X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fdcn.py;h=b8542820a36534fe548aac43ea7f64375396e3ba;hb=3c2c3af059d99e6795d1944a55d6601b5959871b;hp=a9a5e94f53ef7d9c5eb7dd9799dfc80788d851bf;hpb=50b9dd734423231f7a01ed8a156d09ca04a23a31;p=youtube-dl diff --git a/youtube_dl/extractor/dcn.py b/youtube_dl/extractor/dcn.py index a9a5e94f5..b8542820a 100644 --- a/youtube_dl/extractor/dcn.py +++ b/youtube_dl/extractor/dcn.py @@ -6,38 +6,79 @@ import base64 from .common import InfoExtractor from ..compat import ( - compat_urllib_parse, - compat_urllib_request, + compat_urllib_parse_urlencode, + compat_str, ) from ..utils import ( int_or_none, parse_iso8601, + sanitized_Request, smuggle_url, unsmuggle_url, + urlencode_postdata, ) -class DCNGeneralIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P\d+)/[^/]+(?:/(?P\d+)/(?P\d+))?' +class DCNIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?(?:awaan|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: - return self.url_result('http://www.dcndigital.ae/#/media/%s' % video_id, '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: - 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(url, 'DCNSeason') + return self.url_result( + 'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason') -class DCNVideoIE(InfoExtractor): +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 { + '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, m3u8_entry_protocol): + formats = [] + format_url_base = 'http' + self._html_search_regex( + [ + r'file\s*:\s*"https?(://[^"]+)/playlist.m3u8', + r']+href="rtsp(://[^"]+)"' + ], webpage, 'format url') + formats.extend(self._extract_mpd_formats( + format_url_base + '/manifest.mpd', + video_id, mpd_id='dash', fatal=False)) + formats.extend(self._extract_m3u8_formats( + format_url_base + '/playlist.m3u8', video_id, 'mp4', + m3u8_entry_protocol, m3u8_id='hls', fatal=False)) + formats.extend(self._extract_f4m_formats( + format_url_base + '/manifest.f4m', + video_id, f4m_id='hds', fatal=False)) + 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 = { + _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P\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', 'info_dict': { @@ -45,7 +86,6 @@ class DCNVideoIE(InfoExtractor): 'ext': 'mp4', 'title': 'رحلة العمر : الحلقة 1', 'description': 'md5:0156e935d870acb8ef0a66d24070c6d6', - 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 2041, 'timestamp': 1227504126, 'upload_date': '20081124', @@ -54,128 +94,63 @@ class DCNVideoIE(InfoExtractor): # m3u8 download 'skip_download': True, }, - } + }, { + '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, + }] 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'] - 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'), ' ') + 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) - - 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': 're:^Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'thumbnail': 're:^https?://.*\.png$', - 'is_live': True, - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - } + _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P\d+)' 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'] - img = channel.get('thumbnail') - thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None - description = channel.get('description_en') or channel.get('description_ar') - timestamp = parse_iso8601(channel.get('create_time') or channel.get('update_time'), ' ') + 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'], + 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': self._live_title(title), - 'description': description, - 'thumbnail': thumbnail, - 'formats': formats, - 'is_live': True, - } + info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8') + return info class DCNSeasonIE(InfoExtractor): IE_NAME = 'dcn:season' - _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P\d+)|season/(?P\d+))' + _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?program/(?:(?P\d+)|season/(?P\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': @@ -195,15 +170,15 @@ class DCNSeasonIE(InfoExtractor): 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), + urlencode_postdata(data), { 'Origin': 'http://www.dcndigital.ae', 'Content-Type': 'application/x-www-form-urlencoded' @@ -218,6 +193,8 @@ class DCNSeasonIE(InfoExtractor): entries = [] for video in show['videos']: - entries.append(self.url_result('http://www.dcndigital.ae/#/media/%s' % video['id'], 'DCNVideo')) + video_id = compat_str(video['id']) + entries.append(self.url_result( + 'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo', video_id)) return self.playlist_result(entries, season_id, title)