[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:
            url = 'http://www.dcndigital.ae/#/media/%s' % video_id
            ie_key = 'DCNVideo'
        else:
            ie_key = 'DCNSeason'
            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 {
            'url': url,
            '_type': 'url',
            'ie_key': ie_key
        }


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']

        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)

        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'), ' ')

        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': 'Dubai Al Oula',
        },
        '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']

        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': title,
            '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',
            'description': '',
        },
        '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']
        title = show['cat'].get('title_en') or show['cat']['title_ar']
        description = show['cat'].get('description_en') or show['cat'].get('description_ar')
        entries = []
        for video in show['videos']:
            entries.append({
                'url': 'http://www.dcndigital.ae/#/media/%s' % video['id'],
                '_type': 'url',
                'ie_key': 'DCNVideo',
            })
        return {
            'id': season_id,
            'title': title,
            'description': description,
            'entries': entries,
            '_type': 'playlist',
        }
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:
	28	url = 'http://www.dcndigital.ae/#/media/%s' % video_id
	29	ie_key = 'DCNVideo'
	30	else:
b477da20	31	ie_key = 'DCNSeason'
9f4921bf	32	if season_id and int(season_id) > 0:
b477da20	33	url = smuggle_url('http://www.dcndigital.ae/#/program/season/%s' % season_id, {'show_id': show_id})
9f4921bf	34	else:
	35	url = 'http://www.dcndigital.ae/#/program/%s' % show_id
	36	return {
	37	'url': url,
	38	'_type': 'url',
	39	'ie_key': ie_key
	40	}
	41
	42
	43	class DCNVideoIE(InfoExtractor):
b477da20	44	IE_NAME = 'dcn:video'
8e2898ed	45	_VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+\|media\|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
3af1fac7	46	_TEST = {
9f4921bf	47	'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	48	'info_dict':
	49	{
	50	'id': '17375',
f94639fa	51	'ext': 'mp4',
3af1fac7	52	'title': 'رحلة العمر : الحلقة 1',
f94639fa S	53	'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
	54	'thumbnail': 're:^https?://.*\.jpg$',
	55	'duration': 2041,
	56	'timestamp': 1227504126,
	57	'upload_date': '20081124',
cd6b555e	58	},
	59	'params': {
	60	# m3u8 download
	61	'skip_download': True,
	62	},
3af1fac7	63	}
	64
	65	def _real_extract(self, url):
	66	video_id = self._match_id(url)
f94639fa	67
cd6b555e	68	request = compat_urllib_request.Request(
f94639fa S	69	'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
	70	headers={'Origin': 'http://www.dcndigital.ae'})
	71
	72	video = self._download_json(request, video_id)
	73	title = video.get('title_en') or video['title_ar']
	74
3af1fac7	75	webpage = self._download_webpage(
f94639fa S	76	'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?'
	77	+ compat_urllib_parse.urlencode({
	78	'id': video['id'],
	79	'user_id': video['user_id'],
	80	'signature': video['signature'],
	81	'countries': 'Q0M=',
	82	'filter': 'DENY',
	83	}), video_id)
	84
	85	m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
	86	formats = self._extract_m3u8_formats(
	87	m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
	88
	89	rtsp_url = self._search_regex(
	90	r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
	91	if rtsp_url:
	92	formats.append({
	93	'url': rtsp_url,
	94	'format_id': 'rtsp',
	95	})
	96
	97	self._sort_formats(formats)
	98
	99	img = video.get('img')
	100	thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
	101	duration = int_or_none(video.get('duration'))
	102	description = video.get('description_en') or video.get('description_ar')
	103	timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')
	104
3af1fac7	105	return {
	106	'id': video_id,
	107	'title': title,
f94639fa	108	'description': description,
3af1fac7	109	'thumbnail': thumbnail,
3af1fac7	110	'duration': duration,
f94639fa	111	'timestamp': timestamp,
3af1fac7	112	'formats': formats,
3af1fac7	113	}
9f4921bf	114
9f4921bf	115
8e2898ed	116	class DCNLiveIE(InfoExtractor):
	117	IE_NAME = 'dcn:live'
	118	_VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)'
	119	_TEST = {
	120	'url': 'http://www.dcndigital.ae/#/live/6/dubai-tv',
	121	'info_dict':
	122	{
	123	'id': '6',
	124	'ext': 'mp4',
	125	'title': 'Dubai Al Oula',
	126	},
	127	'params': {
	128	# m3u8 download
	129	'skip_download': True,
	130	},
	131	}
	132
	133	def _real_extract(self, url):
	134	channel_id = self._match_id(url)
	135
	136	request = compat_urllib_request.Request(
	137	'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
	138	headers={'Origin': 'http://www.dcndigital.ae'})
	139
	140	channel = self._download_json(request, channel_id)
	141	title = channel.get('title_en') or channel['title_ar']
	142
	143	webpage = self._download_webpage(
	144	'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?'
	145	+ compat_urllib_parse.urlencode({
	146	'id': base64.b64encode(channel['user_id'].encode()).decode(),
	147	'channelid': base64.b64encode(channel['id'].encode()).decode(),
	148	'signature': channel['signature'],
	149	'countries': 'Q0M=',
	150	'filter': 'DENY',
	151	}), channel_id)
	152
	153	m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
	154	formats = self._extract_m3u8_formats(
	155	m3u8_url, channel_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
	156
	157	rtsp_url = self._search_regex(
	158	r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
	159	if rtsp_url:
	160	formats.append({
	161	'url': rtsp_url,
	162	'format_id': 'rtsp',
	163	})
	164
	165	self._sort_formats(formats)
	166
	167	return {
	168	'id': channel_id,
	169	'title': title,
	170	'formats': formats,
	171	'is_live': True,
	172	}
	173
	174
b477da20	175	class DCNSeasonIE(InfoExtractor):
b477da20	176	IE_NAME = 'dcn:season'
9f4921bf	177	_VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)\|season/(?P<season_id>\d+))'
	178	_TEST = {
	179	'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',
	180	'info_dict':
	181	{
b477da20	182	'id': '7910',
9f4921bf	183	'title': 'محاضرات الشيخ الشعراوي',
	184	'description': '',
	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()
	192	data = {}
	193	if season_id:
9f4921bf	194	data['season'] = season_id
b477da20	195	show_id = smuggled_data.get('show_id')
	196	if show_id is None:
	197	request = compat_urllib_request.Request(
	198	'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
	199	headers={'Origin': 'http://www.dcndigital.ae'})
	200	season = self._download_json(request, season_id)
	201	show_id = season['id']
9f4921bf	202	data['show_id'] = show_id
	203	request = compat_urllib_request.Request(
	204	'http://admin.mangomolo.com/analytics/index.php/plus/show',
	205	compat_urllib_parse.urlencode(data),
	206	{
	207	'Origin': 'http://www.dcndigital.ae',
	208	'Content-Type': 'application/x-www-form-urlencoded'
	209	})
	210	show = self._download_json(request, show_id)
b477da20	211	season_id = season_id or show['default_season']
9f4921bf	212	title = show['cat'].get('title_en') or show['cat']['title_ar']
	213	description = show['cat'].get('description_en') or show['cat'].get('description_ar')
	214	entries = []
	215	for video in show['videos']:
	216	entries.append({
	217	'url': 'http://www.dcndigital.ae/#/media/%s' % video['id'],
	218	'_type': 'url',
	219	'ie_key': 'DCNVideo',
	220	})
	221	return {
b477da20	222	'id': season_id,
9f4921bf	223	'title': title,
	224	'description': description,
	225	'entries': entries,
	226	'_type': 'playlist',
	227	}