@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/lifenews.py

@@ -0,0 +1,234 @@
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    int_or_none,
+    parse_iso8601,
+    remove_end,
+)
+
+
+class LifeNewsIE(InfoExtractor):
+    IE_NAME = 'life'
+    IE_DESC = 'Life.ru'
+    _VALID_URL = r'https?://life\.ru/t/[^/]+/(?P<id>\d+)'
+
+    _TESTS = [{
+        # single video embedded via video/source
+        'url': 'https://life.ru/t/новости/98736',
+        'md5': '77c95eaefaca216e32a76a343ad89d23',
+        'info_dict': {
+            'id': '98736',
+            'ext': 'mp4',
+            'title': 'Мужчина нашел дома архив оборонного завода',
+            'description': 'md5:3b06b1b39b5e2bea548e403d99b8bf26',
+            'timestamp': 1344154740,
+            'upload_date': '20120805',
+            'view_count': int,
+        }
+    }, {
+        # single video embedded via iframe
+        'url': 'https://life.ru/t/новости/152125',
+        'md5': '77d19a6f0886cd76bdbf44b4d971a273',
+        'info_dict': {
+            'id': '152125',
+            'ext': 'mp4',
+            'title': 'В Сети появилось видео захвата «Правым сектором» колхозных полей ',
+            'description': 'Жители двух поселков Днепропетровской области не простили радикалам угрозу лишения плодородных земель и пошли в лобовую. ',
+            'timestamp': 1427961840,
+            'upload_date': '20150402',
+            'view_count': int,
+        }
+    }, {
+        # two videos embedded via iframe
+        'url': 'https://life.ru/t/новости/153461',
+        'info_dict': {
+            'id': '153461',
+            'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве',
+            'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.',
+            'timestamp': 1430825520,
+            'view_count': int,
+        },
+        'playlist': [{
+            'md5': '9b6ef8bc0ffa25aebc8bdb40d89ab795',
+            'info_dict': {
+                'id': '153461-video1',
+                'ext': 'mp4',
+                'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве (Видео 1)',
+                'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.',
+                'timestamp': 1430825520,
+                'upload_date': '20150505',
+            },
+        }, {
+            'md5': 'ebb3bf3b1ce40e878d0d628e93eb0322',
+            'info_dict': {
+                'id': '153461-video2',
+                'ext': 'mp4',
+                'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве (Видео 2)',
+                'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.',
+                'timestamp': 1430825520,
+                'upload_date': '20150505',
+            },
+        }],
+    }, {
+        'url': 'https://life.ru/t/новости/213035',
+        'only_matching': True,
+    }, {
+        'url': 'https://life.ru/t/%D0%BD%D0%BE%D0%B2%D0%BE%D1%81%D1%82%D0%B8/153461',
+        'only_matching': True,
+    }, {
+        'url': 'https://life.ru/t/новости/411489/manuel_vals_nazval_frantsiiu_tsieliu_nomier_odin_dlia_ighil',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_urls = re.findall(
+            r'<video[^>]+><source[^>]+src=["\'](.+?)["\']', webpage)
+
+        iframe_links = re.findall(
+            r'<iframe[^>]+src=["\']((?:https?:)?//embed\.life\.ru/(?:embed|video)/.+?)["\']',
+            webpage)
+
+        if not video_urls and not iframe_links:
+            raise ExtractorError('No media links available for %s' % video_id)
+
+        title = remove_end(
+            self._og_search_title(webpage),
+            ' - Life.ru')
+
+        description = self._og_search_description(webpage)
+
+        view_count = self._html_search_regex(
+            r'<div[^>]+class=(["\']).*?\bhits-count\b.*?\1[^>]*>\s*(?P<value>\d+)\s*</div>',
+            webpage, 'view count', fatal=False, group='value')
+
+        timestamp = parse_iso8601(self._search_regex(
+            r'<time[^>]+datetime=(["\'])(?P<value>.+?)\1',
+            webpage, 'upload date', fatal=False, group='value'))
+
+        common_info = {
+            'description': description,
+            'view_count': int_or_none(view_count),
+            'timestamp': timestamp,
+        }
+
+        def make_entry(video_id, video_url, index=None):
+            cur_info = dict(common_info)
+            cur_info.update({
+                'id': video_id if not index else '%s-video%s' % (video_id, index),
+                'url': video_url,
+                'title': title if not index else '%s (Видео %s)' % (title, index),
+            })
+            return cur_info
+
+        def make_video_entry(video_id, video_url, index=None):
+            video_url = compat_urlparse.urljoin(url, video_url)
+            return make_entry(video_id, video_url, index)
+
+        def make_iframe_entry(video_id, video_url, index=None):
+            video_url = self._proto_relative_url(video_url, 'http:')
+            cur_info = make_entry(video_id, video_url, index)
+            cur_info['_type'] = 'url_transparent'
+            return cur_info
+
+        if len(video_urls) == 1 and not iframe_links:
+            return make_video_entry(video_id, video_urls[0])
+
+        if len(iframe_links) == 1 and not video_urls:
+            return make_iframe_entry(video_id, iframe_links[0])
+
+        entries = []
+
+        if video_urls:
+            for num, video_url in enumerate(video_urls, 1):
+                entries.append(make_video_entry(video_id, video_url, num))
+
+        if iframe_links:
+            for num, iframe_link in enumerate(iframe_links, len(video_urls) + 1):
+                entries.append(make_iframe_entry(video_id, iframe_link, num))
+
+        playlist = common_info.copy()
+        playlist.update(self.playlist_result(entries, video_id, title, description))
+        return playlist
+
+
+class LifeEmbedIE(InfoExtractor):
+    IE_NAME = 'life:embed'
+    _VALID_URL = r'https?://embed\.life\.ru/(?:embed|video)/(?P<id>[\da-f]{32})'
+
+    _TESTS = [{
+        'url': 'http://embed.life.ru/embed/e50c2dec2867350528e2574c899b8291',
+        'md5': 'b889715c9e49cb1981281d0e5458fbbe',
+        'info_dict': {
+            'id': 'e50c2dec2867350528e2574c899b8291',
+            'ext': 'mp4',
+            'title': 'e50c2dec2867350528e2574c899b8291',
+            'thumbnail': r're:http://.*\.jpg',
+        }
+    }, {
+        # with 1080p
+        'url': 'https://embed.life.ru/video/e50c2dec2867350528e2574c899b8291',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        thumbnail = None
+        formats = []
+
+        def extract_m3u8(manifest_url):
+            formats.extend(self._extract_m3u8_formats(
+                manifest_url, video_id, 'mp4',
+                entry_protocol='m3u8_native', m3u8_id='m3u8'))
+
+        def extract_original(original_url):
+            formats.append({
+                'url': original_url,
+                'format_id': determine_ext(original_url, None),
+                'quality': 1,
+            })
+
+        playlist = self._parse_json(
+            self._search_regex(
+                r'options\s*=\s*({.+?});', webpage, 'options', default='{}'),
+            video_id).get('playlist', {})
+        if playlist:
+            master = playlist.get('master')
+            if isinstance(master, compat_str) and determine_ext(master) == 'm3u8':
+                extract_m3u8(compat_urlparse.urljoin(url, master))
+            original = playlist.get('original')
+            if isinstance(original, compat_str):
+                extract_original(original)
+            thumbnail = playlist.get('image')
+
+        # Old rendition fallback
+        if not formats:
+            for video_url in re.findall(r'"file"\s*:\s*"([^"]+)', webpage):
+                video_url = compat_urlparse.urljoin(url, video_url)
+                if determine_ext(video_url) == 'm3u8':
+                    extract_m3u8(video_url)
+                else:
+                    extract_original(video_url)
+
+        thumbnail = thumbnail or self._search_regex(
+            r'"image"\s*:\s*"([^"]+)', webpage, 'thumbnail', default=None)
+
+        return {
+            'id': video_id,
+            'title': video_id,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

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

@@ -0,0 +1,182 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    js_to_json,
+    parse_iso8601,
+    str_or_none,
+    traverse_obj,
+)
+
+
+class LikeeIE(InfoExtractor):
+    IE_NAME = 'likee'
+    _VALID_URL = r'(?x)https?://(www\.)?likee\.video/(?:(?P<channel_name>[^/]+)/video/|v/)(?P<id>\w+)'
+    _TESTS = [{
+        'url': 'https://likee.video/@huynh_hong_quan_/video/7093444807096327263',
+        'info_dict': {
+            'id': '7093444807096327263',
+            'ext': 'mp4',
+            'title': '🤴🤴🤴',
+            'description': 'md5:9a7ebe816f0e78722ee5ed76f75983b4',
+            'thumbnail': r're:^https?://.+\.jpg',
+            'uploader': 'Huỳnh Hồng Qu&acirc;n ',
+            'artist': 'Huỳnh Hồng Qu&acirc;n ',
+            'timestamp': 1651571320,
+            'upload_date': '20220503',
+            'view_count': int,
+            'uploader_id': 'huynh_hong_quan_',
+            'duration': 12374,
+            'comment_count': int,
+            'like_count': int,
+        },
+    }, {
+        'url': 'https://likee.video/@649222262/video/7093167848050058862',
+        'info_dict': {
+            'id': '7093167848050058862',
+            'ext': 'mp4',
+            'title': 'likee video #7093167848050058862',
+            'description': 'md5:3f971c8c6ee8a216f2b1a9094c5de99f',
+            'thumbnail': r're:^https?://.+\.jpg',
+            'comment_count': int,
+            'like_count': int,
+            'uploader': 'Vương Phước Nhi',
+            'timestamp': 1651506835,
+            'upload_date': '20220502',
+            'duration': 60024,
+            'artist': 'Vương Phước Nhi',
+            'uploader_id': '649222262',
+            'view_count': int,
+        },
+    }, {
+        'url': 'https://likee.video/@fernanda_rivasg/video/6932224568407629502',
+        'info_dict': {
+            'id': '6932224568407629502',
+            'ext': 'mp4',
+            'title': 'Un trend viejito🔥 #LIKEE #Ferlovers #trend ',
+            'description': 'md5:c42b903a72a99d6d8b73e3d1126fbcef',
+            'thumbnail': r're:^https?://.+\.jpg',
+            'comment_count': int,
+            'duration': 9684,
+            'uploader_id': 'fernanda_rivasg',
+            'view_count': int,
+            'artist': 'La Cami La✨',
+            'like_count': int,
+            'uploader': 'Fernanda Rivas🎶',
+            'timestamp': 1614034308,
+            'upload_date': '20210222',
+        },
+    }, {
+        'url': 'https://likee.video/v/k6QcOp',
+        'info_dict': {
+            'id': 'k6QcOp',
+            'ext': 'mp4',
+            'title': '#AguaChallenge t&uacute; ya lo intentaste?😱🤩',
+            'description': 'md5:b0cc462689d4ff2b624daa4dba7640d9',
+            'thumbnail': r're:^https?://.+\.jpg',
+            'comment_count': int,
+            'duration': 18014,
+            'view_count': int,
+            'timestamp': 1611694774,
+            'like_count': int,
+            'uploader': 'Fernanda Rivas🎶',
+            'uploader_id': 'fernanda_rivasg',
+            'artist': 'ʟᴇʀɪᴋ_ᴜɴɪᴄᴏʀɴ♡︎',
+            'upload_date': '20210126',
+        },
+    }, {
+        'url': 'https://www.likee.video/@649222262/video/7093167848050058862',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.likee.video/v/k6QcOp',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        info = self._parse_json(
+            self._search_regex(r'window\.data\s=\s({.+?});', webpage, 'video info'),
+            video_id, transform_source=js_to_json)
+        video_url = traverse_obj(info, 'video_url', ('originVideoInfo', 'video_url'))
+        if not video_url:
+            self.raise_no_formats('Video was deleted', expected=True)
+        formats = [{
+            'format_id': 'mp4-with-watermark',
+            'url': video_url,
+            'height': info.get('video_height'),
+            'width': info.get('video_width'),
+        }, {
+            'format_id': 'mp4-without-watermark',
+            'url': video_url.replace('_4', ''),
+            'height': info.get('video_height'),
+            'width': info.get('video_width'),
+            'quality': 1,
+        }]
+        return {
+            'id': video_id,
+            'title': info.get('msgText'),
+            'description': info.get('share_desc'),
+            'view_count': int_or_none(info.get('video_count')),
+            'like_count': int_or_none(info.get('likeCount')),
+            'comment_count': int_or_none(info.get('comment_count')),
+            'uploader': str_or_none(info.get('nick_name')),
+            'uploader_id': str_or_none(info.get('likeeId')),
+            'artist': str_or_none(traverse_obj(info, ('sound', 'owner_name'))),
+            'timestamp': parse_iso8601(info.get('uploadDate')),
+            'thumbnail': info.get('coverUrl'),
+            'duration': int_or_none(traverse_obj(info, ('option_data', 'dur'))),
+            'formats': formats,
+        }
+
+
+class LikeeUserIE(InfoExtractor):
+    IE_NAME = 'likee:user'
+    _VALID_URL = r'https?://(www\.)?likee\.video/(?P<id>[^/]+)/?$'
+    _TESTS = [{
+        'url': 'https://likee.video/@fernanda_rivasg',
+        'info_dict': {
+            'id': '925638334',
+            'title': 'fernanda_rivasg',
+        },
+        'playlist_mincount': 500,
+    }, {
+        'url': 'https://likee.video/@may_hmoob',
+        'info_dict': {
+            'id': '2943949041',
+            'title': 'may_hmoob',
+        },
+        'playlist_mincount': 80,
+    }]
+    _PAGE_SIZE = 50
+    _API_GET_USER_VIDEO = 'https://api.like-video.com/likee-activity-flow-micro/videoApi/getUserVideo'
+
+    def _entries(self, user_name, user_id):
+        last_post_id = ''
+        while True:
+            user_videos = self._download_json(
+                self._API_GET_USER_VIDEO, user_name,
+                data=json.dumps({
+                    'uid': user_id,
+                    'count': self._PAGE_SIZE,
+                    'lastPostId': last_post_id,
+                    'tabType': 0,
+                }).encode('utf-8'),
+                headers={'content-type': 'application/json'},
+                note=f'Get user info with lastPostId #{last_post_id}')
+            items = traverse_obj(user_videos, ('data', 'videoList'))
+            if not items:
+                break
+            for item in items:
+                last_post_id = item['postId']
+                yield self.url_result(f'https://likee.video/{user_name}/video/{last_post_id}')
+
+    def _real_extract(self, url):
+        user_name = self._match_id(url)
+        webpage = self._download_webpage(url, user_name)
+        info = self._parse_json(
+            self._search_regex(r'window\.data\s*=\s*({.+?});', webpage, 'user info'),
+            user_name, transform_source=js_to_json)
+        user_id = traverse_obj(info, ('userinfo', 'uid'))
+        return self.playlist_result(self._entries(user_name, user_id), user_id, traverse_obj(info, ('userinfo', 'user_name')))