summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/vrv.py
diff options
context:
space:
mode:
Diffstat (limited to 'yt_dlp/extractor/vrv.py')
-rw-r--r--yt_dlp/extractor/vrv.py268
1 files changed, 268 insertions, 0 deletions
diff --git a/yt_dlp/extractor/vrv.py b/yt_dlp/extractor/vrv.py
new file mode 100644
index 0000000..ad9dc56
--- /dev/null
+++ b/yt_dlp/extractor/vrv.py
@@ -0,0 +1,268 @@
+import base64
+import hashlib
+import hmac
+import json
+import random
+import string
+import time
+import urllib.parse
+
+from .common import InfoExtractor
+from ..compat import compat_HTTPError, compat_urllib_parse_urlencode
+from ..utils import (
+ ExtractorError,
+ float_or_none,
+ int_or_none,
+ join_nonempty,
+ traverse_obj,
+)
+
+
+class VRVBaseIE(InfoExtractor):
+ _API_DOMAIN = None
+ _API_PARAMS = {}
+ _CMS_SIGNING = {}
+ _TOKEN = None
+ _TOKEN_SECRET = ''
+
+ def _call_api(self, path, video_id, note, data=None):
+ # https://tools.ietf.org/html/rfc5849#section-3
+ base_url = self._API_DOMAIN + '/core/' + path
+ query = [
+ ('oauth_consumer_key', self._API_PARAMS['oAuthKey']),
+ ('oauth_nonce', ''.join(random.choices(string.ascii_letters, k=32))),
+ ('oauth_signature_method', 'HMAC-SHA1'),
+ ('oauth_timestamp', int(time.time())),
+ ]
+ if self._TOKEN:
+ query.append(('oauth_token', self._TOKEN))
+ encoded_query = compat_urllib_parse_urlencode(query)
+ headers = self.geo_verification_headers()
+ if data:
+ data = json.dumps(data).encode()
+ headers['Content-Type'] = 'application/json'
+ base_string = '&'.join([
+ 'POST' if data else 'GET',
+ urllib.parse.quote(base_url, ''),
+ urllib.parse.quote(encoded_query, '')])
+ oauth_signature = base64.b64encode(hmac.new(
+ (self._API_PARAMS['oAuthSecret'] + '&' + self._TOKEN_SECRET).encode('ascii'),
+ base_string.encode(), hashlib.sha1).digest()).decode()
+ encoded_query += '&oauth_signature=' + urllib.parse.quote(oauth_signature, '')
+ try:
+ return self._download_json(
+ '?'.join([base_url, encoded_query]), video_id,
+ note='Downloading %s JSON metadata' % note, headers=headers, data=data)
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+ raise ExtractorError(json.loads(e.cause.read().decode())['message'], expected=True)
+ raise
+
+ def _call_cms(self, path, video_id, note):
+ if not self._CMS_SIGNING:
+ index = self._call_api('index', video_id, 'CMS Signing')
+ self._CMS_SIGNING = index.get('cms_signing') or {}
+ if not self._CMS_SIGNING:
+ for signing_policy in index.get('signing_policies', []):
+ signing_path = signing_policy.get('path')
+ if signing_path and signing_path.startswith('/cms/'):
+ name, value = signing_policy.get('name'), signing_policy.get('value')
+ if name and value:
+ self._CMS_SIGNING[name] = value
+ return self._download_json(
+ self._API_DOMAIN + path, video_id, query=self._CMS_SIGNING,
+ note='Downloading %s JSON metadata' % note, headers=self.geo_verification_headers())
+
+ def _get_cms_resource(self, resource_key, video_id):
+ return self._call_api(
+ 'cms_resource', video_id, 'resource path', data={
+ 'resource_key': resource_key,
+ })['__links__']['cms_resource']['href']
+
+ def _extract_vrv_formats(self, url, video_id, stream_format, audio_lang, hardsub_lang):
+ if not url or stream_format not in ('hls', 'dash', 'adaptive_hls'):
+ return []
+ format_id = join_nonempty(
+ stream_format,
+ audio_lang and 'audio-%s' % audio_lang,
+ hardsub_lang and 'hardsub-%s' % hardsub_lang)
+ if 'hls' in stream_format:
+ adaptive_formats = self._extract_m3u8_formats(
+ url, video_id, 'mp4', m3u8_id=format_id,
+ note='Downloading %s information' % format_id,
+ fatal=False)
+ elif stream_format == 'dash':
+ adaptive_formats = self._extract_mpd_formats(
+ url, video_id, mpd_id=format_id,
+ note='Downloading %s information' % format_id,
+ fatal=False)
+ if audio_lang:
+ for f in adaptive_formats:
+ if f.get('acodec') != 'none':
+ f['language'] = audio_lang
+ return adaptive_formats
+
+ def _set_api_params(self):
+ webpage = self._download_webpage(
+ 'https://vrv.co/', None, headers=self.geo_verification_headers())
+ self._API_PARAMS = self._parse_json(self._search_regex(
+ [
+ r'window\.__APP_CONFIG__\s*=\s*({.+?})(?:</script>|;)',
+ r'window\.__APP_CONFIG__\s*=\s*({.+})'
+ ], webpage, 'app config'), None)['cxApiParams']
+ self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co')
+
+
+class VRVIE(VRVBaseIE):
+ IE_NAME = 'vrv'
+ _VALID_URL = r'https?://(?:www\.)?vrv\.co/watch/(?P<id>[A-Z0-9]+)'
+ _TESTS = [{
+ 'url': 'https://vrv.co/watch/GR9PNZ396/Hidden-America-with-Jonah-Ray:BOSTON-WHERE-THE-PAST-IS-THE-PRESENT',
+ 'info_dict': {
+ 'id': 'GR9PNZ396',
+ 'ext': 'mp4',
+ 'title': 'BOSTON: WHERE THE PAST IS THE PRESENT',
+ 'description': 'md5:4ec8844ac262ca2df9e67c0983c6b83f',
+ 'uploader_id': 'seeso',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ }, {
+ # movie listing
+ 'url': 'https://vrv.co/watch/G6NQXZ1J6/Lily-CAT',
+ 'info_dict': {
+ 'id': 'G6NQXZ1J6',
+ 'title': 'Lily C.A.T',
+ 'description': 'md5:988b031e7809a6aeb60968be4af7db07',
+ },
+ 'playlist_count': 2,
+ }]
+ _NETRC_MACHINE = 'vrv'
+
+ def _perform_login(self, username, password):
+ token_credentials = self._call_api(
+ 'authenticate/by:credentials', None, 'Token Credentials', data={
+ 'email': username,
+ 'password': password,
+ })
+ self._TOKEN = token_credentials['oauth_token']
+ self._TOKEN_SECRET = token_credentials['oauth_token_secret']
+
+ def _initialize_pre_login(self):
+ return self._set_api_params()
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ object_data = self._call_cms(self._get_cms_resource(
+ 'cms:/objects/' + video_id, video_id), video_id, 'object')['items'][0]
+ resource_path = object_data['__links__']['resource']['href']
+ video_data = self._call_cms(resource_path, video_id, 'video')
+ title = video_data['title']
+ description = video_data.get('description')
+
+ if video_data.get('__class__') == 'movie_listing':
+ items = self._call_cms(
+ video_data['__links__']['movie_listing/movies']['href'],
+ video_id, 'movie listing').get('items') or []
+ if len(items) != 1:
+ entries = []
+ for item in items:
+ item_id = item.get('id')
+ if not item_id:
+ continue
+ entries.append(self.url_result(
+ 'https://vrv.co/watch/' + item_id,
+ self.ie_key(), item_id, item.get('title')))
+ return self.playlist_result(entries, video_id, title, description)
+ video_data = items[0]
+
+ streams_path = video_data['__links__'].get('streams', {}).get('href')
+ if not streams_path:
+ self.raise_login_required()
+ streams_json = self._call_cms(streams_path, video_id, 'streams')
+
+ audio_locale = streams_json.get('audio_locale')
+ formats = []
+ for stream_type, streams in streams_json.get('streams', {}).items():
+ if stream_type in ('adaptive_hls', 'adaptive_dash'):
+ for stream in streams.values():
+ formats.extend(self._extract_vrv_formats(
+ stream.get('url'), video_id, stream_type.split('_')[1],
+ audio_locale, stream.get('hardsub_locale')))
+
+ subtitles = {}
+ for k in ('captions', 'subtitles'):
+ for subtitle in streams_json.get(k, {}).values():
+ subtitle_url = subtitle.get('url')
+ if not subtitle_url:
+ continue
+ subtitles.setdefault(subtitle.get('locale', 'en-US'), []).append({
+ 'url': subtitle_url,
+ 'ext': subtitle.get('format', 'ass'),
+ })
+
+ thumbnails = []
+ for thumbnail in traverse_obj(video_data, ('images', 'thumbnail', ..., ...)) or []:
+ thumbnail_url = thumbnail.get('source')
+ if not thumbnail_url:
+ continue
+ thumbnails.append({
+ 'url': thumbnail_url,
+ 'width': int_or_none(thumbnail.get('width')),
+ 'height': int_or_none(thumbnail.get('height')),
+ })
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ 'thumbnails': thumbnails,
+ 'description': description,
+ 'duration': float_or_none(video_data.get('duration_ms'), 1000),
+ 'uploader_id': video_data.get('channel_id'),
+ 'series': video_data.get('series_title'),
+ 'season': video_data.get('season_title'),
+ 'season_number': int_or_none(video_data.get('season_number')),
+ 'season_id': video_data.get('season_id'),
+ 'episode': title,
+ 'episode_number': int_or_none(video_data.get('episode_number')),
+ 'episode_id': video_data.get('production_episode_id'),
+ }
+
+
+class VRVSeriesIE(VRVBaseIE):
+ IE_NAME = 'vrv:series'
+ _VALID_URL = r'https?://(?:www\.)?vrv\.co/series/(?P<id>[A-Z0-9]+)'
+ _TEST = {
+ 'url': 'https://vrv.co/series/G68VXG3G6/The-Perfect-Insider',
+ 'info_dict': {
+ 'id': 'G68VXG3G6',
+ },
+ 'playlist_mincount': 11,
+ }
+
+ def _initialize_pre_login(self):
+ return self._set_api_params()
+
+ def _real_extract(self, url):
+ series_id = self._match_id(url)
+
+ seasons_path = self._get_cms_resource(
+ 'cms:/seasons?series_id=' + series_id, series_id)
+ seasons_data = self._call_cms(seasons_path, series_id, 'seasons')
+
+ entries = []
+ for season in seasons_data.get('items', []):
+ episodes_path = season['__links__']['season/episodes']['href']
+ episodes = self._call_cms(episodes_path, series_id, 'episodes')
+ for episode in episodes.get('items', []):
+ episode_id = episode['id']
+ entries.append(self.url_result(
+ 'https://vrv.co/watch/' + episode_id,
+ 'VRV', episode_id, episode.get('title')))
+
+ return self.playlist_result(entries, series_id)
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-01 10:43:05 +0000