random.random() * 2147483647) * curMs % 1E10)
+
+    def _real_extract(self, url):
+        mid = self._match_id(url)
+
+        detail_info_page = self._download_webpage(
+            'http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid=%s&play=0' % mid,
+            mid, note='Download song detail info',
+            errnote='Unable to get song detail info', encoding='gbk')
+
+        song_name = self._html_search_regex(
+            r"songname:\s*'([^']+)'", detail_info_page, 'song name')
+
+        publish_time = self._html_search_regex(
+            r'发行时间：(\d{4}-\d{2}-\d{2})', detail_info_page,
+            'publish time', default=None)
+        if publish_time:
+            publish_time = publish_time.replace('-', '')
+
+        singer = self._html_search_regex(
+            r"singer:\s*'([^']+)", detail_info_page, 'singer', default=None)
+
+        lrc_content = self._html_search_regex(
+            r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
+            detail_info_page, 'LRC lyrics', default=None)
+        if lrc_content:
+            lrc_content = lrc_content.replace('\\n', '\n')
+
+        thumbnail_url = None
+        albummid = self._search_regex(
+            [r'albummid:\'([0-9a-zA-Z]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'],
+            detail_info_page, 'album mid', default=None)
+        if albummid:
+            thumbnail_url = 'http://i.gtimg.cn/music/photo/mid_album_500/%s/%s/%s.jpg' \
+                            % (albummid[-2:-1], albummid[-1], albummid)
+
+        guid = self.m_r_get_ruin()
+
+        vkey = self._download_json(
+            'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid,
+            mid, note='Retrieve vkey', errnote='Unable to get vkey',
+            transform_source=strip_jsonp)['key']
+
+        formats = []
+        for format_id, details in self._FORMATS.items():
+            formats.append({
+                'url': 'http://cc.stream.qqmusic.qq.com/%s%s.%s?vkey=%s&guid=%s&fromtag=0'
+                       % (details['prefix'], mid, details['ext'], vkey, guid),
+                'format': format_id,
+                'format_id': format_id,
+                'quality': details['preference'],
+                'abr': details.get('abr'),
+            })
+        self._check_formats(formats, mid)
+
+        actual_lrc_lyrics = ''.join(
+            line + '\n' for line in re.findall(
+                r'(?m)^(\[[0-9]{2}:[0-9]{2}(?:\.[0-9]{2,})?\][^\n]*|\[[^\]]*\])', lrc_content))
+
+        info_dict = {
+            'id': mid,
+            'formats': formats,
+            'title': song_name,
+            'release_date': publish_time,
+            'creator': singer,
+            'description': lrc_content,
+            'thumbnail': thumbnail_url
+        }
+        if actual_lrc_lyrics:
+            info_dict['subtitles'] = {
+                'origin': [{
+                    'ext': 'lrc',
+                    'data': actual_lrc_lyrics,
+                }]
+            }
+        return info_dict
+
+
+class QQPlaylistBaseIE(InfoExtractor):
+    @staticmethod
+    def qq_static_url(category, mid):
+        return 'http://y.qq.com/y/static/%s/%s/%s/%s.html' % (category, mid[-2], mid[-1], mid)
+
+    def get_singer_all_songs(self, singmid, num):
+        return self._download_webpage(
+            r'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg', singmid,
+            query={
+                'format': 'json',
+                'inCharset': 'utf8',
+                'outCharset': 'utf-8',
+                'platform': 'yqq',
+                'needNewCode': 0,
+                'singermid': singmid,
+                'order': 'listen',
+                'begin': 0,
+                'num': num,
+                'songstatus': 1,
+            })
+
+    def get_entries_from_page(self, singmid):
+        entries = []
+
+        default_num = 1
+        json_text = self.get_singer_all_songs(singmid, default_num)
+        json_obj_all_songs = self._parse_json(json_text, singmid)
+
+        if json_obj_all_songs['code'] == 0:
+            total = json_obj_all_songs['data']['total']
+            json_text = self.get_singer_all_songs(singmid, total)
+            json_obj_all_songs = self._parse_json(json_text, singmid)
+
+        for item in json_obj_all_songs['data']['list']:
+            if item['musicData'].get('songmid') is not None:
+                songmid = item['musicData']['songmid']
+                entries.append(self.url_result(
+                    r'https://y.qq.com/n/yqq/song/%s.html' % songmid, 'QQMusic', songmid))
+
+        return entries
+
+
+class QQMusicSingerIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:singer'
+    IE_DESC = 'QQ音乐 - 歌手'
+    _VALID_URL = r'https?://y\.qq\.com/n/yqq/singer/(?P<id>[0-9A-Za-z]+)\.html'
+    _TEST = {
+        'url': 'https://y.qq.com/n/yqq/singer/001BLpXF2DyJe2.html',
+        'info_dict': {
+            'id': '001BLpXF2DyJe2',
+            'title': '林俊杰',
+            'description': 'md5:870ec08f7d8547c29c93010899103751',
+        },
+        'playlist_mincount': 12,
+    }
+
+    def _real_extract(self, url):
+        mid = self._match_id(url)
+
+        entries = self.get_entries_from_page(mid)
+        singer_page = self._download_webpage(url, mid, 'Download singer page')
+        singer_name = self._html_search_regex(
+            r"singername\s*:\s*'(.*?)'", singer_page, 'singer name', default=None)
+        singer_desc = None
+
+        if mid:
+            singer_desc_page = self._download_xml(
+                'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg', mid,
+                'Donwload singer description XML',
+                query={'utf8': 1, 'outCharset': 'utf-8', 'format': 'xml', 'singermid': mid},
+                headers={'Referer': 'https://y.qq.com/n/yqq/singer/'})
+
+            singer_desc = singer_desc_page.find('./data/info/desc').text
+
+        return self.playlist_result(entries, mid, singer_name, singer_desc)
+
+
+class QQMusicAlbumIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:album'
+    IE_DESC = 'QQ音乐 - 专辑'
+    _VALID_URL = r'https?://y\.qq\.com/n/yqq/album/(?P<id>[0-9A-Za-z]+)\.html'
+
+    _TESTS = [{
+        'url': 'https://y.qq.com/n/yqq/album/000gXCTb2AhRR1.html',
+        'info_dict': {
+            'id': '000gXCTb2AhRR1',
+            'title': '我们都是这样长大的',
+            'description': 'md5:179c5dce203a5931970d306aa9607ea6',
+        },
+        'playlist_count': 4,
+    }, {
+        'url': 'https://y.qq.com/n/yqq/album/002Y5a3b3AlCu3.html',
+        'info_dict': {
+            'id': '002Y5a3b3AlCu3',
+            'title': '그리고...',
+            'description': 'md5:a48823755615508a95080e81b51ba729',
+        },
+        'playlist_count': 8,
+    }]
+
+    def _real_extract(self, url):
+        mid = self._match_id(url)
+
+        album = self._download_json(
+            'http://i.y.qq.com/v8/fcg-bin/fcg_v8_album_info_cp.fcg?albummid=%s&format=json' % mid,
+            mid, 'Download album page')['data']
+
+        entries = [
+            self.url_result(
+                'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid']
+            ) for song in album['list']
+        ]
+        album_name = album.get('name')
+        album_detail = album.get('desc')
+        if album_detail is not None:
+            album_detail = album_detail.strip()
+
+        return self.playlist_result(entries, mid, album_name, album_detail)
+
+
+class QQMusicToplistIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:toplist'
+    IE_DESC = 'QQ音乐 - 排行榜'
+    _VALID_URL = r'https?://y\.qq\.com/n/yqq/toplist/(?P<id>[0-9]+)\.html'
+
+    _TESTS = [{
+        'url': 'https://y.qq.com/n/yqq/toplist/123.html',
+        'info_dict': {
+            'id': '123',
+            'title': '美国iTunes榜',
+            'description': 'md5:89db2335fdbb10678dee2d43fe9aba08',
+        },
+        'playlist_count': 100,
+    }, {
+        'url': 'https://y.qq.com/n/yqq/toplist/3.html',
+        'info_dict': {
+            'id': '3',
+            'title': '巅峰榜·欧美',
+            'description': 'md5:5a600d42c01696b26b71f8c4d43407da',
+        },
+        'playlist_count': 100,
+    }, {
+        'url': 'https://y.qq.com/n/yqq/toplist/106.html',
+        'info_dict': {
+            'id': '106',
+            'title': '韩国Mnet榜',
+            'description': 'md5:cb84b325215e1d21708c615cac82a6e7',
+        },
+        'playlist_count': 50,
+    }]
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+
+        toplist_json = self._download_json(
+            'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg', list_id,
+            note='Download toplist page',
+            query={'type': 'toplist', 'topid': list_id, 'format': 'json'})
+
+        entries = [self.url_result(
+            'https://y.qq.com/n/yqq/song/' + song['data']['songmid'] + '.html', 'QQMusic',
+            song['data']['songmid'])
+            for song in toplist_json['songlist']]
+
+        topinfo = toplist_json.get('topinfo', {})
+        list_name = topinfo.get('ListName')
+        list_description = topinfo.get('info')
+        return self.playlist_result(entries, list_id, list_name, list_description)
+
+
+class QQMusicPlaylistIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:playlist'
+    IE_DESC = 'QQ音乐 - 歌单'
+    _VALID_URL = r'https?://y\.qq\.com/n/yqq/playlist/(?P<id>[0-9]+)\.html'
+
+    _TESTS = [{
+        'url': 'http://y.qq.com/n/yqq/playlist/3462654915.html',
+        'info_dict': {
+            'id': '3462654915',
+            'title': '韩国5月新歌精选下旬',
+            'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4',
+        },
+        'playlist_count': 40,
+        'skip': 'playlist gone',
+    }, {
+        'url': 'https://y.qq.com/n/yqq/playlist/1374105607.html',
+        'info_dict': {
+            'id': '1374105607',
+            'title': '易入人心的华语民谣',
+            'description': '民谣的歌曲易于传唱、、歌词朗朗伤口、旋律简单温馨。属于那种才入耳孔。却上心头的感觉。没有太多的复杂情绪。简单而直接地表达乐者的情绪，就是这样的简单才易入人心。',
+        },
+        'playlist_count': 20,
+    }]
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+
+        list_json = self._download_json(
+            'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg',
+            list_id, 'Download list page',
+            query={'type': 1, 'json': 1, 'utf8': 1, 'onlysong': 0, 'disstid': list_id},
+            transform_source=strip_jsonp)
+        if not len(list_json.get('cdlist', [])):
+            if list_json.get('code'):
+                raise ExtractorError(
+                    'QQ Music said: error %d in fetching playlist info' % list_json['code'],
+                    expected=True)
+            raise ExtractorError('Unable to get playlist info')
+
+        cdlist = list_json['cdlist'][0]
+        entries = [self.url_result(
+            'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid'])
+            for song in cdlist['songlist']]
+
+        list_name = cdlist.get('dissname')
+        list_description = clean_html(unescapeHTML(cdlist.get('desc')))
+        return self.playlist_result(entries, list_id, list_name, list_description)

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/r7.py

@@ -0,0 +1,112 @@
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class R7IE(InfoExtractor):
+    _WORKING = False
+    _ENABLED = None  # XXX: pass through to GenericIE
+    _VALID_URL = r'''(?x)
+                        https?://
+                        (?:
+                            (?:[a-zA-Z]+)\.r7\.com(?:/[^/]+)+/idmedia/|
+                            noticias\.r7\.com(?:/[^/]+)+/[^/]+-|
+                            player\.r7\.com/video/i/
+                        )
+                        (?P<id>[\da-f]{24})
+                    '''
+    _TESTS = [{
+        'url': 'http://videos.r7.com/policiais-humilham-suspeito-a-beira-da-morte-morre-com-dignidade-/idmedia/54e7050b0cf2ff57e0279389.html',
+        'md5': '403c4e393617e8e8ddc748978ee8efde',
+        'info_dict': {
+            'id': '54e7050b0cf2ff57e0279389',
+            'ext': 'mp4',
+            'title': 'Policiais humilham suspeito à beira da morte: "Morre com dignidade"',
+            'description': 'md5:01812008664be76a6479aa58ec865b72',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 98,
+            'like_count': int,
+            'view_count': int,
+        },
+    }, {
+        'url': 'http://esportes.r7.com/videos/cigano-manda-recado-aos-fas/idmedia/4e176727b51a048ee6646a1b.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://noticias.r7.com/record-news/video/representante-do-instituto-sou-da-paz-fala-sobre-fim-do-estatuto-do-desarmamento-5480fc580cf2285b117f438d/',
+        'only_matching': True,
+    }, {
+        'url': 'http://player.r7.com/video/i/54e7050b0cf2ff57e0279389?play=true&video=http://vsh.r7.com/54e7050b0cf2ff57e0279389/ER7_RE_BG_MORTE_JOVENS_570kbps_2015-02-2009f17818-cc82-4c8f-86dc-89a66934e633-ATOS_copy.mp4&linkCallback=http://videos.r7.com/policiais-humilham-suspeito-a-beira-da-morte-morre-com-dignidade-/idmedia/54e7050b0cf2ff57e0279389.html&thumbnail=http://vtb.r7.com/ER7_RE_BG_MORTE_JOVENS_570kbps_2015-02-2009f17818-cc82-4c8f-86dc-89a66934e633-thumb.jpg&idCategory=192&share=true&layout=full&full=true',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            'http://player-api.r7.com/video/i/%s' % video_id, video_id)
+
+        title = video['title']
+
+        formats = []
+        media_url_hls = video.get('media_url_hls')
+        if media_url_hls:
+            formats.extend(self._extract_m3u8_formats(
+                media_url_hls, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+        media_url = video.get('media_url')
+        if media_url:
+            f = {
+                'url': media_url,
+                'format_id': 'http',
+            }
+            # m3u8 format always matches the http format, let's copy metadata from
+            # one to another
+            m3u8_formats = list(filter(
+                lambda f: f.get('vcodec') != 'none', formats))
+            if len(m3u8_formats) == 1:
+                f_copy = m3u8_formats[0].copy()
+                f_copy.update(f)
+                f_copy['protocol'] = 'http'
+                f = f_copy
+            formats.append(f)
+
+        description = video.get('description')
+        thumbnail = video.get('thumb')
+        duration = int_or_none(video.get('media_duration'))
+        like_count = int_or_none(video.get('likes'))
+        view_count = int_or_none(video.get('views'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'like_count': like_count,
+            'view_count': view_count,
+            'formats': formats,
+        }
+
+
+class R7ArticleIE(InfoExtractor):
+    _WORKING = False
+    _ENABLED = None  # XXX: pass through to GenericIE
+    _VALID_URL = r'https?://(?:[a-zA-Z]+)\.r7\.com/(?:[^/]+/)+[^/?#&]+-(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://tv.r7.com/record-play/balanco-geral/videos/policiais-humilham-suspeito-a-beira-da-morte-morre-com-dignidade-16102015',
+        'only_matching': True,
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return False if R7IE.suitable(url) else super(R7ArticleIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r'<div[^>]+(?:id=["\']player-|class=["\']embed["\'][^>]+id=["\'])([\da-f]{24})',
+            webpage, 'video id')
+
+        return self.url_result('http://player.r7.com/video/i/%s' % video_id, R7IE.ie_key())