[Zee5] Fix extractor and add subtitles (#733)

Closes #728
Authored by Ashish0804

1 files changed, 77 insertions, 37 deletions

diff --git a/yt_dlp/extractor/zee5.py b/yt_dlp/extractor/zee5.py
index e12c4e59b..7b08c77fc 100644
--- a/yt_dlp/extractor/zee5.py
+++ b/yt_dlp/extractor/zee5.py
@@ -1,11 +1,13 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
+    ExtractorError,
     int_or_none,
     parse_age_limit,
     str_or_none,
@@ -60,7 +62,7 @@ class Zee5IE(InfoExtractor):
             'average_rating': 4,
             'description': compat_str,
             'alt_title': 'Episode 1 - The Test Of Bramha',
-            'uploader': 'Green Gold',
+            'uploader': 'Zee Entertainment Enterprises Ltd',
             'release_date': '20090101',
             'upload_date': '20090101',
             'timestamp': 1230768000,
@@ -80,53 +82,91 @@ class Zee5IE(InfoExtractor):
         'url': 'https://www.zee5.com/global/hi/tvshows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730',
         'only_matching': True
     }]
+    _DETAIL_API_URL = 'https://spapi.zee5.com/singlePlayback/getDetails?content_id={}&device_id={}&platform_name=desktop_web&country=IN&check_parental_control=false'
+    _DEVICE_ID = 'iIxsxYf40cqO3koIkwzKHZhnJzHN13zb'
+    _USER_TOKEN = None
+    _LOGIN_HINT = 'Use "--username <mobile_number>" to login using otp or "--username token" and "--password <user_token>" to login using user token.'
+    _NETRC_MACHINE = 'zee5'
+
+    def _login(self):
+        username, password = self._get_login_info()
+        if username:
+            if len(username) == 10 and username.isdigit() and self._USER_TOKEN is None:
+                self.report_login()
+                otp_request_json = self._download_json('https://b2bapi.zee5.com/device/sendotp_v1.php?phoneno=91{}'.format(username),
+                                                       None, note='Sending OTP')
+                if otp_request_json['code'] == 0:
+                    self.to_screen(otp_request_json['message'])
+                else:
+                    raise ExtractorError(otp_request_json['message'], expected=True)
+                otp_code = self._get_tfa_info('OTP')
+                otp_verify_json = self._download_json('https://b2bapi.zee5.com/device/verifyotp_v1.php?phoneno=91{}&otp={}&guest_token={}&platform=web'.format(username, otp_code, self._DEVICE_ID),
+                                                      None, note='Verifying OTP', fatal=False)
+                if not otp_verify_json:
+                    raise ExtractorError('Unable to verify OTP.', expected=True)
+                self._USER_TOKEN = otp_verify_json.get('token')
+                if not self._USER_TOKEN:
+                    raise ExtractorError(otp_request_json['message'], expected=True)
+            elif username.lower() == 'token' and len(password) > 1198:
+                self._USER_TOKEN = password
+
+    def _real_initialize(self):
+        self._login()
 
     def _real_extract(self, url):
         video_id, display_id = re.match(self._VALID_URL, url).group('id', 'display_id')
         access_token_request = self._download_json(
             'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
             video_id, note='Downloading access token')
-        token_request = self._download_json(
-            'https://useraction.zee5.com/tokennd',
-            video_id, note='Downloading video token')
-        json_data = self._download_json(
-            'https://gwapi.zee5.com/content/details/{}?translation=en&country=IN'.format(video_id),
-            video_id, headers={'X-Access-Token': access_token_request['token']})
-        m3u8_url = try_get(
-            json_data,
-            (lambda x: x['hls'][0], lambda x: x['video_details']['hls_url']),
-            compat_str)
-        formats = self._extract_m3u8_formats(
-            'https://zee5vodnd.akamaized.net' + m3u8_url.replace('/drm', '/hls', 1) + token_request['video_token'],
-            video_id, 'mp4', fatal=False)
-        mpd_url = try_get(
-            json_data,
-            (lambda x: x['video'][0], lambda x: x['video_details']['url']),
-            compat_str)
-        formats += self._extract_mpd_formats(
-            'https://zee5vod.akamaized.net' + mpd_url,
-            video_id, fatal=False)
+        data = {
+            'x-access-token': access_token_request['token']
+        }
+        if self._USER_TOKEN:
+            data['Authorization'] = 'bearer %s' % self._USER_TOKEN
+        else:
+            data['X-Z5-Guest-Token'] = self._DEVICE_ID
 
+        json_data = self._download_json(
+            self._DETAIL_API_URL.format(video_id, self._DEVICE_ID),
+            video_id, headers={'content-type': 'application/json'}, data=json.dumps(data).encode('utf-8'))
+        asset_data = json_data['assetDetails']
+        show_data = json_data.get('showDetails', {})
+        if 'premium' in asset_data['business_type']:
+            raise ExtractorError('Premium content is DRM protected.', expected=True)
+        if not asset_data.get('hls_url'):
+            self.raise_login_required(self._LOGIN_HINT, metadata_available=True, method=None)
+        formats, m3u8_subs = self._extract_m3u8_formats_and_subtitles(asset_data['hls_url'], video_id, 'mp4', fatal=False)
         self._sort_formats(formats)
+
+        subtitles = {}
+        for sub in asset_data.get('subtitle_url', []):
+            sub_url = sub.get('url')
+            if not sub_url:
+                continue
+            subtitles.setdefault(sub.get('language', 'en'), []).append({
+                'url': self._proto_relative_url(sub_url),
+            })
+        subtitles = self._merge_subtitles(subtitles, m3u8_subs)
         return {
             'id': video_id,
             'display_id': display_id,
-            'title': json_data['title'],
+            'title': asset_data['title'],
             'formats': formats,
-            'duration': int_or_none(json_data.get('duration')),
-            'average_rating': int_or_none(json_data.get('rating')),
-            'description': str_or_none(json_data.get('description')),
-            'alt_title': str_or_none(json_data.get('original_title')),
-            'uploader': str_or_none(json_data.get('content_owner')),
-            'age_limit': parse_age_limit(json_data.get('age_rating')),
-            'release_date': unified_strdate(json_data.get('release_date')),
-            'timestamp': unified_timestamp(json_data.get('release_date')),
-            'thumbnail': url_or_none(json_data.get('image_url')),
-            'series': try_get(json_data, lambda x: x['tvshow_details']['title'], str),
-            'season': try_get(json_data, lambda x: x['season_details']['title'], str),
-            'season_number': int_or_none(try_get(json_data, lambda x: x['season_details']['index'])),
-            'episode_number': int_or_none(try_get(json_data, lambda x: x['index'])),
-            'tags': try_get(json_data, lambda x: x['tags'], list)
+            'subtitles': subtitles,
+            'duration': int_or_none(asset_data.get('duration')),
+            'average_rating': int_or_none(asset_data.get('rating')),
+            'description': str_or_none(asset_data.get('description')),
+            'alt_title': str_or_none(asset_data.get('original_title')),
+            'uploader': str_or_none(asset_data.get('content_owner')),
+            'age_limit': parse_age_limit(asset_data.get('age_rating')),
+            'release_date': unified_strdate(asset_data.get('release_date')),
+            'timestamp': unified_timestamp(asset_data.get('release_date')),
+            'thumbnail': url_or_none(asset_data.get('image_url')),
+            'series': str_or_none(asset_data.get('tvshow_name')),
+            'season': try_get(show_data, lambda x: x['seasons']['title'], str),
+            'season_number': int_or_none(try_get(show_data, lambda x: x['seasons'][0]['orderid'])),
+            'episode_number': int_or_none(try_get(asset_data, lambda x: x['orderid'])),
+            'tags': try_get(asset_data, lambda x: x['tags'], list)
         }
 
 
@@ -154,7 +194,7 @@ class Zee5SeriesIE(InfoExtractor):
         },
     }, {
         'url': 'https://www.zee5.com/tvshows/details/agent-raghav-crime-branch/0-6-965',
-        'playlist_mincount': 25,
+        'playlist_mincount': 24,
         'info_dict': {
             'id': '0-6-965',
         },