X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fdcn.py;h=0d140f12fd8ea81d1c486f470bd4f83a2edf82d9;hb=974c1b2d4292308a26a47136e7fcf9b61f8b285a;hp=2e8fff6606ec7fca147cc90a80f936b98eb0c291;hpb=8e2898edf930830260ab6b294c8866e7651a01a6;p=youtube-dl diff --git a/youtube_dl/extractor/dcn.py b/youtube_dl/extractor/dcn.py index 2e8fff660..0d140f12f 100644 --- a/youtube_dl/extractor/dcn.py +++ b/youtube_dl/extractor/dcn.py @@ -5,42 +5,75 @@ import re import base64 from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( int_or_none, parse_iso8601, + sanitized_Request, smuggle_url, unsmuggle_url, ) -class DCNGeneralIE(InfoExtractor): +class DCNIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P\d+)/[^/]+(?:/(?P\d+)/(?P\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' + return self.url_result( + 'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo') + elif season_id and int(season_id) > 0: + return self.url_result(smuggle_url( + 'http://www.dcndigital.ae/program/season/%s' % season_id, + {'show_id': show_id}), 'DCNSeason') 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 self.url_result( + 'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason') + + +class DCNBaseIE(InfoExtractor): + def _extract_video_info(self, video_data, video_id, is_live): + title = video_data.get('title_en') or video_data['title_ar'] + img = video_data.get('img') + thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None + duration = int_or_none(video_data.get('duration')) + description = video_data.get('description_en') or video_data.get('description_ar') + timestamp = parse_iso8601(video_data.get('create_time'), ' ') + return { - 'url': url, - '_type': 'url', - 'ie_key': ie_key + 'id': video_id, + 'title': self._live_title(title) if is_live else title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'is_live': is_live, } + def _extract_video_formats(self, webpage, video_id, entry_protocol): + formats = [] + m3u8_url = self._html_search_regex( + r'file\s*:\s*"([^"]+)', webpage, 'm3u8 url', fatal=False) + if m3u8_url: + m3u8_formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=None) + if m3u8_formats: + formats.extend(m3u8_formats) -class DCNVideoIE(InfoExtractor): + 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) + return formats + + +class DCNVideoIE(DCNBaseIE): IE_NAME = 'dcn:video' _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P\d+)' _TEST = { @@ -51,7 +84,6 @@ class DCNVideoIE(InfoExtractor): 'ext': 'mp4', 'title': 'رحلة العمر : الحلقة 1', 'description': 'md5:0156e935d870acb8ef0a66d24070c6d6', - 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 2041, 'timestamp': 1227504126, 'upload_date': '20081124', @@ -65,111 +97,50 @@ class DCNVideoIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - request = compat_urllib_request.Request( + request = sanitized_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'] + video_data = self._download_json(request, video_id) + info = self._extract_video_info(video_data, video_id, False) 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'], + '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', }), video_id) + info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native') + return info - 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, - 'timestamp': timestamp, - 'formats': formats, - } - - -class DCNLiveIE(InfoExtractor): +class DCNLiveIE(DCNBaseIE): IE_NAME = 'dcn:live' _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P\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( + request = sanitized_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'] + channel_data = self._download_json(request, channel_id) + info = self._extract_video_info(channel_data, channel_id, True) 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'], + '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', }), 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']+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, - } + info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8') + return info class DCNSeasonIE(InfoExtractor): @@ -181,7 +152,6 @@ class DCNSeasonIE(InfoExtractor): { 'id': '7910', 'title': 'محاضرات الشيخ الشعراوي', - 'description': '', }, 'playlist_mincount': 27, } @@ -189,39 +159,36 @@ class DCNSeasonIE(InfoExtractor): 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( + request = sanitized_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( + request = sanitized_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', - } + 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'] + + 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)