From 8fddc232bfe99eee847a4c4fa57ed7a334ebd62c Mon Sep 17 00:00:00 2001 From: zulaport <70630440+zulaport@users.noreply.github.com> Date: Tue, 8 Nov 2022 19:23:24 -0800 Subject: [PATCH] [extractor/camsoda] Add extractor (#5465) Authored by: zulaport --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/camsoda.py | 59 +++++++++++++++++++++++++++++++++ 2 files changed, 60 insertions(+) create mode 100644 yt_dlp/extractor/camsoda.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 6d5fc033e..97da309c5 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -255,6 +255,7 @@ from .camdemy import ( CamdemyFolderIE ) from .cammodels import CamModelsIE +from .camsoda import CamsodaIE from .camtasia import CamtasiaEmbedIE from .camwithher import CamWithHerIE from .canalalpha import CanalAlphaIE diff --git a/yt_dlp/extractor/camsoda.py b/yt_dlp/extractor/camsoda.py new file mode 100644 index 000000000..1b47b0584 --- /dev/null +++ b/yt_dlp/extractor/camsoda.py @@ -0,0 +1,59 @@ +import random + +from .common import InfoExtractor +from ..utils import ExtractorError, traverse_obj + + +class CamsodaIE(InfoExtractor): + _VALID_URL = r'https?://www\.camsoda\.com/(?P[\w-]+)' + _TESTS = [{ + 'url': 'https://www.camsoda.com/lizzhopf', + 'info_dict': { + 'id': 'lizzhopf', + 'ext': 'mp4', + 'title': 'lizzhopf (lizzhopf) Nude on Cam. Free Live Sex Chat Room - CamSoda', + 'description': str, + 'is_live': True, + 'age_limit': 18, + }, + 'skip': 'Room is offline', + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id, headers=self.geo_verification_headers()) + + data = self._download_json( + f'https://camsoda.com/api/v1/video/vtoken/{video_id}', video_id, + query={'username': f'guest_{random.randrange(10000, 99999)}'}, + headers=self.geo_verification_headers()) + if not data: + raise ExtractorError('Unable to find configuration for stream.') + elif data.get('private_servers'): + raise ExtractorError('Model is in private show.', expected=True) + elif not data.get('stream_name'): + raise ExtractorError('Model is offline.', expected=True) + + stream_name = traverse_obj(data, 'stream_name', expected_type=str) + token = traverse_obj(data, 'token', expected_type=str) + + formats = [] + for server in traverse_obj(data, ('edge_servers', ...)): + formats = self._extract_m3u8_formats( + f'https://{server}/{stream_name}_v1/index.m3u8?token={token}', + video_id, ext='mp4', m3u8_id='hls', fatal=False, live=True) + if formats: + break + if not formats: + self.raise_no_formats('No active streams found', expected=True) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': self._html_extract_title(webpage), + 'description': self._html_search_meta('description', webpage, default=None), + 'is_live': True, + 'formats': formats, + 'age_limit': 18, + }