ytdl/youtube_dl/extractor/dcn.py

85 lines
2.8 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
2015-07-18 10:51:59 +02:00
from .common import InfoExtractor
2015-08-07 20:06:03 +02:00
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
int_or_none,
parse_iso8601,
)
2015-07-18 10:51:59 +02:00
2015-08-07 20:06:03 +02:00
class DCNIE(InfoExtractor):
2015-08-07 20:19:40 +02:00
_VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P<id>\d+)'
2015-07-18 10:51:59 +02:00
_TEST = {
'url': 'http://www.dcndigital.ae/#/show/199074/%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%A9-1/17375/6887',
'info_dict':
{
'id': '17375',
2015-08-07 20:06:03 +02:00
'ext': 'mp4',
2015-07-18 10:51:59 +02:00
'title': 'رحلة العمر : الحلقة 1',
2015-08-07 20:06:03 +02:00
'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 2041,
'timestamp': 1227504126,
'upload_date': '20081124',
},
'params': {
# m3u8 download
'skip_download': True,
},
2015-07-18 10:51:59 +02:00
}
def _real_extract(self, url):
video_id = self._match_id(url)
2015-08-07 20:06:03 +02:00
request = compat_urllib_request.Request(
2015-08-07 20:06:03 +02:00
'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']
2015-07-18 10:51:59 +02:00
webpage = self._download_webpage(
2015-08-07 20:06:03 +02:00
'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'), ' ')
2015-07-18 10:51:59 +02:00
return {
'id': video_id,
'title': title,
2015-08-07 20:06:03 +02:00
'description': description,
2015-07-18 10:51:59 +02:00
'thumbnail': thumbnail,
'duration': duration,
2015-08-07 20:06:03 +02:00
'timestamp': timestamp,
2015-07-18 10:51:59 +02:00
'formats': formats,
}