@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/safari.py

@@ -0,0 +1,259 @@
+import json
+import re
+
+from .common import InfoExtractor
+
+from ..compat import (
+    compat_parse_qs,
+    compat_urlparse,
+)
+from ..utils import (
+    ExtractorError,
+    update_url_query,
+)
+
+
+class SafariBaseIE(InfoExtractor):
+    _LOGIN_URL = 'https://learning.oreilly.com/accounts/login/'
+    _NETRC_MACHINE = 'safari'
+
+    _API_BASE = 'https://learning.oreilly.com/api/v1'
+    _API_FORMAT = 'json'
+
+    LOGGED_IN = False
+
+    def _perform_login(self, username, password):
+        _, urlh = self._download_webpage_handle(
+            'https://learning.oreilly.com/accounts/login-check/', None,
+            'Downloading login page')
+
+        def is_logged(urlh):
+            return 'learning.oreilly.com/home/' in urlh.url
+
+        if is_logged(urlh):
+            self.LOGGED_IN = True
+            return
+
+        redirect_url = urlh.url
+        parsed_url = compat_urlparse.urlparse(redirect_url)
+        qs = compat_parse_qs(parsed_url.query)
+        next_uri = compat_urlparse.urljoin(
+            'https://api.oreilly.com', qs['next'][0])
+
+        auth, urlh = self._download_json_handle(
+            'https://www.oreilly.com/member/auth/login/', None, 'Logging in',
+            data=json.dumps({
+                'email': username,
+                'password': password,
+                'redirect_uri': next_uri,
+            }).encode(), headers={
+                'Content-Type': 'application/json',
+                'Referer': redirect_url,
+            }, expected_status=400)
+
+        credentials = auth.get('credentials')
+        if (not auth.get('logged_in') and not auth.get('redirect_uri')
+                and credentials):
+            raise ExtractorError(
+                'Unable to login: %s' % credentials, expected=True)
+
+        # oreilly serves two same instances of the following cookies
+        # in Set-Cookie header and expects first one to be actually set
+        for cookie in ('groot_sessionid', 'orm-jwt', 'orm-rt'):
+            self._apply_first_set_cookie_header(urlh, cookie)
+
+        _, urlh = self._download_webpage_handle(
+            auth.get('redirect_uri') or next_uri, None, 'Completing login',)
+
+        if is_logged(urlh):
+            self.LOGGED_IN = True
+            return
+
+        raise ExtractorError('Unable to log in')
+
+
+class SafariIE(SafariBaseIE):
+    IE_NAME = 'safari'
+    IE_DESC = 'safaribooksonline.com online video'
+    _VALID_URL = r'''(?x)
+                        https?://
+                            (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
+                            (?:
+                                library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?\#&]+)\.html|
+                                videos/[^/]+/[^/]+/(?P<reference_id>[^-]+-[^/?\#&]+)
+                            )
+                    '''
+
+    _TESTS = [{
+        'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
+        'md5': 'dcc5a425e79f2564148652616af1f2a3',
+        'info_dict': {
+            'id': '0_qbqx90ic',
+            'ext': 'mp4',
+            'title': 'Introduction to Hadoop Fundamentals LiveLessons',
+            'timestamp': 1437758058,
+            'upload_date': '20150724',
+            'uploader_id': 'stork',
+        },
+    }, {
+        # non-digits in course id
+        'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314/9780134217314-PYMC_13_00',
+        'only_matching': True,
+    }, {
+        'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838/9780133392838-00_SeriesIntro',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/00_SeriesIntro.html',
+        'only_matching': True,
+    }]
+
+    _PARTNER_ID = '1926081'
+    _UICONF_ID = '29375172'
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+
+        reference_id = mobj.group('reference_id')
+        if reference_id:
+            video_id = reference_id
+            partner_id = self._PARTNER_ID
+            ui_id = self._UICONF_ID
+        else:
+            video_id = '%s-%s' % (mobj.group('course_id'), mobj.group('part'))
+
+            webpage, urlh = self._download_webpage_handle(url, video_id)
+
+            mobj = re.match(self._VALID_URL, urlh.url)
+            reference_id = mobj.group('reference_id')
+            if not reference_id:
+                reference_id = self._search_regex(
+                    r'data-reference-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                    webpage, 'kaltura reference id', group='id')
+            partner_id = self._search_regex(
+                r'data-partner-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                webpage, 'kaltura widget id', default=self._PARTNER_ID,
+                group='id')
+            ui_id = self._search_regex(
+                r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                webpage, 'kaltura uiconf id', default=self._UICONF_ID,
+                group='id')
+
+        query = {
+            'wid': '_%s' % partner_id,
+            'uiconf_id': ui_id,
+            'flashvars[referenceId]': reference_id,
+        }
+
+        if self.LOGGED_IN:
+            kaltura_session = self._download_json(
+                '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id),
+                video_id, 'Downloading kaltura session JSON',
+                'Unable to download kaltura session JSON', fatal=False,
+                headers={'Accept': 'application/json'})
+            if kaltura_session:
+                session = kaltura_session.get('session')
+                if session:
+                    query['flashvars[ks]'] = session
+
+        return self.url_result(update_url_query(
+            'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query),
+            'Kaltura')
+
+
+class SafariApiIE(SafariBaseIE):
+    IE_NAME = 'safari:api'
+    _VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
+
+    _TESTS = [{
+        'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        part = self._download_json(
+            url, '%s/%s' % (mobj.group('course_id'), mobj.group('part')),
+            'Downloading part JSON')
+        web_url = part['web_url']
+        if 'library/view' in web_url:
+            web_url = web_url.replace('library/view', 'videos')
+            natural_keys = part['natural_key']
+            web_url = f'{web_url.rsplit("/", 1)[0]}/{natural_keys[0]}-{natural_keys[1][:-5]}'
+        return self.url_result(web_url, SafariIE.ie_key())
+
+
+class SafariCourseIE(SafariBaseIE):
+    IE_NAME = 'safari:course'
+    IE_DESC = 'safaribooksonline.com online courses'
+
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
+                            (?:
+                                library/view/[^/]+|
+                                api/v1/book|
+                                videos/[^/]+
+                            )|
+                            techbus\.safaribooksonline\.com
+                        )
+                        /(?P<id>[^/]+)
+                    '''
+
+    _TESTS = [{
+        'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
+        'info_dict': {
+            'id': '9780133392838',
+            'title': 'Hadoop Fundamentals LiveLessons',
+        },
+        'playlist_count': 22,
+        'skip': 'Requires safaribooksonline account credentials',
+    }, {
+        'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
+        'only_matching': True,
+    }, {
+        'url': 'http://techbus.safaribooksonline.com/9780134426365',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314',
+        'only_matching': True,
+    }, {
+        'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return (False if SafariIE.suitable(url) or SafariApiIE.suitable(url)
+                else super(SafariCourseIE, cls).suitable(url))
+
+    def _real_extract(self, url):
+        course_id = self._match_id(url)
+
+        course_json = self._download_json(
+            '%s/book/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
+            course_id, 'Downloading course JSON')
+
+        if 'chapters' not in course_json:
+            raise ExtractorError(
+                'No chapters found for course %s' % course_id, expected=True)
+
+        entries = [
+            self.url_result(chapter, SafariApiIE.ie_key())
+            for chapter in course_json['chapters']]
+
+        course_title = course_json['title']
+
+        return self.playlist_result(entries, course_id, course_title)

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

@@ -0,0 +1,75 @@
+from .common import InfoExtractor
+from ..utils import ExtractorError, try_get
+
+
+class SaitosanIE(InfoExtractor):
+    _WORKING = False
+    IE_NAME = 'Saitosan'
+    _VALID_URL = r'https?://(?:www\.)?saitosan\.net/bview.html\?id=(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.saitosan.net/bview.html?id=10031846',
+        'info_dict': {
+            'id': '10031846',
+            'ext': 'mp4',
+            'title': '井下原 和弥',
+            'uploader': '井下原 和弥',
+            'thumbnail': 'http://111.171.196.85:8088/921f916f-7f55-4c97-b92e-5d9d0fef8f5f/thumb',
+            'is_live': True,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'skip': 'Broadcasts are ephemeral',
+    },
+        {
+        'url': 'http://www.saitosan.net/bview.html?id=10031795',
+        'info_dict': {
+            'id': '10031795',
+            'ext': 'mp4',
+            'title': '橋本',
+            'uploader': '橋本',
+            'thumbnail': 'http://111.171.196.85:8088/1a3933e1-a01a-483b-8931-af15f37f8082/thumb',
+            'is_live': True,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'skip': 'Broadcasts are ephemeral',
+    }]
+
+    def _real_extract(self, url):
+        b_id = self._match_id(url)
+
+        base = 'http://hankachi.saitosan-api.net:8002/socket.io/?transport=polling&EIO=3'
+        sid = self._download_socket_json(base, b_id, note='Opening socket').get('sid')
+        base += '&sid=' + sid
+
+        self._download_webpage(base, b_id, note='Polling socket')
+        payload = '420["room_start_join",{"room_id":"%s"}]' % b_id
+        payload = '%s:%s' % (len(payload), payload)
+
+        self._download_webpage(base, b_id, data=payload, note='Polling socket with payload')
+        response = self._download_socket_json(base, b_id, note='Polling socket')
+        if not response.get('ok'):
+            err = response.get('error') or {}
+            raise ExtractorError(
+                '%s said: %s - %s' % (self.IE_NAME, err.get('code', '?'), err.get('msg', 'Unknown')) if err
+                else 'The socket reported that the broadcast could not be joined. Maybe it\'s offline or the URL is incorrect',
+                expected=True, video_id=b_id)
+
+        self._download_webpage(base, b_id, data='26:421["room_finish_join",{}]', note='Polling socket')
+        b_data = self._download_socket_json(base, b_id, note='Getting broadcast metadata from socket')
+        m3u8_url = b_data.get('url')
+
+        self._download_webpage(base, b_id, data='1:1', note='Closing socket', fatal=False)
+
+        return {
+            'id': b_id,
+            'title': b_data.get('name'),
+            'formats': self._extract_m3u8_formats(m3u8_url, b_id, 'mp4', live=True),
+            'thumbnail': m3u8_url.replace('av.m3u8', 'thumb'),
+            'uploader': try_get(b_data, lambda x: x['broadcast_user']['name']),  # same as title
+            'is_live': True
+        }

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

@@ -0,0 +1,97 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    extract_attributes,
+    get_element_by_attribute,
+    int_or_none,
+)
+
+
+class SampleFocusIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?samplefocus\.com/samples/(?P<id>[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://samplefocus.com/samples/lil-peep-sad-emo-guitar',
+        'md5': '48c8d62d60be467293912e0e619a5120',
+        'info_dict': {
+            'id': '40316',
+            'display_id': 'lil-peep-sad-emo-guitar',
+            'ext': 'mp3',
+            'title': 'Lil Peep Sad Emo Guitar',
+            'thumbnail': r're:^https?://.+\.png',
+            'license': 'Standard License',
+            'uploader': 'CapsCtrl',
+            'uploader_id': 'capsctrl',
+            'like_count': int,
+            'comment_count': int,
+            'categories': ['Samples', 'Guitar', 'Electric guitar'],
+        },
+    }, {
+        'url': 'https://samplefocus.com/samples/dababy-style-bass-808',
+        'only_matching': True
+    }, {
+        'url': 'https://samplefocus.com/samples/young-chop-kick',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        sample_id = self._search_regex(
+            r'<input[^>]+id=(["\'])sample_id\1[^>]+value=(?:["\'])(?P<id>\d+)',
+            webpage, 'sample id', group='id')
+
+        title = self._og_search_title(webpage, fatal=False) or self._html_search_regex(
+            r'<h1>(.+?)</h1>', webpage, 'title')
+
+        mp3_url = self._search_regex(
+            r'<input[^>]+id=(["\'])sample_mp3\1[^>]+value=(["\'])(?P<url>(?:(?!\2).)+)',
+            webpage, 'mp3', fatal=False, group='url') or extract_attributes(self._search_regex(
+                r'<meta[^>]+itemprop=(["\'])contentUrl\1[^>]*>',
+                webpage, 'mp3 url', group=0))['content']
+
+        thumbnail = self._og_search_thumbnail(webpage) or self._html_search_regex(
+            r'<img[^>]+class=(?:["\'])waveform responsive-img[^>]+src=(["\'])(?P<url>(?:(?!\1).)+)',
+            webpage, 'mp3', fatal=False, group='url')
+
+        comments = []
+        for author_id, author, body in re.findall(r'(?s)<p[^>]+class="comment-author"><a[^>]+href="/users/([^"]+)">([^"]+)</a>.+?<p[^>]+class="comment-body">([^>]+)</p>', webpage):
+            comments.append({
+                'author': author,
+                'author_id': author_id,
+                'text': body,
+            })
+
+        uploader_id = uploader = None
+        mobj = re.search(r'>By <a[^>]+href="/users/([^"]+)"[^>]*>([^<]+)', webpage)
+        if mobj:
+            uploader_id, uploader = mobj.groups()
+
+        breadcrumb = get_element_by_attribute('typeof', 'BreadcrumbList', webpage)
+        categories = []
+        if breadcrumb:
+            for _, name in re.findall(r'<span[^>]+property=(["\'])name\1[^>]*>([^<]+)', breadcrumb):
+                categories.append(name)
+
+        def extract_count(klass):
+            return int_or_none(self._html_search_regex(
+                r'<span[^>]+class=(?:["\'])?%s-count[^>]*>(\d+)' % klass,
+                webpage, klass, fatal=False))
+
+        return {
+            'id': sample_id,
+            'title': title,
+            'url': mp3_url,
+            'display_id': display_id,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'license': self._html_search_regex(
+                r'<a[^>]+href=(["\'])/license\1[^>]*>(?P<license>[^<]+)<',
+                webpage, 'license', fatal=False, group='license'),
+            'uploader_id': uploader_id,
+            'like_count': extract_count('sample-%s-favorites' % sample_id),
+            'comment_count': extract_count('comments'),
+            'comments': comments,
+            'categories': categories,
+        }

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

@@ -0,0 +1,114 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    unified_strdate,
+)
+
+
+class SapoIE(InfoExtractor):
+    IE_DESC = 'SAPO Vídeos'
+    _VALID_URL = r'https?://(?:(?:v2|www)\.)?videos\.sapo\.(?:pt|cv|ao|mz|tl)/(?P<id>[\da-zA-Z]{20})'
+
+    _TESTS = [
+        {
+            'url': 'http://videos.sapo.pt/UBz95kOtiWYUMTA5Ghfi',
+            'md5': '79ee523f6ecb9233ac25075dee0eda83',
+            'note': 'SD video',
+            'info_dict': {
+                'id': 'UBz95kOtiWYUMTA5Ghfi',
+                'ext': 'mp4',
+                'title': 'Benfica - Marcas na Hitória',
+                'description': 'md5:c9082000a128c3fd57bf0299e1367f22',
+                'duration': 264,
+                'uploader': 'tiago_1988',
+                'upload_date': '20080229',
+                'categories': ['benfica', 'cabral', 'desporto', 'futebol', 'geovanni', 'hooijdonk', 'joao', 'karel', 'lisboa', 'miccoli'],
+            },
+        },
+        {
+            'url': 'http://videos.sapo.pt/IyusNAZ791ZdoCY5H5IF',
+            'md5': '90a2f283cfb49193fe06e861613a72aa',
+            'note': 'HD video',
+            'info_dict': {
+                'id': 'IyusNAZ791ZdoCY5H5IF',
+                'ext': 'mp4',
+                'title': 'Codebits VII - Report',
+                'description': 'md5:6448d6fd81ce86feac05321f354dbdc8',
+                'duration': 144,
+                'uploader': 'codebits',
+                'upload_date': '20140427',
+                'categories': ['codebits', 'codebits2014'],
+            },
+        },
+        {
+            'url': 'http://v2.videos.sapo.pt/yLqjzPtbTimsn2wWBKHz',
+            'md5': 'e5aa7cc0bdc6db9b33df1a48e49a15ac',
+            'note': 'v2 video',
+            'info_dict': {
+                'id': 'yLqjzPtbTimsn2wWBKHz',
+                'ext': 'mp4',
+                'title': 'Hipnose Condicionativa 4',
+                'description': 'md5:ef0481abf8fb4ae6f525088a6dadbc40',
+                'duration': 692,
+                'uploader': 'sapozen',
+                'upload_date': '20090609',
+                'categories': ['condicionativa', 'heloisa', 'hipnose', 'miranda', 'sapo', 'zen'],
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        video_id = mobj.group('id')
+
+        item = self._download_xml(
+            'http://rd3.videos.sapo.pt/%s/rss2' % video_id, video_id).find('./channel/item')
+
+        title = item.find('./title').text
+        description = item.find('./{http://videos.sapo.pt/mrss/}synopse').text
+        thumbnail = item.find('./{http://search.yahoo.com/mrss/}content').get('url')
+        duration = parse_duration(item.find('./{http://videos.sapo.pt/mrss/}time').text)
+        uploader = item.find('./{http://videos.sapo.pt/mrss/}author').text
+        upload_date = unified_strdate(item.find('./pubDate').text)
+        view_count = int(item.find('./{http://videos.sapo.pt/mrss/}views').text)
+        comment_count = int(item.find('./{http://videos.sapo.pt/mrss/}comment_count').text)
+        tags = item.find('./{http://videos.sapo.pt/mrss/}tags').text
+        categories = tags.split() if tags else []
+        age_limit = 18 if item.find('./{http://videos.sapo.pt/mrss/}m18').text == 'true' else 0
+
+        video_url = item.find('./{http://videos.sapo.pt/mrss/}videoFile').text
+        video_size = item.find('./{http://videos.sapo.pt/mrss/}videoSize').text.split('x')
+
+        formats = [{
+            'url': video_url,
+            'ext': 'mp4',
+            'format_id': 'sd',
+            'width': int(video_size[0]),
+            'height': int(video_size[1]),
+        }]
+
+        if item.find('./{http://videos.sapo.pt/mrss/}HD').text == 'true':
+            formats.append({
+                'url': re.sub(r'/mov/1$', '/mov/39', video_url),
+                'ext': 'mp4',
+                'format_id': 'hd',
+                'width': 1280,
+                'height': 720,
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'uploader': uploader,
+            'upload_date': upload_date,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'categories': categories,
+            'age_limit': age_limit,
+            'formats': formats,
+        }