[yt-dlp.git] / youtube_dl / extractor / dcn.py

# coding: utf-8
from __future__ import unicode_literals

import re
import base64

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse,
    compat_urllib_request,
)
from ..utils import (
    int_or_none,
    parse_iso8601,
    smuggle_url,
    unsmuggle_url,
)


class DCNGeneralIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'

    def _real_extract(self, url):
        show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
        url = ''
        ie_key = ''
        if video_id and int(video_id) > 0:
            return self.url_result('http://www.dcndigital.ae/#/media/%s' % video_id, 'DCNVideo')
        else:
            if season_id and int(season_id) > 0:
                url = smuggle_url('http://www.dcndigital.ae/#/program/season/%s' % season_id, {'show_id': show_id})
            else:
                url = 'http://www.dcndigital.ae/#/program/%s' % show_id
            return self.url_result(url, 'DCNSeason')


class DCNVideoIE(InfoExtractor):
    IE_NAME = 'dcn:video'
    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
    _TEST = {
        'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375',
        'info_dict':
        {
            'id': '17375',
            'ext': 'mp4',
            'title': 'رحلة العمر : الحلقة 1',
            'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
            'thumbnail': 're:^https?://.*\.jpg$',
            'duration': 2041,
            'timestamp': 1227504126,
            'upload_date': '20081124',
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }

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

        request = compat_urllib_request.Request(
            'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
            headers={'Origin': 'http://www.dcndigital.ae'})

        video = self._download_json(request, video_id)
        title = video.get('title_en') or video['title_ar']
        img = video.get('img')
        thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
        duration = int_or_none(video.get('duration'))
        description = video.get('description_en') or video.get('description_ar')
        timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')

        webpage = self._download_webpage(
            'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?'
            + compat_urllib_parse.urlencode({
                'id': video['id'],
                'user_id': video['user_id'],
                'signature': video['signature'],
                'countries': 'Q0M=',
                'filter': 'DENY',
            }), video_id)

        m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
        formats = self._extract_m3u8_formats(
            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')

        rtsp_url = self._search_regex(
            r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
        if rtsp_url:
            formats.append({
                'url': rtsp_url,
                'format_id': 'rtsp',
            })

        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': title,
            'description': description,
            'thumbnail': thumbnail,
            'duration': duration,
            'timestamp': timestamp,
            'formats': formats,
        }


class DCNLiveIE(InfoExtractor):
    IE_NAME = 'dcn:live'
    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)'
    _TEST = {
        'url': 'http://www.dcndigital.ae/#/live/6/dubai-tv',
        'info_dict':
        {
            'id': '6',
            'ext': 'mp4',
            'title': 're:^Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
            'thumbnail': 're:^https?://.*\.png$',
            'is_live': True,
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }

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

        request = compat_urllib_request.Request(
            'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
            headers={'Origin': 'http://www.dcndigital.ae'})

        channel = self._download_json(request, channel_id)
        title = channel.get('title_en') or channel['title_ar']
        img = channel.get('thumbnail')
        thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
        description = channel.get('description_en') or channel.get('description_ar')
        timestamp = parse_iso8601(channel.get('create_time') or channel.get('update_time'), ' ')

        webpage = self._download_webpage(
            'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
            compat_urllib_parse.urlencode({
                'id': base64.b64encode(channel['user_id'].encode()).decode(),
                'channelid': base64.b64encode(channel['id'].encode()).decode(),
                'signature': channel['signature'],
                'countries': 'Q0M=',
                'filter': 'DENY',
            }), channel_id)

        m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
        formats = self._extract_m3u8_formats(
            m3u8_url, channel_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')

        rtsp_url = self._search_regex(
            r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
        if rtsp_url:
            formats.append({
                'url': rtsp_url,
                'format_id': 'rtsp',
            })

        self._sort_formats(formats)

        return {
            'id': channel_id,
            'title': self._live_title(title),
            'description': description,
            'thumbnail': thumbnail,
            'formats': formats,
            'is_live': True,
        }


class DCNSeasonIE(InfoExtractor):
    IE_NAME = 'dcn:season'
    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
    _TEST = {
        'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A',
        'info_dict':
        {
            'id': '7910',
            'title': 'محاضرات الشيخ الشعراوي',
        },
        'playlist_mincount': 27,
    }

    def _real_extract(self, url):
        url, smuggled_data = unsmuggle_url(url, {})
        show_id, season_id = re.match(self._VALID_URL, url).groups()

        data = {}
        if season_id:
            data['season'] = season_id
            show_id = smuggled_data.get('show_id')
            if show_id is None:
                request = compat_urllib_request.Request(
                    'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
                    headers={'Origin': 'http://www.dcndigital.ae'})
                season = self._download_json(request, season_id)
                show_id = season['id']
        data['show_id'] = show_id
        request = compat_urllib_request.Request(
            'http://admin.mangomolo.com/analytics/index.php/plus/show',
            compat_urllib_parse.urlencode(data),
            {
                'Origin': 'http://www.dcndigital.ae',
                'Content-Type': 'application/x-www-form-urlencoded'
            })

        show = self._download_json(request, show_id)
        season_id = season_id or show['default_season']
        season = {}
        for _ in show['seasons']:
            if _['id'] == season_id:
                season = _
                break
        title = season.get('title_en') or season['title_ar']

        entries = []
        for video in show['videos']:
            entries.append(self.url_result('http://www.dcndigital.ae/#/media/%s' % video['id'], 'DCNVideo'))

        return self.playlist_result(entries, season_id, title)
Commit	Line	Data
cd6b555e	1	# coding: utf-8
	2	from __future__ import unicode_literals
	3
9f4921bf	4	import re
8e2898ed	5	import base64
9f4921bf	6
3af1fac7	7	from .common import InfoExtractor
f94639fa S	8	from ..compat import (
	9	compat_urllib_parse,
	10	compat_urllib_request,
	11	)
	12	from ..utils import (
	13	int_or_none,
	14	parse_iso8601,
b477da20	15	smuggle_url,
b477da20	16	unsmuggle_url,
f94639fa	17	)
cd6b555e	18
3af1fac7	19
9f4921bf	20	class DCNGeneralIE(InfoExtractor):
	21	_VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
	22
	23	def _real_extract(self, url):
	24	show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
	25	url = ''
	26	ie_key = ''
	27	if video_id and int(video_id) > 0:
48637515	28	return self.url_result('http://www.dcndigital.ae/#/media/%s' % video_id, 'DCNVideo')
9f4921bf	29	else:
9f4921bf	30	if season_id and int(season_id) > 0:
b477da20	31	url = smuggle_url('http://www.dcndigital.ae/#/program/season/%s' % season_id, {'show_id': show_id})
9f4921bf	32	else:
9f4921bf	33	url = 'http://www.dcndigital.ae/#/program/%s' % show_id
48637515	34	return self.url_result(url, 'DCNSeason')
9f4921bf	35
	36
	37	class DCNVideoIE(InfoExtractor):
b477da20	38	IE_NAME = 'dcn:video'
8e2898ed	39	_VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+\|media\|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
3af1fac7	40	_TEST = {
9f4921bf	41	'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375',
3af1fac7	42	'info_dict':
	43	{
	44	'id': '17375',
f94639fa	45	'ext': 'mp4',
3af1fac7	46	'title': 'رحلة العمر : الحلقة 1',
f94639fa S	47	'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
	48	'thumbnail': 're:^https?://.*\.jpg$',
	49	'duration': 2041,
	50	'timestamp': 1227504126,
	51	'upload_date': '20081124',
cd6b555e	52	},
	53	'params': {
	54	# m3u8 download
	55	'skip_download': True,
	56	},
3af1fac7	57	}
	58
	59	def _real_extract(self, url):
	60	video_id = self._match_id(url)
f94639fa	61
cd6b555e	62	request = compat_urllib_request.Request(
f94639fa S	63	'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
	64	headers={'Origin': 'http://www.dcndigital.ae'})
	65
	66	video = self._download_json(request, video_id)
	67	title = video.get('title_en') or video['title_ar']
48637515	68	img = video.get('img')
	69	thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
	70	duration = int_or_none(video.get('duration'))
	71	description = video.get('description_en') or video.get('description_ar')
	72	timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')
f94639fa	73
3af1fac7	74	webpage = self._download_webpage(
f94639fa S	75	'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?'
	76	+ compat_urllib_parse.urlencode({
	77	'id': video['id'],
	78	'user_id': video['user_id'],
	79	'signature': video['signature'],
	80	'countries': 'Q0M=',
	81	'filter': 'DENY',
	82	}), video_id)
	83
	84	m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
	85	formats = self._extract_m3u8_formats(
	86	m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
	87
	88	rtsp_url = self._search_regex(
	89	r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
	90	if rtsp_url:
	91	formats.append({
	92	'url': rtsp_url,
	93	'format_id': 'rtsp',
	94	})
	95
	96	self._sort_formats(formats)
	97
3af1fac7	98	return {
	99	'id': video_id,
	100	'title': title,
f94639fa	101	'description': description,
3af1fac7	102	'thumbnail': thumbnail,
3af1fac7	103	'duration': duration,
f94639fa	104	'timestamp': timestamp,
3af1fac7	105	'formats': formats,
3af1fac7	106	}
9f4921bf	107
9f4921bf	108
8e2898ed	109	class DCNLiveIE(InfoExtractor):
	110	IE_NAME = 'dcn:live'
	111	_VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)'
	112	_TEST = {
	113	'url': 'http://www.dcndigital.ae/#/live/6/dubai-tv',
	114	'info_dict':
	115	{
	116	'id': '6',
	117	'ext': 'mp4',
48637515	118	'title': 're:^Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
	119	'thumbnail': 're:^https?://.*\.png$',
	120	'is_live': True,
8e2898ed	121	},
	122	'params': {
	123	# m3u8 download
	124	'skip_download': True,
	125	},
	126	}
	127
	128	def _real_extract(self, url):
	129	channel_id = self._match_id(url)
	130
	131	request = compat_urllib_request.Request(
	132	'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
	133	headers={'Origin': 'http://www.dcndigital.ae'})
	134
	135	channel = self._download_json(request, channel_id)
	136	title = channel.get('title_en') or channel['title_ar']
48637515	137	img = channel.get('thumbnail')
	138	thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
	139	description = channel.get('description_en') or channel.get('description_ar')
	140	timestamp = parse_iso8601(channel.get('create_time') or channel.get('update_time'), ' ')
8e2898ed	141
8e2898ed	142	webpage = self._download_webpage(
48637515	143	'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
48637515	144	compat_urllib_parse.urlencode({
8e2898ed	145	'id': base64.b64encode(channel['user_id'].encode()).decode(),
	146	'channelid': base64.b64encode(channel['id'].encode()).decode(),
	147	'signature': channel['signature'],
	148	'countries': 'Q0M=',
	149	'filter': 'DENY',
	150	}), channel_id)
	151
	152	m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
	153	formats = self._extract_m3u8_formats(
	154	m3u8_url, channel_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
	155
	156	rtsp_url = self._search_regex(
	157	r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
	158	if rtsp_url:
	159	formats.append({
	160	'url': rtsp_url,
	161	'format_id': 'rtsp',
	162	})
	163
	164	self._sort_formats(formats)
	165
	166	return {
	167	'id': channel_id,
48637515	168	'title': self._live_title(title),
	169	'description': description,
	170	'thumbnail': thumbnail,
8e2898ed	171	'formats': formats,
	172	'is_live': True,
	173	}
	174
	175
b477da20	176	class DCNSeasonIE(InfoExtractor):
b477da20	177	IE_NAME = 'dcn:season'
9f4921bf	178	_VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)\|season/(?P<season_id>\d+))'
	179	_TEST = {
	180	'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A',
	181	'info_dict':
	182	{
b477da20	183	'id': '7910',
9f4921bf	184	'title': 'محاضرات الشيخ الشعراوي',
9f4921bf	185	},
	186	'playlist_mincount': 27,
	187	}
	188
	189	def _real_extract(self, url):
b477da20	190	url, smuggled_data = unsmuggle_url(url, {})
9f4921bf	191	show_id, season_id = re.match(self._VALID_URL, url).groups()
48637515	192
9f4921bf	193	data = {}
9f4921bf	194	if season_id:
9f4921bf	195	data['season'] = season_id
b477da20	196	show_id = smuggled_data.get('show_id')
	197	if show_id is None:
	198	request = compat_urllib_request.Request(
	199	'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
	200	headers={'Origin': 'http://www.dcndigital.ae'})
	201	season = self._download_json(request, season_id)
	202	show_id = season['id']
9f4921bf	203	data['show_id'] = show_id
	204	request = compat_urllib_request.Request(
	205	'http://admin.mangomolo.com/analytics/index.php/plus/show',
	206	compat_urllib_parse.urlencode(data),
	207	{
	208	'Origin': 'http://www.dcndigital.ae',
	209	'Content-Type': 'application/x-www-form-urlencoded'
	210	})
48637515	211
9f4921bf	212	show = self._download_json(request, show_id)
b477da20	213	season_id = season_id or show['default_season']
48637515	214	season = {}
	215	for _ in show['seasons']:
	216	if _['id'] == season_id:
	217	season = _
	218	break
	219	title = season.get('title_en') or season['title_ar']
	220
9f4921bf	221	entries = []
9f4921bf	222	for video in show['videos']:
48637515	223	entries.append(self.url_result('http://www.dcndigital.ae/#/media/%s' % video['id'], 'DCNVideo'))
	224
	225	return self.playlist_result(entries, season_id, title)