1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-13 17:16:16 +01:00
yt-dlp/yt_dlp/extractor/zee5.py
2021-08-23 00:50:40 +05:30

245 lines
10 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
parse_age_limit,
str_or_none,
try_get,
unified_strdate,
unified_timestamp,
url_or_none,
)
class Zee5IE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:
zee5:|
(?:https?://)(?:www\.)?zee5\.com/(?:[^#?]+/)?
(?:
(?:tvshows|kids|zee5originals)(?:/[^#/?]+){3}
|movies/[^#/?]+
)/(?P<display_id>[^#/?]+)/
)
(?P<id>[^#/?]+)/?(?:$|[?#])
'''
_TESTS = [{
'url': 'https://www.zee5.com/movies/details/krishna-the-birth/0-0-63098',
'info_dict': {
'id': '0-0-63098',
'ext': 'mp4',
'display_id': 'krishna-the-birth',
'title': 'Krishna - The Birth',
'duration': 4368,
'average_rating': 4,
'description': compat_str,
'alt_title': 'Krishna - The Birth',
'uploader': 'Zee Entertainment Enterprises Ltd',
'release_date': '20060101',
'upload_date': '20060101',
'timestamp': 1136073600,
'thumbnail': 'https://akamaividz.zee5.com/resources/0-0-63098/list/270x152/0063098_list_80888170.jpg',
'tags': list
},
'params': {
'format': 'bv',
},
}, {
'url': 'https://zee5.com/tvshows/details/krishna-balram/0-6-1871/episode-1-the-test-of-bramha/0-1-233402',
'info_dict': {
'id': '0-1-233402',
'ext': 'mp4',
'display_id': 'episode-1-the-test-of-bramha',
'title': 'Episode 1 - The Test Of Bramha',
'duration': 1336,
'average_rating': 4,
'description': compat_str,
'alt_title': 'Episode 1 - The Test Of Bramha',
'uploader': 'Zee Entertainment Enterprises Ltd',
'release_date': '20090101',
'upload_date': '20090101',
'timestamp': 1230768000,
'thumbnail': 'https://akamaividz.zee5.com/resources/0-1-233402/list/270x152/01233402_list.jpg',
'series': 'Krishna Balram',
'season_number': 1,
'episode_number': 1,
'tags': list,
},
'params': {
'format': 'bv',
},
}, {
'url': 'https://www.zee5.com/hi/tvshows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730?country=IN',
'only_matching': True
}, {
'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 = self._match_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')
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': asset_data['title'],
'formats': formats,
'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)
}
class Zee5SeriesIE(InfoExtractor):
IE_NAME = 'zee5:series'
_VALID_URL = r'''(?x)
(?:
zee5:series:|
(?:https?://)(?:www\.)?zee5\.com/(?:[^#?]+/)?
(?:tvshows|kids|zee5originals)(?:/[^#/?]+){2}/
)
(?P<id>[^#/?]+)/?(?:$|[?#])
'''
_TESTS = [{
'url': 'https://www.zee5.com/kids/kids-shows/krishna-balram/0-6-1871',
'playlist_mincount': 43,
'info_dict': {
'id': '0-6-1871',
},
}, {
'url': 'https://www.zee5.com/tvshows/details/bhabi-ji-ghar-par-hai/0-6-199',
'playlist_mincount': 1500,
'info_dict': {
'id': '0-6-199',
},
}, {
'url': 'https://www.zee5.com/tvshows/details/agent-raghav-crime-branch/0-6-965',
'playlist_mincount': 24,
'info_dict': {
'id': '0-6-965',
},
}, {
'url': 'https://www.zee5.com/ta/tvshows/details/nagabhairavi/0-6-3201',
'playlist_mincount': 3,
'info_dict': {
'id': '0-6-3201',
},
}, {
'url': 'https://www.zee5.com/global/hi/tvshows/details/khwaabon-ki-zamin-par/0-6-270',
'playlist_mincount': 150,
'info_dict': {
'id': '0-6-270',
},
}
]
def _entries(self, show_id):
access_token_request = self._download_json(
'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
show_id, note='Downloading access token')
headers = {
'X-Access-Token': access_token_request['token'],
'Referer': 'https://www.zee5.com/',
}
show_url = 'https://gwapi.zee5.com/content/tvshow/{}?translation=en&country=IN'.format(show_id)
page_num = 0
show_json = self._download_json(show_url, video_id=show_id, headers=headers)
for season in show_json.get('seasons') or []:
season_id = try_get(season, lambda x: x['id'], compat_str)
next_url = 'https://gwapi.zee5.com/content/tvshow/?season_id={}&type=episode&translation=en&country=IN&on_air=false&asset_subtype=tvshow&page=1&limit=100'.format(season_id)
while next_url:
page_num += 1
episodes_json = self._download_json(
next_url, video_id=show_id, headers=headers,
note='Downloading JSON metadata page %d' % page_num)
for episode in try_get(episodes_json, lambda x: x['episode'], list) or []:
video_id = episode.get('id')
yield self.url_result(
'zee5:%s' % video_id,
ie=Zee5IE.ie_key(), video_id=video_id)
next_url = url_or_none(episodes_json.get('next_episode_api'))
def _real_extract(self, url):
show_id = self._match_id(url)
return self.playlist_result(self._entries(show_id), playlist_id=show_id)