diff options
Diffstat (limited to 'hypervideo_dl/extractor/hotstar.py')
| -rw-r--r-- | hypervideo_dl/extractor/hotstar.py | 303 |
1 files changed, 192 insertions, 111 deletions
diff --git a/hypervideo_dl/extractor/hotstar.py b/hypervideo_dl/extractor/hotstar.py index 1620822..74e2728 100644 --- a/hypervideo_dl/extractor/hotstar.py +++ b/hypervideo_dl/extractor/hotstar.py @@ -3,15 +3,15 @@ from __future__ import unicode_literals import hashlib import hmac -import json import re import time import uuid +import json from .common import InfoExtractor from ..compat import ( compat_HTTPError, - compat_str, + compat_str ) from ..utils import ( determine_ext, @@ -26,52 +26,79 @@ from ..utils import ( class HotStarBaseIE(InfoExtractor): _AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee' - def _call_api_impl(self, path, video_id, headers, query, data=None): - st = int(time.time()) + def _call_api_impl(self, path, video_id, query, st=None, cookies=None): + st = int_or_none(st) or int(time.time()) exp = st + 6000 auth = 'st=%d~exp=%d~acl=/*' % (st, exp) auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest() - h = {'hotstarauth': auth} - h.update(headers) - return self._download_json( - 'https://api.hotstar.com/' + path, - video_id, headers=h, query=query, data=data) + + if cookies and cookies.get('userUP'): + token = cookies.get('userUP').value + else: + token = self._download_json( + 'https://api.hotstar.com/um/v3/users', + video_id, note='Downloading token', + data=json.dumps({"device_ids": [{"id": compat_str(uuid.uuid4()), "type": "device_id"}]}).encode('utf-8'), + headers={ + 'hotstarauth': auth, + 'x-hs-platform': 'PCTV', # or 'web' + 'Content-Type': 'application/json', + })['user_identity'] + + response = self._download_json( + 'https://api.hotstar.com/' + path, video_id, headers={ + 'hotstarauth': auth, + 'x-hs-appversion': '6.72.2', + 'x-hs-platform': 'web', + 'x-hs-usertoken': token, + }, query=query) + + if response['message'] != "Playback URL's fetched successfully": + raise ExtractorError( + response['message'], expected=True) + return response['data'] def _call_api(self, path, video_id, query_name='contentId'): - response = self._call_api_impl(path, video_id, { - 'x-country-code': 'IN', - 'x-platform-code': 'JIO', - }, { + return self._download_json('https://api.hotstar.com/' + path, video_id=video_id, query={ query_name: video_id, 'tas': 10000, + }, headers={ + 'x-country-code': 'IN', + 'x-platform-code': 'PCTV', }) - if response['statusCode'] != 'OK': - raise ExtractorError( - response['body']['message'], expected=True) - return response['body']['results'] - - def _call_api_v2(self, path, video_id, headers, query=None, data=None): - h = {'X-Request-Id': compat_str(uuid.uuid4())} - h.update(headers) - try: - return self._call_api_impl( - path, video_id, h, query, data) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError): - if e.cause.code == 402: - self.raise_login_required() - message = self._parse_json(e.cause.read().decode(), video_id)['message'] - if message in ('Content not available in region', 'Country is not supported'): - raise self.raise_geo_restricted(message) - raise ExtractorError(message) - raise e + + def _call_api_v2(self, path, video_id, st=None, cookies=None): + return self._call_api_impl( + '%s/content/%s' % (path, video_id), video_id, st=st, cookies=cookies, query={ + 'desired-config': 'audio_channel:stereo|container:fmp4|dynamic_range:hdr|encryption:plain|ladder:tv|package:dash|resolution:fhd|subs-tag:HotstarVIP|video_codec:h265', + 'device-id': cookies.get('device_id').value if cookies.get('device_id') else compat_str(uuid.uuid4()), + 'os-name': 'Windows', + 'os-version': '10', + }) class HotStarIE(HotStarBaseIE): IE_NAME = 'hotstar' - _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+[/-])?(?P<id>\d{10})' + _VALID_URL = r'''(?x) + (?: + hotstar\:| + https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/) + ) + (?: + (?P<type>movies|sports|episode|(?P<tv>tv)) + (?: + \:| + /[^/?#]+/ + (?(tv) + (?:[^/?#]+/){2}| + (?:[^/?#]+/)* + ) + )| + [^/?#]+/ + )? + (?P<id>\d{10}) + ''' _TESTS = [{ - # contentData 'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273', 'info_dict': { 'id': '1000076273', @@ -82,147 +109,161 @@ class HotStarIE(HotStarBaseIE): 'upload_date': '20151111', 'duration': 381, }, - 'params': { - # m3u8 download - 'skip_download': True, - } }, { - # contentDetail + 'url': 'hotstar:1000076273', + 'only_matching': True, + }, { 'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157', + 'info_dict': { + 'id': '1000057157', + 'ext': 'mp4', + 'title': 'Radha Gopalam', + 'description': 'md5:be3bc342cc120bbc95b3b0960e2b0d22', + 'timestamp': 1140805800, + 'upload_date': '20060224', + 'duration': 9182, + }, + }, { + 'url': 'hotstar:movies:1000057157', 'only_matching': True, }, { - 'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583', + 'url': 'https://www.hotstar.com/in/sports/cricket/follow-the-blues-2021/recap-eng-fight-back-on-day-2/1260066104', 'only_matching': True, }, { - 'url': 'http://www.hotstar.com/1000000515', + 'url': 'https://www.hotstar.com/in/sports/football/most-costly-pl-transfers-ft-grealish/1260065956', 'only_matching': True, }, { - # only available via api v2 - 'url': 'https://www.hotstar.com/tv/ek-bhram-sarvagun-sampanna/s-2116/janhvi-targets-suman/1000234847', + # contentData + 'url': 'hotstar:sports:1260065956', 'only_matching': True, }, { - 'url': 'https://www.hotstar.com/in/tv/start-music/1260005217/cooks-vs-comalis/1100039717', + # contentData + 'url': 'hotstar:sports:1260066104', + 'only_matching': True, + }, { + 'url': 'https://www.hotstar.com/tv/ek-bhram-sarvagun-sampanna/s-2116/janhvi-targets-suman/1000234847', + 'info_dict': { + 'id': '1000234847', + 'ext': 'mp4', + 'title': 'Janhvi Targets Suman', + 'description': 'md5:78a85509348910bd1ca31be898c5796b', + 'timestamp': 1556670600, + 'upload_date': '20190501', + 'duration': 1219, + 'channel': 'StarPlus', + 'channel_id': 3, + 'series': 'Ek Bhram - Sarvagun Sampanna', + 'season': 'Chapter 1', + 'season_number': 1, + 'season_id': 6771, + 'episode': 'Janhvi Targets Suman', + 'episode_number': 8, + }, + }, { + 'url': 'hotstar:episode:1000234847', 'only_matching': True, }] _GEO_BYPASS = False - _DEVICE_ID = None - _USER_TOKEN = None + _TYPE = { + 'movies': 'movie', + 'sports': 'match', + 'episode': 'episode', + 'tv': 'episode', + None: 'content', + } def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - app_state = self._parse_json(self._search_regex( - r'<script>window\.APP_STATE\s*=\s*({.+?})</script>', - webpage, 'app state'), video_id) - video_data = {} - getters = list( - lambda x, k=k: x['initialState']['content%s' % k]['content'] - for k in ('Data', 'Detail') - ) - for v in app_state.values(): - content = try_get(v, getters, dict) - if content and content.get('contentId') == video_id: - video_data = content - break - + mobj = self._match_valid_url(url) + video_id = mobj.group('id') + video_type = mobj.group('type') + cookies = self._get_cookies(url) + video_type = self._TYPE.get(video_type, video_type) + video_data = self._call_api(f'o/v1/{video_type}/detail', video_id)['body']['results']['item'] title = video_data['title'] - if video_data.get('drmProtected'): - raise ExtractorError('This video is DRM protected.', expected=True) + if not self.get_param('allow_unplayable_formats') and video_data.get('drmProtected'): + self.report_drm(video_id) - headers = {'Referer': url} + headers = {'Referer': 'https://www.hotstar.com/in'} formats = [] + subs = {} geo_restricted = False - - if not self._USER_TOKEN: - self._DEVICE_ID = compat_str(uuid.uuid4()) - self._USER_TOKEN = self._call_api_v2('um/v3/users', video_id, { - 'X-HS-Platform': 'PCTV', - 'Content-Type': 'application/json', - }, data=json.dumps({ - 'device_ids': [{ - 'id': self._DEVICE_ID, - 'type': 'device_id', - }], - }).encode())['user_identity'] - - playback_sets = self._call_api_v2( - 'play/v2/playback/content/' + video_id, video_id, { - 'X-HS-Platform': 'web', - 'X-HS-AppVersion': '6.99.1', - 'X-HS-UserToken': self._USER_TOKEN, - }, query={ - 'device-id': self._DEVICE_ID, - 'desired-config': 'encryption:plain', - 'os-name': 'Windows', - 'os-version': '10', - })['data']['playBackSets'] + _, urlh = self._download_webpage_handle('https://www.hotstar.com/in', video_id) + # Required to fix https://github.com/hypervideo/hypervideo/issues/396 + st = urlh.headers.get('x-origin-date') + # change to v2 in the future + playback_sets = self._call_api_v2('play/v1/playback', video_id, st=st, cookies=cookies)['playBackSets'] for playback_set in playback_sets: if not isinstance(playback_set, dict): continue + dr = re.search(r'dynamic_range:(?P<dr>[a-z]+)', playback_set.get('tagsCombination')).group('dr') format_url = url_or_none(playback_set.get('playbackUrl')) if not format_url: continue format_url = re.sub( r'(?<=//staragvod)(\d)', r'web\1', format_url) tags = str_or_none(playback_set.get('tagsCombination')) or '' - if tags and 'encryption:plain' not in tags: - continue ext = determine_ext(format_url) + current_formats, current_subs = [], {} try: if 'package:hls' in tags or ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( + current_formats, current_subs = self._extract_m3u8_formats_and_subtitles( format_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', headers=headers)) + m3u8_id=f'{dr}-hls', headers=headers) elif 'package:dash' in tags or ext == 'mpd': - formats.extend(self._extract_mpd_formats( - format_url, video_id, mpd_id='dash', headers=headers)) + current_formats, current_subs = self._extract_mpd_formats_and_subtitles( + format_url, video_id, mpd_id=f'{dr}-dash', headers=headers) elif ext == 'f4m': # produce broken files pass else: - formats.append({ + current_formats = [{ 'url': format_url, 'width': int_or_none(playback_set.get('width')), 'height': int_or_none(playback_set.get('height')), - }) + }] except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: geo_restricted = True continue + if tags and 'encryption:plain' not in tags: + for f in current_formats: + f['has_drm'] = True + formats.extend(current_formats) + subs = self._merge_subtitles(subs, current_subs) if not formats and geo_restricted: - self.raise_geo_restricted(countries=['IN']) + self.raise_geo_restricted(countries=['IN'], metadata_available=True) self._sort_formats(formats) for f in formats: f.setdefault('http_headers', {}).update(headers) - image = try_get(video_data, lambda x: x['image']['h'], compat_str) - return { 'id': video_id, 'title': title, - 'thumbnail': 'https://img1.hotstarext.com/image/upload/' + image if image else None, 'description': video_data.get('description'), 'duration': int_or_none(video_data.get('duration')), 'timestamp': int_or_none(video_data.get('broadcastDate') or video_data.get('startDate')), 'formats': formats, + 'subtitles': subs, 'channel': video_data.get('channelName'), - 'channel_id': str_or_none(video_data.get('channelId')), + 'channel_id': video_data.get('channelId'), 'series': video_data.get('showName'), 'season': video_data.get('seasonName'), 'season_number': int_or_none(video_data.get('seasonNo')), - 'season_id': str_or_none(video_data.get('seasonId')), + 'season_id': video_data.get('seasonId'), 'episode': title, 'episode_number': int_or_none(video_data.get('episodeNo')), + 'http_headers': { + 'Referer': 'https://www.hotstar.com/in', + } } class HotStarPlaylistIE(HotStarBaseIE): IE_NAME = 'hotstar:playlist' - _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:[a-z]{2}/)?tv/[^/]+/s-\w+/list/[^/]+/t-(?P<id>\w+)' + _VALID_URL = r'https?://(?:www\.)?hotstar\.com/tv/[^/]+/s-\w+/list/[^/]+/t-(?P<id>\w+)' _TESTS = [{ 'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26', 'info_dict': { @@ -232,16 +273,12 @@ class HotStarPlaylistIE(HotStarBaseIE): }, { 'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480', 'only_matching': True, - }, { - 'url': 'https://www.hotstar.com/us/tv/masterchef-india/s-830/list/episodes/t-1_2_830', - 'only_matching': True, }] def _real_extract(self, url): playlist_id = self._match_id(url) - collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId') - + collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId')['body']['results'] entries = [ self.url_result( 'https://www.hotstar.com/%s' % video['contentId'], @@ -250,3 +287,47 @@ class HotStarPlaylistIE(HotStarBaseIE): if video.get('contentId')] return self.playlist_result(entries, playlist_id) + + +class HotStarSeriesIE(HotStarBaseIE): + IE_NAME = 'hotstar:series' + _VALID_URL = r'(?P<url>(?:https?://)(?:www\.)?hotstar\.com(?:/in)?/tv/[^/]+/(?P<id>\d+))' + _TESTS = [{ + 'url': 'https://www.hotstar.com/in/tv/radhakrishn/1260000646', + 'info_dict': { + 'id': '1260000646', + }, + 'playlist_mincount': 690, + }, { + 'url': 'https://www.hotstar.com/tv/dancee-/1260050431', + 'info_dict': { + 'id': '1260050431', + }, + 'playlist_mincount': 43, + }, { + 'url': 'https://www.hotstar.com/in/tv/mahabharat/435/', + 'info_dict': { + 'id': '435', + }, + 'playlist_mincount': 269, + }] + + def _real_extract(self, url): + url, series_id = self._match_valid_url(url).groups() + headers = { + 'x-country-code': 'IN', + 'x-platform-code': 'PCTV', + } + detail_json = self._download_json('https://api.hotstar.com/o/v1/show/detail?contentId=' + series_id, + video_id=series_id, headers=headers) + id = compat_str(try_get(detail_json, lambda x: x['body']['results']['item']['id'], int)) + item_json = self._download_json('https://api.hotstar.com/o/v1/tray/g/1/items?etid=0&tao=0&tas=10000&eid=' + id, + video_id=series_id, headers=headers) + entries = [ + self.url_result( + '%s/ignoreme/%d' % (url, video['contentId']), + ie=HotStarIE.ie_key(), video_id=video['contentId']) + for video in item_json['body']['results']['items'] + if video.get('contentId')] + + return self.playlist_result(entries, series_id) |