diff options
Diffstat (limited to 'yt_dlp/extractor/hotstar.py')
-rw-r--r-- | yt_dlp/extractor/hotstar.py | 119 |
1 files changed, 68 insertions, 51 deletions
diff --git a/yt_dlp/extractor/hotstar.py b/yt_dlp/extractor/hotstar.py index d9223a416..8725c9436 100644 --- a/yt_dlp/extractor/hotstar.py +++ b/yt_dlp/extractor/hotstar.py @@ -1,22 +1,19 @@ 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 -) +from ..compat import compat_HTTPError, compat_str from ..utils import ( - determine_ext, ExtractorError, + determine_ext, int_or_none, join_nonempty, str_or_none, - try_get, + traverse_obj, url_or_none, ) @@ -26,6 +23,11 @@ class HotStarBaseIE(InfoExtractor): _API_URL = 'https://api.hotstar.com' _AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee' + def _call_api_v1(self, path, *args, **kwargs): + return self._download_json( + f'{self._API_URL}/o/v1/{path}', *args, **kwargs, + headers={'x-country-code': 'IN', 'x-platform-code': 'PCTV'}) + 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 @@ -59,17 +61,6 @@ class HotStarBaseIE(InfoExtractor): response['message'], expected=True) return response['data'] - def _call_api(self, path, video_id, query_name='contentId'): - return self._download_json( - f'{self._API_URL}/{path}', video_id=video_id, - query={ - query_name: video_id, - 'tas': 10000, - }, headers={ - 'x-country-code': 'IN', - 'x-platform-code': 'PCTV', - }) - def _call_api_v2(self, path, video_id, st=None, cookies=None): return self._call_api_impl( f'{path}/content/{video_id}', video_id, st=st, cookies=cookies, query={ @@ -79,6 +70,13 @@ class HotStarBaseIE(InfoExtractor): 'os-version': '10', }) + def _playlist_entries(self, path, item_id, root=None, **kwargs): + results = self._call_api_v1(path, item_id, **kwargs)['body']['results'] + for video in traverse_obj(results, (('assets', None), 'items', ...)): + if video.get('contentId'): + yield self.url_result( + HotStarIE._video_url(video['contentId'], root=root), HotStarIE, video['contentId']) + class HotStarIE(HotStarBaseIE): IE_NAME = 'hotstar' @@ -104,6 +102,7 @@ class HotStarIE(HotStarBaseIE): 'duration': 381, 'episode': 'Can You Not Spread Rumours?', }, + 'params': {'skip_download': 'm3u8'}, }, { 'url': 'https://www.hotstar.com/tv/ek-bhram-sarvagun-sampanna/s-2116/janhvi-targets-suman/1000234847', 'info_dict': { @@ -161,7 +160,8 @@ class HotStarIE(HotStarBaseIE): video_type = self._TYPE.get(video_type, video_type) cookies = self._get_cookies(url) # Cookies before any request - video_data = self._call_api(f'o/v1/{video_type}/detail', video_id)['body']['results']['item'] + video_data = self._call_api_v1(f'{video_type}/detail', video_id, + query={'tas': 10000, 'contentId': video_id})['body']['results']['item'] if not self.get_param('allow_unplayable_formats') and video_data.get('drmProtected'): self.report_drm(video_id) @@ -227,7 +227,6 @@ class HotStarIE(HotStarBaseIE): if not formats and geo_restricted: self.raise_geo_restricted(countries=['IN'], metadata_available=True) - self._sort_formats(formats) for f in formats: f.setdefault('http_headers', {}).update(headers) @@ -258,16 +257,16 @@ class HotStarPrefixIE(InfoExtractor): 'url': 'hotstar:1000076273', 'only_matching': True, }, { - 'url': 'hotstar:movies:1000057157', + 'url': 'hotstar:movies:1260009879', 'info_dict': { - 'id': '1000057157', + 'id': '1260009879', 'ext': 'mp4', - 'title': 'Radha Gopalam', - 'description': 'md5:be3bc342cc120bbc95b3b0960e2b0d22', - 'timestamp': 1140805800, - 'upload_date': '20060224', - 'duration': 9182, - 'episode': 'Radha Gopalam', + 'title': 'Nuvvu Naaku Nachav', + 'description': 'md5:d43701b1314e6f8233ce33523c043b7d', + 'timestamp': 1567525674, + 'upload_date': '20190903', + 'duration': 10787, + 'episode': 'Nuvvu Naaku Nachav', }, }, { 'url': 'hotstar:episode:1000234847', @@ -289,7 +288,7 @@ class HotStarPrefixIE(InfoExtractor): class HotStarPlaylistIE(HotStarBaseIE): IE_NAME = 'hotstar:playlist' - _VALID_URL = r'https?://(?:www\.)?hotstar\.com/tv/[^/]+/s-\w+/list/[^/]+/t-(?P<id>\w+)' + _VALID_URL = r'https?://(?:www\.)?hotstar\.com(?:/in)?/tv(?:/[^/]+){2}/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': { @@ -299,22 +298,49 @@ 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/in/tv/karthika-deepam/15457/list/popular-clips/t-3_2_1272', + 'only_matching': True, }] def _real_extract(self, url): - playlist_id = self._match_id(url) + id_ = self._match_id(url) + return self.playlist_result( + self._playlist_entries('tray/find', id_, query={'tas': 10000, 'uqId': id_}), id_) - collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId')['body']['results'] - entries = [ - self.url_result(HotStarIE._video_url(video['contentId']), HotStarIE, video['contentId']) - for video in collection['assets']['items'] if video.get('contentId')] - return self.playlist_result(entries, playlist_id) +class HotStarSeasonIE(HotStarBaseIE): + IE_NAME = 'hotstar:season' + _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/tv/[^/]+/\w+)/seasons/[^/]+/ss-(?P<id>\w+)' + _TESTS = [{ + 'url': 'https://www.hotstar.com/tv/radhakrishn/1260000646/seasons/season-2/ss-8028', + 'info_dict': { + 'id': '8028', + }, + 'playlist_mincount': 35, + }, { + 'url': 'https://www.hotstar.com/in/tv/ishqbaaz/9567/seasons/season-2/ss-4357', + 'info_dict': { + 'id': '4357', + }, + 'playlist_mincount': 30, + }, { + 'url': 'https://www.hotstar.com/in/tv/bigg-boss/14714/seasons/season-4/ss-8208/', + 'info_dict': { + 'id': '8208', + }, + 'playlist_mincount': 19, + }] + + def _real_extract(self, url): + url, season_id = self._match_valid_url(url).groups() + return self.playlist_result(self._playlist_entries( + 'season/asset', season_id, url, query={'tao': 0, 'tas': 0, 'size': 10000, 'id': season_id}), season_id) class HotStarSeriesIE(HotStarBaseIE): IE_NAME = 'hotstar:series' - _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/tv/[^/]+/(?P<id>\d+))' + _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': { @@ -332,22 +358,13 @@ class HotStarSeriesIE(HotStarBaseIE): 'info_dict': { 'id': '435', }, - 'playlist_mincount': 269, + 'playlist_mincount': 267, }] 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( - f'{self._API_URL}/o/v1/show/detail?contentId={series_id}', series_id, headers=headers) - id = try_get(detail_json, lambda x: x['body']['results']['item']['id'], int) - item_json = self._download_json( - f'{self._API_URL}/o/v1/tray/g/1/items?etid=0&tao=0&tas=10000&eid={id}', series_id, headers=headers) - - return self.playlist_result([ - self.url_result(HotStarIE._video_url(video['contentId'], root=url), HotStarIE, video['contentId']) - for video in item_json['body']['results']['items'] if video.get('contentId') - ], series_id) + id_ = self._call_api_v1( + 'show/detail', series_id, query={'contentId': series_id})['body']['results']['item']['id'] + + return self.playlist_result(self._playlist_entries( + 'tray/g/1/items', series_id, url, query={'tao': 0, 'tas': 10000, 'etid': 0, 'eid': id_}), series_id) |