[yt-dlp.git] / yt_dlp / extractor / shahid.py

import json
import math
import re

from .aws import AWSIE
from ..networking.exceptions import HTTPError
from ..utils import (
    ExtractorError,
    InAdvancePagedList,
    clean_html,
    int_or_none,
    parse_iso8601,
    str_or_none,
    urlencode_postdata,
)


class ShahidBaseIE(AWSIE):
    _AWS_PROXY_HOST = 'api2.shahid.net'
    _AWS_API_KEY = '2RRtuMHx95aNI1Kvtn2rChEuwsCogUd4samGPjLh'
    _VALID_URL_BASE = r'https?://shahid\.mbc\.net/[a-z]{2}/'

    def _handle_error(self, e):
        fail_data = self._parse_json(
            e.cause.response.read().decode('utf-8'), None, fatal=False)
        if fail_data:
            faults = fail_data.get('faults', [])
            faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
            if faults_message:
                raise ExtractorError(faults_message, expected=True)

    def _call_api(self, path, video_id, request=None):
        query = {}
        if request:
            query['request'] = json.dumps(request)
        try:
            return self._aws_execute_api({
                'uri': '/proxy/v2/' + path,
                'access_key': 'AKIAI6X4TYCIXM2B7MUQ',
                'secret_key': '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',
            }, video_id, query)
        except ExtractorError as e:
            if isinstance(e.cause, HTTPError):
                self._handle_error(e)
            raise


class ShahidIE(ShahidBaseIE):
    _NETRC_MACHINE = 'shahid'
    _VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
    _TESTS = [{
        'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AA%D8%AD%D9%81-%D8%A7%D9%84%D8%AF%D8%AD%D9%8A%D8%AD-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-816924',
        'info_dict': {
            'id': '816924',
            'ext': 'mp4',
            'title': 'متحف الدحيح الموسم 1 كليب 1',
            'timestamp': 1602806400,
            'upload_date': '20201016',
            'description': 'برومو',
            'duration': 22,
            'categories': ['كوميديا'],
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        }
    }, {
        'url': 'https://shahid.mbc.net/ar/movies/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9/movie-151746',
        'only_matching': True
    }, {
        # shahid plus subscriber only
        'url': 'https://shahid.mbc.net/ar/series/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/episode-90511',
        'only_matching': True
    }, {
        'url': 'https://shahid.mbc.net/en/shows/Ramez-Fi-Al-Shallal-season-1-episode-1/episode-359319',
        'only_matching': True
    }]

    def _perform_login(self, username, password):
        try:
            user_data = self._download_json(
                'https://shahid.mbc.net/wd/service/users/login',
                None, 'Logging in', data=json.dumps({
                    'email': username,
                    'password': password,
                    'basic': 'false',
                }).encode('utf-8'), headers={
                    'Content-Type': 'application/json; charset=UTF-8',
                })['user']
        except ExtractorError as e:
            if isinstance(e.cause, HTTPError):
                self._handle_error(e)
            raise

        self._download_webpage(
            'https://shahid.mbc.net/populateContext',
            None, 'Populate Context', data=urlencode_postdata({
                'firstName': user_data['firstName'],
                'lastName': user_data['lastName'],
                'userName': user_data['email'],
                'csg_user_name': user_data['email'],
                'subscriberId': user_data['id'],
                'sessionId': user_data['sessionId'],
            }))

    def _real_extract(self, url):
        page_type, video_id = self._match_valid_url(url).groups()
        if page_type == 'clip':
            page_type = 'episode'

        playout = self._call_api(
            'playout/new/url/' + video_id, video_id)['playout']

        if not self.get_param('allow_unplayable_formats') and playout.get('drm'):
            self.report_drm(video_id)

        formats = self._extract_m3u8_formats(re.sub(
            # https://docs.aws.amazon.com/mediapackage/latest/ug/manifest-filtering.html
            r'aws\.manifestfilter=[\w:;,-]+&?',
            '', playout['url']), video_id, 'mp4')

        # video = self._call_api(
        #     'product/id', video_id, {
        #         'id': video_id,
        #         'productType': 'ASSET',
        #         'productSubType': page_type.upper()
        #     })['productModel']

        response = self._download_json(
            'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id),
            video_id, 'Downloading video JSON', query={
                'apiKey': 'sh@hid0nlin3',
                'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
            })
        data = response.get('data', {})
        error = data.get('error')
        if error:
            raise ExtractorError(
                '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
                expected=True)

        video = data[page_type]
        title = video['title']
        categories = [
            category['name']
            for category in video.get('genres', []) if 'name' in category]

        return {
            'id': video_id,
            'title': title,
            'description': video.get('description'),
            'thumbnail': video.get('thumbnailUrl'),
            'duration': int_or_none(video.get('duration')),
            'timestamp': parse_iso8601(video.get('referenceDate')),
            'categories': categories,
            'series': video.get('showTitle') or video.get('showName'),
            'season': video.get('seasonTitle'),
            'season_number': int_or_none(video.get('seasonNumber')),
            'season_id': str_or_none(video.get('seasonId')),
            'episode_number': int_or_none(video.get('number')),
            'episode_id': video_id,
            'formats': formats,
        }


class ShahidShowIE(ShahidBaseIE):
    _VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
    _TESTS = [{
        'url': 'https://shahid.mbc.net/ar/shows/%D8%B1%D8%A7%D9%85%D8%B2-%D9%82%D8%B1%D8%B4-%D8%A7%D9%84%D8%A8%D8%AD%D8%B1/show-79187',
        'info_dict': {
            'id': '79187',
            'title': 'رامز قرش البحر',
            'description': 'md5:c88fa7e0f02b0abd39d417aee0d046ff',
        },
        'playlist_mincount': 32,
    }, {
        'url': 'https://shahid.mbc.net/ar/series/How-to-live-Longer-(The-Big-Think)/series-291861',
        'only_matching': True
    }]
    _PAGE_SIZE = 30

    def _real_extract(self, url):
        show_id = self._match_id(url)

        product = self._call_api(
            'playableAsset', show_id, {'showId': show_id})['productModel']
        playlist = product['playlist']
        playlist_id = playlist['id']
        show = product.get('show', {})

        def page_func(page_num):
            playlist = self._call_api(
                'product/playlist', show_id, {
                    'playListId': playlist_id,
                    'pageNumber': page_num,
                    'pageSize': 30,
                    'sorts': [{
                        'order': 'DESC',
                        'type': 'SORTDATE'
                    }],
                })
            for product in playlist.get('productList', {}).get('products', []):
                product_url = product.get('productUrl', []).get('url')
                if not product_url:
                    continue
                yield self.url_result(
                    product_url, 'Shahid',
                    str_or_none(product.get('id')),
                    product.get('title'))

        entries = InAdvancePagedList(
            page_func,
            math.ceil(playlist['count'] / self._PAGE_SIZE),
            self._PAGE_SIZE)

        return self.playlist_result(
            entries, show_id, show.get('title'), show.get('description'))
Commit	Line	Data
3b4b66b5	1	import json
78466fca RA	2	import math
78466fca RA	3	import re
3b4b66b5	4
78466fca	5	from .aws import AWSIE
3d2623a8	6	from ..networking.exceptions import HTTPError
02c126a7	7	from ..utils import (
02c126a7	8	ExtractorError,
78466fca	9	InAdvancePagedList,
e897bd82	10	clean_html,
c576ef1e S	11	int_or_none,
c576ef1e S	12	parse_iso8601,
41aa4425	13	str_or_none,
3b4b66b5	14	urlencode_postdata,
84c0ed50	15	)
114ed20e	16
3be3c622	17
78466fca RA	18	class ShahidBaseIE(AWSIE):
	19	_AWS_PROXY_HOST = 'api2.shahid.net'
	20	_AWS_API_KEY = '2RRtuMHx95aNI1Kvtn2rChEuwsCogUd4samGPjLh'
b73612a2	21	_VALID_URL_BASE = r'https?://shahid\.mbc\.net/[a-z]{2}/'
78466fca RA	22
	23	def _handle_error(self, e):
	24	fail_data = self._parse_json(
3d2623a8	25	e.cause.response.read().decode('utf-8'), None, fatal=False)
78466fca RA	26	if fail_data:
	27	faults = fail_data.get('faults', [])
	28	faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
	29	if faults_message:
	30	raise ExtractorError(faults_message, expected=True)
	31
	32	def _call_api(self, path, video_id, request=None):
	33	query = {}
	34	if request:
	35	query['request'] = json.dumps(request)
	36	try:
	37	return self._aws_execute_api({
	38	'uri': '/proxy/v2/' + path,
	39	'access_key': 'AKIAI6X4TYCIXM2B7MUQ',
	40	'secret_key': '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',
	41	}, video_id, query)
	42	except ExtractorError as e:
3d2623a8	43	if isinstance(e.cause, HTTPError):
78466fca RA	44	self._handle_error(e)
	45	raise
	46
	47
	48	class ShahidIE(ShahidBaseIE):
3b4b66b5	49	_NETRC_MACHINE = 'shahid'
b73612a2	50	_VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:serie\|show\|movie)s/[^/]+/(?P<type>episode\|clip\|movie)-(?P<id>\d+)'
c576ef1e	51	_TESTS = [{
10db0d2f	52	'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AA%D8%AD%D9%81-%D8%A7%D9%84%D8%AF%D8%AD%D9%8A%D8%AD-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-816924',
c576ef1e	53	'info_dict': {
10db0d2f	54	'id': '816924',
5de5ab89	55	'ext': 'mp4',
10db0d2f	56	'title': 'متحف الدحيح الموسم 1 كليب 1',
	57	'timestamp': 1602806400,
	58	'upload_date': '20201016',
	59	'description': 'برومو',
	60	'duration': 22,
	61	'categories': ['كوميديا'],
114ed20e	62	},
c576ef1e S	63	'params': {
	64	# m3u8 download
	65	'skip_download': True,
114ed20e	66	}
3b4b66b5	67	}, {
414e7094	68	'url': 'https://shahid.mbc.net/ar/movies/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9/movie-151746',
3b4b66b5	69	'only_matching': True
c576ef1e S	70	}, {
c576ef1e S	71	# shahid plus subscriber only
414e7094	72	'url': 'https://shahid.mbc.net/ar/series/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/episode-90511',
c576ef1e	73	'only_matching': True
b73612a2	74	}, {
	75	'url': 'https://shahid.mbc.net/en/shows/Ramez-Fi-Al-Shallal-season-1-episode-1/episode-359319',
	76	'only_matching': True
c576ef1e	77	}]
114ed20e	78
52efa4b3	79	def _perform_login(self, username, password):
78466fca RA	80	try:
	81	user_data = self._download_json(
	82	'https://shahid.mbc.net/wd/service/users/login',
	83	None, 'Logging in', data=json.dumps({
52efa4b3	84	'email': username,
78466fca RA	85	'password': password,
	86	'basic': 'false',
	87	}).encode('utf-8'), headers={
	88	'Content-Type': 'application/json; charset=UTF-8',
	89	})['user']
	90	except ExtractorError as e:
3d2623a8	91	if isinstance(e.cause, HTTPError):
78466fca RA	92	self._handle_error(e)
78466fca RA	93	raise
414e7094	94
3b4b66b5 RA	95	self._download_webpage(
	96	'https://shahid.mbc.net/populateContext',
	97	None, 'Populate Context', data=urlencode_postdata({
	98	'firstName': user_data['firstName'],
	99	'lastName': user_data['lastName'],
	100	'userName': user_data['email'],
	101	'csg_user_name': user_data['email'],
	102	'subscriberId': user_data['id'],
	103	'sessionId': user_data['sessionId'],
	104	}))
	105
114ed20e	106	def _real_extract(self, url):
5ad28e7f	107	page_type, video_id = self._match_valid_url(url).groups()
414e7094 RA	108	if page_type == 'clip':
414e7094 RA	109	page_type = 'episode'
c576ef1e	110
78466fca	111	playout = self._call_api(
10db0d2f	112	'playout/new/url/' + video_id, video_id)['playout']
a62fd1af	113
a06916d9	114	if not self.get_param('allow_unplayable_formats') and playout.get('drm'):
88acdbc2	115	self.report_drm(video_id)
2334762b	116
10db0d2f	117	formats = self._extract_m3u8_formats(re.sub(
	118	# https://docs.aws.amazon.com/mediapackage/latest/ug/manifest-filtering.html
	119	r'aws\.manifestfilter=[\w:;,-]+&?',
	120	'', playout['url']), video_id, 'mp4')
3be3c622	121
78466fca RA	122	# video = self._call_api(
	123	# 'product/id', video_id, {
	124	# 'id': video_id,
	125	# 'productType': 'ASSET',
	126	# 'productSubType': page_type.upper()
	127	# })['productModel']
	128
	129	response = self._download_json(
3b4b66b5 RA	130	'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id),
	131	video_id, 'Downloading video JSON', query={
	132	'apiKey': 'sh@hid0nlin3',
	133	'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
78466fca RA	134	})
	135	data = response.get('data', {})
	136	error = data.get('error')
	137	if error:
	138	raise ExtractorError(
	139	'%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
	140	expected=True)
c576ef1e	141
78466fca	142	video = data[page_type]
c576ef1e	143	title = video['title']
c576ef1e S	144	categories = [
	145	category['name']
	146	for category in video.get('genres', []) if 'name' in category]
a62fd1af	147
114ed20e	148	return {
	149	'id': video_id,
	150	'title': title,
41aa4425 RA	151	'description': video.get('description'),
	152	'thumbnail': video.get('thumbnailUrl'),
	153	'duration': int_or_none(video.get('duration')),
	154	'timestamp': parse_iso8601(video.get('referenceDate')),
c576ef1e	155	'categories': categories,
41aa4425 RA	156	'series': video.get('showTitle') or video.get('showName'),
	157	'season': video.get('seasonTitle'),
	158	'season_number': int_or_none(video.get('seasonNumber')),
	159	'season_id': str_or_none(video.get('seasonId')),
	160	'episode_number': int_or_none(video.get('number')),
	161	'episode_id': video_id,
114ed20e	162	'formats': formats,
114ed20e	163	}
78466fca RA	164
	165
	166	class ShahidShowIE(ShahidBaseIE):
b73612a2	167	_VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:show\|serie)s/[^/]+/(?:show\|series)-(?P<id>\d+)'
78466fca RA	168	_TESTS = [{
	169	'url': 'https://shahid.mbc.net/ar/shows/%D8%B1%D8%A7%D9%85%D8%B2-%D9%82%D8%B1%D8%B4-%D8%A7%D9%84%D8%A8%D8%AD%D8%B1/show-79187',
	170	'info_dict': {
	171	'id': '79187',
	172	'title': 'رامز قرش البحر',
	173	'description': 'md5:c88fa7e0f02b0abd39d417aee0d046ff',
	174	},
	175	'playlist_mincount': 32,
	176	}, {
	177	'url': 'https://shahid.mbc.net/ar/series/How-to-live-Longer-(The-Big-Think)/series-291861',
	178	'only_matching': True
	179	}]
	180	_PAGE_SIZE = 30
	181
	182	def _real_extract(self, url):
	183	show_id = self._match_id(url)
	184
	185	product = self._call_api(
	186	'playableAsset', show_id, {'showId': show_id})['productModel']
	187	playlist = product['playlist']
	188	playlist_id = playlist['id']
	189	show = product.get('show', {})
	190
	191	def page_func(page_num):
	192	playlist = self._call_api(
	193	'product/playlist', show_id, {
	194	'playListId': playlist_id,
	195	'pageNumber': page_num,
	196	'pageSize': 30,
	197	'sorts': [{
	198	'order': 'DESC',
	199	'type': 'SORTDATE'
	200	}],
	201	})
	202	for product in playlist.get('productList', {}).get('products', []):
	203	product_url = product.get('productUrl', []).get('url')
	204	if not product_url:
	205	continue
	206	yield self.url_result(
	207	product_url, 'Shahid',
	208	str_or_none(product.get('id')),
	209	product.get('title'))
	210
	211	entries = InAdvancePagedList(
	212	page_func,
	213	math.ceil(playlist['count'] / self._PAGE_SIZE),
	214	self._PAGE_SIZE)
	215
	216	return self.playlist_result(
	217	entries, show_id, show.get('title'), show.get('description'))