1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-23 04:02:58 +08:00
youtube-dl/youtube_dl/extractor/awaan.py

186 lines
7.0 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import re
import base64
2015-07-18 16:51:59 +08:00
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_str,
)
2015-08-08 02:06:03 +08:00
from ..utils import (
int_or_none,
parse_iso8601,
smuggle_url,
unsmuggle_url,
urlencode_postdata,
2015-08-08 02:06:03 +08:00
)
2015-07-18 16:51:59 +08:00
class AWAANIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:awaan|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()
if video_id and int(video_id) > 0:
2015-12-27 16:56:15 +08:00
return self.url_result(
'http://awaan.ae/media/%s' % video_id, 'AWAANVideo')
2015-12-27 16:56:15 +08:00
elif season_id and int(season_id) > 0:
return self.url_result(smuggle_url(
'http://awaan.ae/program/season/%s' % season_id,
{'show_id': show_id}), 'AWAANSeason')
else:
2015-12-27 16:56:15 +08:00
return self.url_result(
'http://awaan.ae/program/%s' % show_id, 'AWAANSeason')
class AWAANBaseIE(InfoExtractor):
def _parse_video_data(self, video_data, video_id, is_live):
2015-12-27 16:56:15 +08:00
title = video_data.get('title_en') or video_data['title_ar']
img = video_data.get('img')
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'description': video_data.get('description_en') or video_data.get('description_ar'),
'thumbnail': 'http://admin.mangomolo.com/analytics/%s' % img if img else None,
'duration': int_or_none(video_data.get('duration')),
'timestamp': parse_iso8601(video_data.get('create_time'), ' '),
2015-12-27 16:56:15 +08:00
'is_live': is_live,
}
class AWAANVideoIE(AWAANBaseIE):
IE_NAME = 'awaan:video'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
_TESTS = [{
'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',
'md5': '5f61c33bfc7794315c671a62d43116aa',
2015-07-18 16:51:59 +08:00
'info_dict':
{
'id': '17375',
2015-08-08 02:06:03 +08:00
'ext': 'mp4',
2015-07-18 16:51:59 +08:00
'title': 'رحلة العمر : الحلقة 1',
2015-08-08 02:06:03 +08:00
'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
'duration': 2041,
'timestamp': 1227504126,
'upload_date': '20081124',
2016-09-27 22:28:37 +08:00
'uploader_id': '71',
},
}, {
'url': 'http://awaan.ae/video/26723981/%D8%AF%D8%A7%D8%B1-%D8%A7%D9%84%D8%B3%D9%84%D8%A7%D9%85:-%D8%AE%D9%8A%D8%B1-%D8%AF%D9%88%D8%B1-%D8%A7%D9%84%D8%A3%D9%86%D8%B5%D8%A7%D8%B1',
'only_matching': True,
}]
2015-07-18 16:51:59 +08:00
def _real_extract(self, url):
video_id = self._match_id(url)
2015-08-08 02:06:03 +08:00
video_data = self._download_json(
2015-08-08 02:06:03 +08:00
'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
video_id, headers={'Origin': 'http://awaan.ae'})
info = self._parse_video_data(video_data, video_id, False)
2015-08-08 02:06:03 +08:00
embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + compat_urllib_parse_urlencode({
'id': video_data['id'],
'user_id': video_data['user_id'],
'signature': video_data['signature'],
'countries': 'Q0M=',
'filter': 'DENY',
})
info.update({
'_type': 'url_transparent',
'url': embed_url,
'ie_key': 'MangomoloVideo',
})
2015-12-27 16:56:15 +08:00
return info
2015-08-08 02:06:03 +08:00
class AWAANLiveIE(AWAANBaseIE):
IE_NAME = 'awaan:live'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P<id>\d+)'
_TEST = {
'url': 'http://awaan.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}$',
'upload_date': '20150107',
'timestamp': 1420588800,
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
channel_id = self._match_id(url)
channel_data = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
channel_id, headers={'Origin': 'http://awaan.ae'})
info = self._parse_video_data(channel_data, channel_id, True)
embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' + compat_urllib_parse_urlencode({
'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
'signature': channel_data['signature'],
'countries': 'Q0M=',
'filter': 'DENY',
})
info.update({
'_type': 'url_transparent',
'url': embed_url,
'ie_key': 'MangomoloLive',
})
2015-12-27 16:56:15 +08:00
return info
class AWAANSeasonIE(InfoExtractor):
IE_NAME = 'awaan:season'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|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:
season = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
season_id, headers={'Origin': 'http://awaan.ae'})
show_id = season['id']
data['show_id'] = show_id
show = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/show',
show_id, data=urlencode_postdata(data), headers={
'Origin': 'http://awaan.ae',
'Content-Type': 'application/x-www-form-urlencoded'
2015-08-08 02:06:03 +08:00
})
2015-10-31 22:40:11 +08:00
if not season_id:
season_id = show['default_season']
for season in show['seasons']:
if season['id'] == season_id:
title = season.get('title_en') or season['title_ar']
2015-08-08 02:06:03 +08:00
2015-10-31 22:40:11 +08:00
entries = []
for video in show['videos']:
video_id = compat_str(video['id'])
2015-12-27 16:56:15 +08:00
entries.append(self.url_result(
'http://awaan.ae/media/%s' % video_id, 'AWAANVideo', video_id))
2015-08-08 02:06:03 +08:00
2015-10-31 22:40:11 +08:00
return self.playlist_result(entries, season_id, title)