From 513ea811552c104aa5d1d1e218cc60cedb35cd46 Mon Sep 17 00:00:00 2001 From: mp107 Date: Sun, 16 Jun 2024 21:00:43 +0200 Subject: [PATCH 1/5] [elemental_tv] Add extractor --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/elemental_tv.py | 114 +++++++++++++++++++++++++++++++ 2 files changed, 115 insertions(+) create mode 100644 yt_dlp/extractor/elemental_tv.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 0f599c9db..0bc73d9fa 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -584,6 +584,7 @@ from .eighttracks import EightTracksIE from .eitb import EitbIE from .elementorembed import ElementorEmbedIE +from .elemental_tv import ElementalTVIE from .elonet import ElonetIE from .elpais import ElPaisIE from .eltrecetv import ElTreceTVIE diff --git a/yt_dlp/extractor/elemental_tv.py b/yt_dlp/extractor/elemental_tv.py new file mode 100644 index 000000000..c85653e71 --- /dev/null +++ b/yt_dlp/extractor/elemental_tv.py @@ -0,0 +1,114 @@ +import json +import re +import time + +from yt_dlp.extractor.common import InfoExtractor +from yt_dlp.utils import ExtractorError + + +class ElementalTVIE(InfoExtractor): + _LOGIN_REQUIRED = True + _NETRC_MACHINE = 'elemental_tv' + _VALID_URL = r'https?://play\.elemental\.tv/channel/[0-9a-f]{24}' + _TESTS = [{ + 'url': 'https://play.elemental.tv/channel/573f5a14761973ec1d502507', + 'info_dict': { + 'id': '573f5a14761973ec1d502507', + 'ext': 'mp4', + 'title': 'БНТ 1 HD', + 'thumbnail': 'https://play.elemental.tv/v1/tumblrs/573f5a14761973ec1d502507', + 'age_limit': 0, + }, + }] + + API_URL_CHANNELS = 'https://play.elemental.tv/v1/channels' + API_URL_LOGIN = 'https://play.elemental.tv/v1/users/login' + API_URL_STREAM_URL = 'https://play.elemental.tv/v1/playlists/%s/playlist.m3u8?begin=%d&access_token=%s' + + access_token = '' + channel_id = '' + + def get_channel_id(self, url): + url_parts = re.search('(?<=channel/)[0-9a-f]{24}', url) + + if not url_parts or not url_parts.group(0): + return None + + return url_parts.group(0) + + def get_stream_metadata(self): + try: + headers = { + 'Authorization': 'Bearer ' + self.access_token, + } + + res_api = self._download_json( + self.API_URL_CHANNELS, self.channel_id, headers=headers) + + data = res_api.get('data').get(self.channel_id) + + if not data: + return {} + + return { + 'title': data.get('name'), + 'age_limit': data.get('age'), + 'thumbnail': data.get('tumblrurl'), + } + except Exception: + self.write_debug('Getting metadata failed') + return {} + + def get_stream_url(self): + # Stream URL needs current epoch time rounded to 10000s + begin = int((time.time() - 60) / 10000) * 10000 + + return self.API_URL_STREAM_URL % (self.channel_id, begin, self.access_token) + + def _perform_login(self, username, password): + url = self.API_URL_LOGIN + + post_data = { + 'email': str(username), + 'grant_type': 'client_credentials', + 'password': str(password), + 'rememberme': 'true', + } + + post_data = json.dumps(post_data).encode() + + res_api = self._download_json(url, self.channel_id, data=post_data).get('data') + + if not res_api or not res_api.get('access_token'): + raise ExtractorError('Accessing login token failed') + + self.access_token = res_api.get('access_token') + token_type = res_api.get('token_type') + + if token_type != 'Bearer': + raise ExtractorError('Unknown login token type') + + def _real_extract(self, url): + if not self.access_token: + raise ExtractorError('Logging in failed') + + self.channel_id = self.get_channel_id(url) + + if not self.channel_id: + raise ExtractorError('Channel ID not found') + + self.write_debug(f'Channel ID: {self.channel_id}') + + stream_url = self.get_stream_url() + + if not stream_url or '.m3u8' not in stream_url: + raise ExtractorError('Unable to get stream URL') + + formats, subtitles = self._extract_m3u8_formats_and_subtitles(stream_url, self.channel_id, ext='mp4') + + return { + 'id': self.channel_id, + 'formats': formats, + 'subtitles': subtitles, + **self.get_stream_metadata(), + } From 80c2305d45a6dc776afdca17ac79483949d79768 Mon Sep 17 00:00:00 2001 From: mp107 Date: Sun, 16 Jun 2024 21:09:48 +0200 Subject: [PATCH 2/5] [elemental_tv] Fix extractors order --- yt_dlp/extractor/_extractors.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 0bc73d9fa..004bc38f9 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -583,8 +583,8 @@ ) from .eighttracks import EightTracksIE from .eitb import EitbIE -from .elementorembed import ElementorEmbedIE from .elemental_tv import ElementalTVIE +from .elementorembed import ElementorEmbedIE from .elonet import ElonetIE from .elpais import ElPaisIE from .eltrecetv import ElTreceTVIE From 11daaaf0607eae32fea08ea3b0d0e31559f8383a Mon Sep 17 00:00:00 2001 From: mp107 Date: Mon, 17 Jun 2024 19:33:09 +0200 Subject: [PATCH 3/5] [elemental_tv] Fix further issues, add logging in error message handling --- yt_dlp/extractor/elemental_tv.py | 63 ++++++++++++++------------------ 1 file changed, 28 insertions(+), 35 deletions(-) diff --git a/yt_dlp/extractor/elemental_tv.py b/yt_dlp/extractor/elemental_tv.py index c85653e71..b010aa132 100644 --- a/yt_dlp/extractor/elemental_tv.py +++ b/yt_dlp/extractor/elemental_tv.py @@ -2,6 +2,7 @@ import re import time +from yt_dlp.networking.exceptions import HTTPError from yt_dlp.extractor.common import InfoExtractor from yt_dlp.utils import ExtractorError @@ -21,33 +22,32 @@ class ElementalTVIE(InfoExtractor): }, }] - API_URL_CHANNELS = 'https://play.elemental.tv/v1/channels' - API_URL_LOGIN = 'https://play.elemental.tv/v1/users/login' - API_URL_STREAM_URL = 'https://play.elemental.tv/v1/playlists/%s/playlist.m3u8?begin=%d&access_token=%s' - access_token = '' channel_id = '' - def get_channel_id(self, url): + def _get_channel_id(self, url): url_parts = re.search('(?<=channel/)[0-9a-f]{24}', url) if not url_parts or not url_parts.group(0): return None - return url_parts.group(0) + self.channel_id = url_parts.group(0) + self.write_debug(f'Channel ID: {self.channel_id}') - def get_stream_metadata(self): + if not self.channel_id: + raise ExtractorError('Channel ID not found') + + def _get_stream_metadata(self): try: headers = { 'Authorization': 'Bearer ' + self.access_token, } - res_api = self._download_json( - self.API_URL_CHANNELS, self.channel_id, headers=headers) - + 'https://play.elemental.tv/v1/channels', self.channel_id, headers=headers) data = res_api.get('data').get(self.channel_id) if not data: + self.write_debug('Getting metadata failed') return {} return { @@ -59,15 +59,17 @@ def get_stream_metadata(self): self.write_debug('Getting metadata failed') return {} - def get_stream_url(self): + def _get_stream_url(self): # Stream URL needs current epoch time rounded to 10000s begin = int((time.time() - 60) / 10000) * 10000 + stream_url = 'https://play.elemental.tv/v1/playlists/%s/playlist.m3u8?begin=%d&access_token=%s' % (self.channel_id, begin, self.access_token) - return self.API_URL_STREAM_URL % (self.channel_id, begin, self.access_token) + if not stream_url or '.m3u8' not in stream_url: + raise ExtractorError('Unable to get stream URL') + + return stream_url def _perform_login(self, username, password): - url = self.API_URL_LOGIN - post_data = { 'email': str(username), 'grant_type': 'client_credentials', @@ -75,40 +77,31 @@ def _perform_login(self, username, password): 'rememberme': 'true', } - post_data = json.dumps(post_data).encode() - - res_api = self._download_json(url, self.channel_id, data=post_data).get('data') + try: + res_api = self._download_json( + 'https://play.elemental.tv/v1/users/login', self.channel_id, data=json.dumps(post_data).encode()).get('data') + except ExtractorError as e: + if isinstance(e.cause, HTTPError) and e.cause.status == 400: + error_message = self._parse_json(e.cause.response.read().decode(), self.channel_id).get('error_info').get('description') + raise ExtractorError(error_message, expected=True) if not res_api or not res_api.get('access_token'): raise ExtractorError('Accessing login token failed') self.access_token = res_api.get('access_token') - token_type = res_api.get('token_type') - if token_type != 'Bearer': + if res_api.get('token_type') != 'Bearer': raise ExtractorError('Unknown login token type') def _real_extract(self, url): - if not self.access_token: - raise ExtractorError('Logging in failed') - - self.channel_id = self.get_channel_id(url) - - if not self.channel_id: - raise ExtractorError('Channel ID not found') - - self.write_debug(f'Channel ID: {self.channel_id}') - - stream_url = self.get_stream_url() - - if not stream_url or '.m3u8' not in stream_url: - raise ExtractorError('Unable to get stream URL') - + self._get_channel_id(url) + stream_url = self._get_stream_url() formats, subtitles = self._extract_m3u8_formats_and_subtitles(stream_url, self.channel_id, ext='mp4') return { 'id': self.channel_id, + 'is_live': True, 'formats': formats, 'subtitles': subtitles, - **self.get_stream_metadata(), + **self._get_stream_metadata(), } From 8bdf94aee3a96c62b7f29e30cd37a5e9b06e4146 Mon Sep 17 00:00:00 2001 From: mp107 Date: Mon, 17 Jun 2024 19:44:51 +0200 Subject: [PATCH 4/5] [elemental_tv] Fix import ordering issues --- yt_dlp/extractor/elemental_tv.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/yt_dlp/extractor/elemental_tv.py b/yt_dlp/extractor/elemental_tv.py index b010aa132..f4dee94f5 100644 --- a/yt_dlp/extractor/elemental_tv.py +++ b/yt_dlp/extractor/elemental_tv.py @@ -2,8 +2,8 @@ import re import time -from yt_dlp.networking.exceptions import HTTPError from yt_dlp.extractor.common import InfoExtractor +from yt_dlp.networking.exceptions import HTTPError from yt_dlp.utils import ExtractorError From b76f13229d8aa5a3206bfd90ca1c6aa52f3be97c Mon Sep 17 00:00:00 2001 From: mp107 Date: Mon, 17 Jun 2024 19:47:25 +0200 Subject: [PATCH 5/5] [elemental_tv] Use relative imports --- yt_dlp/extractor/elemental_tv.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/yt_dlp/extractor/elemental_tv.py b/yt_dlp/extractor/elemental_tv.py index f4dee94f5..b79752389 100644 --- a/yt_dlp/extractor/elemental_tv.py +++ b/yt_dlp/extractor/elemental_tv.py @@ -2,9 +2,9 @@ import re import time -from yt_dlp.extractor.common import InfoExtractor -from yt_dlp.networking.exceptions import HTTPError -from yt_dlp.utils import ExtractorError +from ..extractor.common import InfoExtractor +from ..networking.exceptions import HTTPError +from ..utils import ExtractorError class ElementalTVIE(InfoExtractor):