@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/owncloud.py

@@ -0,0 +1,80 @@
+import re
+import urllib.parse
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    determine_ext,
+    url_or_none,
+    urlencode_postdata,
+)
+
+
+class OwnCloudIE(InfoExtractor):
+    _INSTANCES_RE = '|'.join((
+        r'(?:[^\.]+\.)?sciebo\.de',
+        r'cloud\.uni-koblenz-landau\.de',
+    ))
+    _VALID_URL = rf'https?://(?:{_INSTANCES_RE})/s/(?P<id>[\w.-]+)'
+
+    _TESTS = [
+        {
+            'url': 'https://ruhr-uni-bochum.sciebo.de/s/wWhqZzh9jTumVFN',
+            'info_dict': {
+                'id': 'wWhqZzh9jTumVFN',
+                'ext': 'mp4',
+                'title': 'CmvpJST.mp4',
+            },
+        },
+        {
+            'url': 'https://ruhr-uni-bochum.sciebo.de/s/WNDuFu0XuFtmm3f',
+            'info_dict': {
+                'id': 'WNDuFu0XuFtmm3f',
+                'ext': 'mp4',
+                'title': 'CmvpJST.mp4',
+            },
+            'params': {
+                'videopassword': '12345',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage, urlh = self._download_webpage_handle(url, video_id)
+
+        if re.search(r'<label[^>]+for="password"', webpage):
+            webpage = self._verify_video_password(webpage, urlh.url, video_id)
+
+        hidden_inputs = self._hidden_inputs(webpage)
+        title = hidden_inputs.get('filename')
+        parsed_url = urllib.parse.urlparse(url)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': url_or_none(hidden_inputs.get('downloadURL')) or parsed_url._replace(
+                path=urllib.parse.urljoin(parsed_url.path, 'download')).geturl(),
+            'ext': determine_ext(title),
+        }
+
+    def _verify_video_password(self, webpage, url, video_id):
+        password = self.get_param('videopassword')
+        if password is None:
+            raise ExtractorError(
+                'This video is protected by a password, use the --video-password option',
+                expected=True)
+
+        validation_response = self._download_webpage(
+            url, video_id, 'Validating Password', 'Wrong password?',
+            data=urlencode_postdata({
+                'requesttoken': self._hidden_inputs(webpage)['requesttoken'],
+                'password': password,
+            }))
+
+        if re.search(r'<label[^>]+for="password"', validation_response):
+            warning = self._search_regex(
+                r'<div[^>]+class="warning">([^<]*)</div>', validation_response,
+                'warning', default='The password is wrong')
+            raise ExtractorError(f'Opening the video failed, {self.IE_NAME} said: {warning!r}', expected=True)
+        return validation_response

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

@@ -0,0 +1,155 @@
+import json
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    # remove_end,
+    str_or_none,
+    strip_or_none,
+    unified_timestamp,
+    # urljoin,
+)
+
+
+class PacktPubBaseIE(InfoExtractor):
+    # _PACKT_BASE = 'https://www.packtpub.com'
+    _STATIC_PRODUCTS_BASE = 'https://static.packt-cdn.com/products/'
+
+
+class PacktPubIE(PacktPubBaseIE):
+    _VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>[^/]+)/(?P<id>[^/]+)(?:/(?P<display_id>[^/?&#]+))?'
+
+    _TESTS = [{
+        'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro',
+        'md5': '1e74bd6cfd45d7d07666f4684ef58f70',
+        'info_dict': {
+            'id': '20530',
+            'ext': 'mp4',
+            'title': 'Project Intro',
+            'thumbnail': r're:(?i)^https?://.*\.jpg',
+            'timestamp': 1490918400,
+            'upload_date': '20170331',
+        },
+    }, {
+        'url': 'https://subscription.packtpub.com/video/web_development/9781787122215/20528/20530/project-intro',
+        'only_matching': True,
+    }, {
+        'url': 'https://subscription.packtpub.com/video/programming/9781838988906/p1/video1_1/business-card-project',
+        'only_matching': True,
+    }]
+    _NETRC_MACHINE = 'packtpub'
+    _TOKEN = None
+
+    def _perform_login(self, username, password):
+        try:
+            self._TOKEN = self._download_json(
+                'https://services.packtpub.com/auth-v1/users/tokens', None,
+                'Downloading Authorization Token', data=json.dumps({
+                    'username': username,
+                    'password': password,
+                }).encode())['data']['access']
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status in (400, 401, 404):
+                message = self._parse_json(e.cause.response.read().decode(), None)['message']
+                raise ExtractorError(message, expected=True)
+            raise
+
+    def _real_extract(self, url):
+        course_id, chapter_id, video_id, display_id = self._match_valid_url(url).groups()
+
+        headers = {}
+        if self._TOKEN:
+            headers['Authorization'] = 'Bearer ' + self._TOKEN
+        try:
+            video_url = self._download_json(
+                'https://services.packtpub.com/products-v1/products/%s/%s/%s' % (course_id, chapter_id, video_id), video_id,
+                'Downloading JSON video', headers=headers)['data']
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 400:
+                self.raise_login_required('This video is locked')
+            raise
+
+        # TODO: find a better way to avoid duplicating course requests
+        # metadata = self._download_json(
+        #     '%s/products/%s/chapters/%s/sections/%s/metadata'
+        #     % (self._MAPT_REST, course_id, chapter_id, video_id),
+        #     video_id)['data']
+
+        # title = metadata['pageTitle']
+        # course_title = metadata.get('title')
+        # if course_title:
+        #     title = remove_end(title, ' - %s' % course_title)
+        # timestamp = unified_timestamp(metadata.get('publicationDate'))
+        # thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath'))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': display_id or video_id,  # title,
+            # 'thumbnail': thumbnail,
+            # 'timestamp': timestamp,
+        }
+
+
+class PacktPubCourseIE(PacktPubBaseIE):
+    _VALID_URL = r'(?P<url>https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P<id>\d+))'
+    _TESTS = [{
+        'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215',
+        'info_dict': {
+            'id': '9781787122215',
+            'title': 'Learn Nodejs by building 12 projects [Video]',
+            'description': 'md5:489da8d953f416e51927b60a1c7db0aa',
+        },
+        'playlist_count': 90,
+    }, {
+        'url': 'https://subscription.packtpub.com/video/web_development/9781787122215',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if PacktPubIE.suitable(url) else super(
+            PacktPubCourseIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        url, course_id = mobj.group('url', 'id')
+
+        course = self._download_json(
+            self._STATIC_PRODUCTS_BASE + '%s/toc' % course_id, course_id)
+        metadata = self._download_json(
+            self._STATIC_PRODUCTS_BASE + '%s/summary' % course_id,
+            course_id, fatal=False) or {}
+
+        entries = []
+        for chapter_num, chapter in enumerate(course['chapters'], 1):
+            chapter_id = str_or_none(chapter.get('id'))
+            sections = chapter.get('sections')
+            if not chapter_id or not isinstance(sections, list):
+                continue
+            chapter_info = {
+                'chapter': chapter.get('title'),
+                'chapter_number': chapter_num,
+                'chapter_id': chapter_id,
+            }
+            for section in sections:
+                section_id = str_or_none(section.get('id'))
+                if not section_id or section.get('contentType') != 'video':
+                    continue
+                entry = {
+                    '_type': 'url_transparent',
+                    'url': '/'.join([url, chapter_id, section_id]),
+                    'title': strip_or_none(section.get('title')),
+                    'description': clean_html(section.get('summary')),
+                    'thumbnail': metadata.get('coverImage'),
+                    'timestamp': unified_timestamp(metadata.get('publicationDate')),
+                    'ie_key': PacktPubIE.ie_key(),
+                }
+                entry.update(chapter_info)
+                entries.append(entry)
+
+        return self.playlist_result(
+            entries, course_id, metadata.get('title'),
+            clean_html(metadata.get('about')))

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/palcomp3.py

@@ -0,0 +1,143 @@
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    str_or_none,
+    try_get,
+)
+
+
+class PalcoMP3BaseIE(InfoExtractor):
+    _GQL_QUERY_TMPL = '''{
+  artist(slug: "%s") {
+    %s
+  }
+}'''
+    _ARTIST_FIELDS_TMPL = '''music(slug: "%%s") {
+      %s
+    }'''
+    _MUSIC_FIELDS = '''duration
+      hls
+      mp3File
+      musicID
+      plays
+      title'''
+
+    def _call_api(self, artist_slug, artist_fields):
+        return self._download_json(
+            'https://www.palcomp3.com.br/graphql/', artist_slug, query={
+                'query': self._GQL_QUERY_TMPL % (artist_slug, artist_fields),
+            })['data']
+
+    def _parse_music(self, music):
+        music_id = compat_str(music['musicID'])
+        title = music['title']
+
+        formats = []
+        hls_url = music.get('hls')
+        if hls_url:
+            formats.append({
+                'url': hls_url,
+                'protocol': 'm3u8_native',
+                'ext': 'mp4',
+            })
+        mp3_file = music.get('mp3File')
+        if mp3_file:
+            formats.append({
+                'url': mp3_file,
+            })
+
+        return {
+            'id': music_id,
+            'title': title,
+            'formats': formats,
+            'duration': int_or_none(music.get('duration')),
+            'view_count': int_or_none(music.get('plays')),
+        }
+
+    def _real_initialize(self):
+        self._ARTIST_FIELDS_TMPL = self._ARTIST_FIELDS_TMPL % self._MUSIC_FIELDS
+
+    def _real_extract(self, url):
+        artist_slug, music_slug = self._match_valid_url(url).groups()
+        artist_fields = self._ARTIST_FIELDS_TMPL % music_slug
+        music = self._call_api(artist_slug, artist_fields)['artist']['music']
+        return self._parse_music(music)
+
+
+class PalcoMP3IE(PalcoMP3BaseIE):
+    IE_NAME = 'PalcoMP3:song'
+    _VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P<artist>[^/]+)/(?P<id>[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/nossas-composicoes-cuida-bem-dela/',
+        'md5': '99fd6405b2d8fd589670f6db1ba3b358',
+        'info_dict': {
+            'id': '3162927',
+            'ext': 'mp3',
+            'title': 'Nossas Composições - CUIDA BEM DELA',
+            'duration': 210,
+            'view_count': int,
+        }
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if PalcoMP3VideoIE.suitable(url) else super(PalcoMP3IE, cls).suitable(url)
+
+
+class PalcoMP3ArtistIE(PalcoMP3BaseIE):
+    IE_NAME = 'PalcoMP3:artist'
+    _VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P<id>[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://www.palcomp3.com.br/condedoforro/',
+        'info_dict': {
+            'id': '358396',
+            'title': 'Conde do Forró',
+        },
+        'playlist_mincount': 188,
+    }]
+    _ARTIST_FIELDS_TMPL = '''artistID
+    musics {
+      nodes {
+        %s
+      }
+    }
+    name'''
+
+    @classmethod
+    def suitable(cls, url):
+        return False if PalcoMP3IE._match_valid_url(url) else super(PalcoMP3ArtistIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        artist_slug = self._match_id(url)
+        artist = self._call_api(artist_slug, self._ARTIST_FIELDS_TMPL)['artist']
+
+        def entries():
+            for music in (try_get(artist, lambda x: x['musics']['nodes'], list) or []):
+                yield self._parse_music(music)
+
+        return self.playlist_result(
+            entries(), str_or_none(artist.get('artistID')), artist.get('name'))
+
+
+class PalcoMP3VideoIE(PalcoMP3BaseIE):
+    IE_NAME = 'PalcoMP3:video'
+    _VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P<artist>[^/]+)/(?P<id>[^/?&#]+)/?#clipe'
+    _TESTS = [{
+        'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/maiara-e-maraisa-voce-faz-falta-aqui-ao-vivo-em-vicosa-mg/#clipe',
+        'add_ie': ['Youtube'],
+        'info_dict': {
+            'id': '_pD1nR2qqPg',
+            'ext': 'mp4',
+            'title': 'Maiara e Maraisa - Você Faz Falta Aqui - DVD Ao Vivo Em Campo Grande',
+            'description': 'md5:7043342c09a224598e93546e98e49282',
+            'upload_date': '20161107',
+            'uploader_id': 'maiaramaraisaoficial',
+            'uploader': 'Maiara e Maraisa',
+        }
+    }]
+    _MUSIC_FIELDS = 'youtubeID'
+
+    def _parse_music(self, music):
+        youtube_id = music['youtubeID']
+        return self.url_result(youtube_id, 'Youtube', youtube_id)