@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/webofstories.py

@@ -0,0 +1,155 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    orderedSet,
+)
+
+
+class WebOfStoriesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?webofstories\.com/play/(?:[^/]+/)?(?P<id>[0-9]+)'
+    _VIDEO_DOMAIN = 'http://eu-mobile.webofstories.com/'
+    _GREAT_LIFE_STREAMER = 'rtmp://eu-cdn1.webofstories.com/cfx/st/'
+    _USER_STREAMER = 'rtmp://eu-users.webofstories.com/cfx/st/'
+    _TESTS = [{
+        'url': 'http://www.webofstories.com/play/hans.bethe/71',
+        'md5': '373e4dd915f60cfe3116322642ddf364',
+        'info_dict': {
+            'id': '4536',
+            'ext': 'mp4',
+            'title': 'The temperature of the sun',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'Hans Bethe talks about calculating the temperature of the sun',
+            'duration': 238,
+        }
+    }, {
+        'url': 'http://www.webofstories.com/play/55908',
+        'md5': '2985a698e1fe3211022422c4b5ed962c',
+        'info_dict': {
+            'id': '55908',
+            'ext': 'mp4',
+            'title': 'The story of Gemmata obscuriglobus',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'Planctomycete talks about The story of Gemmata obscuriglobus',
+            'duration': 169,
+        },
+        'skip': 'notfound',
+    }, {
+        # malformed og:title meta
+        'url': 'http://www.webofstories.com/play/54215?o=MS',
+        'info_dict': {
+            'id': '54215',
+            'ext': 'mp4',
+            'title': '"A Leg to Stand On"',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'Oliver Sacks talks about the death and resurrection of a limb',
+            'duration': 97,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        # Sometimes og:title meta is malformed
+        title = self._og_search_title(webpage, default=None) or self._html_search_regex(
+            r'(?s)<strong>Title:\s*</strong>(.+?)<', webpage, 'title')
+        description = self._html_search_meta('description', webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        embed_params = [s.strip(" \r\n\t'") for s in self._search_regex(
+            r'(?s)\$\("#embedCode"\).html\(getEmbedCode\((.*?)\)',
+            webpage, 'embed params').split(',')]
+
+        (
+            _, speaker_id, story_id, story_duration,
+            speaker_type, great_life, _thumbnail, _has_subtitles,
+            story_filename, _story_order) = embed_params
+
+        is_great_life_series = great_life == 'true'
+        duration = int_or_none(story_duration)
+
+        # URL building, see: http://www.webofstories.com/scripts/player.js
+        ms_prefix = ''
+        if speaker_type.lower() == 'ms':
+            ms_prefix = 'mini_sites/'
+
+        if is_great_life_series:
+            mp4_url = '{0:}lives/{1:}/{2:}.mp4'.format(
+                self._VIDEO_DOMAIN, speaker_id, story_filename)
+            rtmp_ext = 'flv'
+            streamer = self._GREAT_LIFE_STREAMER
+            play_path = 'stories/{0:}/{1:}'.format(
+                speaker_id, story_filename)
+        else:
+            mp4_url = '{0:}{1:}{2:}/{3:}.mp4'.format(
+                self._VIDEO_DOMAIN, ms_prefix, speaker_id, story_filename)
+            rtmp_ext = 'mp4'
+            streamer = self._USER_STREAMER
+            play_path = 'mp4:{0:}{1:}/{2}.mp4'.format(
+                ms_prefix, speaker_id, story_filename)
+
+        formats = [{
+            'format_id': 'mp4_sd',
+            'url': mp4_url,
+        }, {
+            'format_id': 'rtmp_sd',
+            'page_url': url,
+            'url': streamer,
+            'ext': rtmp_ext,
+            'play_path': play_path,
+        }]
+
+        return {
+            'id': story_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'description': description,
+            'duration': duration,
+        }
+
+
+class WebOfStoriesPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?webofstories\.com/playAll/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://www.webofstories.com/playAll/donald.knuth',
+        'info_dict': {
+            'id': 'donald.knuth',
+            'title': 'Donald Knuth (Scientist)',
+        },
+        'playlist_mincount': 97,
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [
+            self.url_result(
+                'http://www.webofstories.com/play/%s' % video_id,
+                'WebOfStories', video_id=video_id)
+            for video_id in orderedSet(re.findall(r'\bid=["\']td_(\d+)', webpage))
+        ]
+
+        title = self._search_regex(
+            r'<div id="speakerName">\s*<span>([^<]+)</span>',
+            webpage, 'speaker', default=None)
+        if title:
+            field = self._search_regex(
+                r'<span id="primaryField">([^<]+)</span>',
+                webpage, 'field', default=None)
+            if field:
+                title += ' (%s)' % field
+
+        if not title:
+            title = self._search_regex(
+                r'<title>Play\s+all\s+stories\s*-\s*([^<]+)\s*-\s*Web\s+of\s+Stories</title>',
+                webpage, 'title')
+
+        return self.playlist_result(entries, playlist_id, title)

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

@@ -0,0 +1,251 @@
+import json
+import random
+import itertools
+import urllib.parse
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    make_archive_id,
+    mimetype2ext,
+    parse_resolution,
+    str_or_none,
+    strip_jsonp,
+    traverse_obj,
+    url_or_none,
+    urlencode_postdata,
+    urljoin,
+)
+
+
+class WeiboBaseIE(InfoExtractor):
+    def _update_visitor_cookies(self, visitor_url, video_id):
+        headers = {'Referer': visitor_url}
+        chrome_ver = self._search_regex(
+            r'Chrome/(\d+)', self.get_param('http_headers')['User-Agent'], 'user agent version', default='90')
+        visitor_data = self._download_json(
+            'https://passport.weibo.com/visitor/genvisitor', video_id,
+            note='Generating first-visit guest request',
+            headers=headers, transform_source=strip_jsonp,
+            data=urlencode_postdata({
+                'cb': 'gen_callback',
+                'fp': json.dumps({
+                    'os': '1',
+                    'browser': f'Chrome{chrome_ver},0,0,0',
+                    'fonts': 'undefined',
+                    'screenInfo': '1920*1080*24',
+                    'plugins': ''
+                }, separators=(',', ':'))}))['data']
+
+        self._download_webpage(
+            'https://passport.weibo.com/visitor/visitor', video_id,
+            note='Running first-visit callback to get guest cookies',
+            headers=headers, query={
+                'a': 'incarnate',
+                't': visitor_data['tid'],
+                'w': 3 if visitor_data.get('new_tid') else 2,
+                'c': f'{visitor_data.get("confidence", 100):03d}',
+                'gc': '',
+                'cb': 'cross_domain',
+                'from': 'weibo',
+                '_rand': random.random(),
+            })
+
+    def _weibo_download_json(self, url, video_id, *args, fatal=True, note='Downloading JSON metadata', **kwargs):
+        webpage, urlh = self._download_webpage_handle(url, video_id, *args, fatal=fatal, note=note, **kwargs)
+        if urllib.parse.urlparse(urlh.url).netloc == 'passport.weibo.com':
+            self._update_visitor_cookies(urlh.url, video_id)
+            webpage = self._download_webpage(url, video_id, *args, fatal=fatal, note=note, **kwargs)
+        return self._parse_json(webpage, video_id, fatal=fatal)
+
+    def _extract_formats(self, video_info):
+        media_info = traverse_obj(video_info, ('page_info', 'media_info'))
+        formats = traverse_obj(media_info, (
+            'playback_list', lambda _, v: url_or_none(v['play_info']['url']), 'play_info', {
+                'url': 'url',
+                'format': ('quality_desc', {str}),
+                'format_id': ('label', {str}),
+                'ext': ('mime', {mimetype2ext}),
+                'tbr': ('bitrate', {int_or_none}, {lambda x: x or None}),
+                'vcodec': ('video_codecs', {str}),
+                'fps': ('fps', {int_or_none}),
+                'width': ('width', {int_or_none}),
+                'height': ('height', {int_or_none}),
+                'filesize': ('size', {int_or_none}),
+                'acodec': ('audio_codecs', {str}),
+                'asr': ('audio_sample_rate', {int_or_none}),
+                'audio_channels': ('audio_channels', {int_or_none}),
+            }))
+        if not formats:  # fallback, should be barely used
+            for url in set(traverse_obj(media_info, (..., {url_or_none}))):
+                if 'label=' in url:  # filter out non-video urls
+                    format_id, resolution = self._search_regex(
+                        r'label=(\w+)&template=(\d+x\d+)', url, 'format info',
+                        group=(1, 2), default=(None, None))
+                    formats.append({
+                        'url': url,
+                        'format_id': format_id,
+                        **parse_resolution(resolution),
+                        **traverse_obj(media_info, (
+                            'video_details', lambda _, v: v['label'].startswith(format_id), {
+                                'size': ('size', {int_or_none}),
+                                'tbr': ('bitrate', {int_or_none}),
+                            }
+                        ), get_all=False),
+                    })
+        return formats
+
+    def _parse_video_info(self, video_info, video_id=None):
+        return {
+            'id': video_id,
+            'extractor_key': WeiboIE.ie_key(),
+            'extractor': WeiboIE.IE_NAME,
+            'formats': self._extract_formats(video_info),
+            'http_headers': {'Referer': 'https://weibo.com/'},
+            '_old_archive_ids': [make_archive_id('WeiboMobile', video_id)],
+            **traverse_obj(video_info, {
+                'id': (('id', 'id_str', 'mid'), {str_or_none}),
+                'display_id': ('mblogid', {str_or_none}),
+                'title': ('page_info', 'media_info', ('video_title', 'kol_title', 'name'), {str}, {lambda x: x or None}),
+                'description': ('text_raw', {str}),
+                'duration': ('page_info', 'media_info', 'duration', {int_or_none}),
+                'timestamp': ('page_info', 'media_info', 'video_publish_time', {int_or_none}),
+                'thumbnail': ('page_info', 'page_pic', {url_or_none}),
+                'uploader': ('user', 'screen_name', {str}),
+                'uploader_id': ('user', ('id', 'id_str'), {str_or_none}),
+                'uploader_url': ('user', 'profile_url', {lambda x: urljoin('https://weibo.com/', x)}),
+                'view_count': ('page_info', 'media_info', 'online_users_number', {int_or_none}),
+                'like_count': ('attitudes_count', {int_or_none}),
+                'repost_count': ('reposts_count', {int_or_none}),
+            }, get_all=False),
+            'tags': traverse_obj(video_info, ('topic_struct', ..., 'topic_title', {str})) or None,
+        }
+
+
+class WeiboIE(WeiboBaseIE):
+    _VALID_URL = r'https?://(?:m\.weibo\.cn/status|(?:www\.)?weibo\.com/\d+)/(?P<id>[a-zA-Z0-9]+)'
+    _TESTS = [{
+        'url': 'https://weibo.com/7827771738/N4xlMvjhI',
+        'info_dict': {
+            'id': '4910815147462302',
+            'ext': 'mp4',
+            'display_id': 'N4xlMvjhI',
+            'title': '【睡前消息暑假版第一期：拉泰国一把  对中国有好处】',
+            'description': 'md5:e2637a7673980d68694ea7c43cf12a5f',
+            'duration': 918,
+            'timestamp': 1686312819,
+            'upload_date': '20230609',
+            'thumbnail': r're:https://.*\.jpg',
+            'uploader': '睡前视频基地',
+            'uploader_id': '7827771738',
+            'uploader_url': 'https://weibo.com/u/7827771738',
+            'view_count': int,
+            'like_count': int,
+            'repost_count': int,
+            'tags': ['泰国大选远进党获胜', '睡前消息', '暑期版'],
+        },
+    }, {
+        'url': 'https://m.weibo.cn/status/4189191225395228',
+        'info_dict': {
+            'id': '4189191225395228',
+            'ext': 'mp4',
+            'display_id': 'FBqgOmDxO',
+            'title': '柴犬柴犬的秒拍视频',
+            'description': 'md5:80f461ab5cdae6bbdb70efbf5a1db24f',
+            'duration': 53,
+            'timestamp': 1514264429,
+            'upload_date': '20171226',
+            'thumbnail': r're:https://.*\.jpg',
+            'uploader': '柴犬柴犬',
+            'uploader_id': '5926682210',
+            'uploader_url': 'https://weibo.com/u/5926682210',
+            'view_count': int,
+            'like_count': int,
+            'repost_count': int,
+        }
+    }, {
+        'url': 'https://weibo.com/0/4224132150961381',
+        'note': 'no playback_list example',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        return self._parse_video_info(self._weibo_download_json(
+            f'https://weibo.com/ajax/statuses/show?id={video_id}', video_id))
+
+
+class WeiboVideoIE(WeiboBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?weibo\.com/tv/show/(?P<id>\d+:\d+)'
+    _TESTS = [{
+        'url': 'https://weibo.com/tv/show/1034:4797699866951785?from=old_pc_videoshow',
+        'info_dict': {
+            'id': '4797700463137878',
+            'ext': 'mp4',
+            'display_id': 'LEZDodaiW',
+            'title': '呃，稍微了解了一下靡烟miya，感觉这东西也太二了',
+            'description': '呃，稍微了解了一下靡烟miya，感觉这东西也太二了 http://t.cn/A6aerGsM ​​​',
+            'duration': 76,
+            'timestamp': 1659344278,
+            'upload_date': '20220801',
+            'thumbnail': r're:https://.*\.jpg',
+            'uploader': '君子爱财陈平安',
+            'uploader_id': '3905382233',
+            'uploader_url': 'https://weibo.com/u/3905382233',
+            'view_count': int,
+            'like_count': int,
+            'repost_count': int,
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        post_data = f'data={{"Component_Play_Playinfo":{{"oid":"{video_id}"}}}}'.encode()
+        video_info = self._weibo_download_json(
+            f'https://weibo.com/tv/api/component?page=%2Ftv%2Fshow%2F{video_id.replace(":", "%3A")}',
+            video_id, headers={'Referer': url}, data=post_data)['data']['Component_Play_Playinfo']
+        return self.url_result(f'https://weibo.com/0/{video_info["mid"]}', WeiboIE)
+
+
+class WeiboUserIE(WeiboBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?weibo\.com/u/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://weibo.com/u/2066652961?tabtype=video',
+        'info_dict': {
+            'id': '2066652961',
+            'title': '萧影殿下的视频',
+            'description': '萧影殿下的全部视频',
+            'uploader': '萧影殿下',
+        },
+        'playlist_mincount': 195,
+    }]
+
+    def _fetch_page(self, uid, cursor=0, page=1):
+        return self._weibo_download_json(
+            'https://weibo.com/ajax/profile/getWaterFallContent',
+            uid, note=f'Downloading videos page {page}',
+            query={'uid': uid, 'cursor': cursor})['data']
+
+    def _entries(self, uid, first_page):
+        cursor = 0
+        for page in itertools.count(1):
+            response = first_page if page == 1 else self._fetch_page(uid, cursor, page)
+            for video_info in traverse_obj(response, ('list', ..., {dict})):
+                yield self._parse_video_info(video_info)
+            cursor = response.get('next_cursor')
+            if (int_or_none(cursor) or -1) < 0:
+                break
+
+    def _real_extract(self, url):
+        uid = self._match_id(url)
+        first_page = self._fetch_page(uid)
+        uploader = traverse_obj(first_page, ('list', ..., 'user', 'screen_name', {str}), get_all=False)
+        metainfo = {
+            'title': f'{uploader}的视频',
+            'description': f'{uploader}的全部视频',
+            'uploader': uploader,
+        } if uploader else {}
+
+        return self.playlist_result(self._entries(uid, first_page), uid, **metainfo)

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

@@ -0,0 +1,50 @@
+from .common import InfoExtractor
+
+
+class WeiqiTVIE(InfoExtractor):
+    _WORKING = False
+    IE_DESC = 'WQTV'
+    _VALID_URL = r'https?://(?:www\.)?weiqitv\.com/index/video_play\?videoId=(?P<id>[A-Za-z0-9]+)'
+
+    _TESTS = [{
+        'url': 'http://www.weiqitv.com/index/video_play?videoId=53c744f09874f0e76a8b46f3',
+        'md5': '26450599afd64c513bc77030ad15db44',
+        'info_dict': {
+            'id': '53c744f09874f0e76a8b46f3',
+            'ext': 'mp4',
+            'title': '2013年度盘点',
+        },
+    }, {
+        'url': 'http://www.weiqitv.com/index/video_play?videoId=567379a2d4c36cca518b4569',
+        'info_dict': {
+            'id': '567379a2d4c36cca518b4569',
+            'ext': 'mp4',
+            'title': '民国围棋史',
+        },
+    }, {
+        'url': 'http://www.weiqitv.com/index/video_play?videoId=5430220a9874f088658b4567',
+        'info_dict': {
+            'id': '5430220a9874f088658b4567',
+            'ext': 'mp4',
+            'title': '二路托过的手段和运用',
+        },
+    }]
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+        page = self._download_webpage(url, media_id)
+
+        info_json_str = self._search_regex(
+            r'var\s+video\s*=\s*(.+});', page, 'info json str')
+        info_json = self._parse_json(info_json_str, media_id)
+
+        letvcloud_url = self._search_regex(
+            r'var\s+letvurl\s*=\s*"([^"]+)', page, 'letvcloud url')
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'LetvCloud',
+            'url': letvcloud_url,
+            'title': info_json['name'],
+            'id': media_id,
+        }