From f94639fadf91312bf3365802981f506ecba698dc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 8 Aug 2015 00:06:03 +0600 Subject: [PATCH] [dcn] Improve --- youtube_dl/extractor/__init__.py | 2 +- youtube_dl/extractor/dcn.py | 78 ++++++++++++++++++++++---------- 2 files changed, 54 insertions(+), 26 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index eb8ef1fe3..922d9b3d8 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -118,7 +118,7 @@ ) from .daum import DaumIE from .dbtv import DBTVIE -from .dcn import DcnIE +from .dcn import DCNIE from .dctp import DctpTvIE from .deezer import DeezerPlaylistIE from .dfb import DFBIE diff --git a/youtube_dl/extractor/dcn.py b/youtube_dl/extractor/dcn.py index 22ff35b56..b98a6c032 100644 --- a/youtube_dl/extractor/dcn.py +++ b/youtube_dl/extractor/dcn.py @@ -2,22 +2,30 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_urllib_request -from ..utils import int_or_none +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, +) +from ..utils import ( + int_or_none, + parse_iso8601, +) -class DcnIE(InfoExtractor): +class DCNIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P\d+)/?' _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', - 'ext': 'm3u8', + 'ext': 'mp4', 'title': 'رحلة العمر : الحلقة 1', - 'description': 'في هذه الحلقة من برنامج رحلة العمر يقدّم الدكتور عمر عبد الكافي تبسيطاً لمناسك الحج والعمرة ويجيب مباشرة على استفسارات حجاج بيت الله الحرام بخصوص مناسك الحج والعمرة\n1', - 'thumbnail': 'http://admin.mangomolo.com/analytics/uploads/71/images/media/2/2cefc09d7bec80afa754682f40e49503.jpg', - 'duration': 2041 + 'description': 'md5:0156e935d870acb8ef0a66d24070c6d6', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 2041, + 'timestamp': 1227504126, + 'upload_date': '20081124', }, 'params': { # m3u8 download @@ -27,30 +35,50 @@ class DcnIE(InfoExtractor): 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=' + video_id, - headers={'Origin': 'http://www.dcndigital.ae'} - ) - json_data = self._download_json(request, video_id) - title = json_data['title_ar'] - thumbnail = 'http://admin.mangomolo.com/analytics/' + json_data.get('img') - duration = int_or_none(json_data.get('duration')) - description = json_data.get('description_ar') + '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?id=' + json_data['id'] + '&user_id=' + json_data['user_id'] + '&countries=Q0M=&w=100%&h=100%&filter=DENY&signature=' + json_data['signature'], - video_id - ) - m3u8_url = self._html_search_regex( - r'file:\s*"([^"]+)', - webpage, - 'm3u8_url' - ) - formats = self._extract_m3u8_formats(m3u8_url, video_id) + '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']+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, - 'description': description, + 'timestamp': timestamp, 'formats': formats, }