From 463e7216c87814edf1453aa3a5bfad89474ba6b1 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Sun, 6 Aug 2017 23:07:06 +0800 Subject: [PATCH 1/3] [niconico] Support HTML5-only videos (closes #13806) --- ChangeLog | 6 ++ youtube_dl/extractor/niconico.py | 124 +++++++++++++++++++++---------- 2 files changed, 90 insertions(+), 40 deletions(-) diff --git a/ChangeLog b/ChangeLog index 18893bba8..7cd385e68 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version + +Extractors ++ [niconico] Support HTML5-only videos (#13806) + + version 2017.08.06 Core diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index 79b9952c3..b13dc0035 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -11,10 +11,13 @@ from ..compat import ( ) from ..utils import ( determine_ext, + dict_get, ExtractorError, int_or_none, parse_duration, parse_iso8601, + try_get, + unified_timestamp, urlencode_postdata, xpath_text, ) @@ -31,12 +34,15 @@ class NiconicoIE(InfoExtractor): 'id': 'sm22312215', 'ext': 'mp4', 'title': 'Big Buck Bunny', + 'thumbnail': r're:https?://.*', 'uploader': 'takuya0301', 'uploader_id': '2698420', 'upload_date': '20131123', 'timestamp': 1385182762, 'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org', 'duration': 33, + 'view_count': int, + 'comment_count': int, }, 'skip': 'Requires an account', }, { @@ -48,6 +54,7 @@ class NiconicoIE(InfoExtractor): 'ext': 'swf', 'title': '【鏡音リン】Dance on media【オリジナル】take2!', 'description': 'md5:689f066d74610b3b22e0f1739add0f58', + 'thumbnail': r're:https?://.*', 'uploader': 'りょうた', 'uploader_id': '18822557', 'upload_date': '20110429', @@ -64,9 +71,11 @@ class NiconicoIE(InfoExtractor): 'ext': 'unknown_video', 'description': 'deleted', 'title': 'ドラえもんエターナル第3話「決戦第3新東京市」＜前編＞', + 'thumbnail': r're:https?://.*', 'upload_date': '20071224', 'timestamp': int, # timestamp field has different value if logged in 'duration': 304, + 'view_count': int, }, 'skip': 'Requires an account', }, { @@ -76,12 +85,31 @@ class NiconicoIE(InfoExtractor): 'ext': 'mp4', 'title': '【第1回】RADIOアニメロミックス ラブライブ！～のぞえりRadio Garden～', 'description': 'md5:b27d224bb0ff53d3c8269e9f8b561cf1', + 'thumbnail': r're:https?://.*', 'timestamp': 1388851200, 'upload_date': '20140104', 'uploader': 'アニメロチャンネル', 'uploader_id': '312', }, 'skip': 'The viewing period of the video you were searching for has expired.', + }, { + # video not available via `getflv` + 'url': 'http://www.nicovideo.jp/watch/sm1151009', + 'info_dict': { + 'id': 'sm1151009', + 'ext': 'flv', + 'title': 'マスターシステム本体内蔵のスペハリのメインテーマ（ＰＳＧ版）', + 'description': 'md5:6ee077e0581ff5019773e2e714cdd0b7', + 'thumbnail': r're:https?://.*', + 'duration': 184, + 'timestamp': 1190868283, + 'upload_date': '20070927', + 'uploader': 'denden2', + 'uploader_id': '1392194', + 'view_count': int, + 'comment_count': int, + }, + 'skip': 'Requires an account', }, { 'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg', 'only_matching': True, @@ -130,33 +158,51 @@ class NiconicoIE(InfoExtractor): if video_id.startswith('so'): video_id = self._match_id(handle.geturl()) - video_info = self._download_xml( - 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id, - note='Downloading video info page') + api_data = self._parse_json(self._html_search_regex( + 'data-api-data="([^"]+)"', webpage, + 'API data', default='{}'), video_id) + video_real_url = try_get( + api_data, lambda x: x['video']['smileInfo']['url']) - # Get flv info - flv_info_webpage = self._download_webpage( - 'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1', - video_id, 'Downloading flv info') + if video_real_url: + def get_video_info(items): + return dict_get(api_data['video'], items) + else: + # Get flv info + flv_info_webpage = self._download_webpage( + 'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1', + video_id, 'Downloading flv info') - flv_info = compat_urlparse.parse_qs(flv_info_webpage) - if 'url' not in flv_info: - if 'deleted' in flv_info: - raise ExtractorError('The video has been deleted.', - expected=True) - elif 'closed' in flv_info: - raise ExtractorError('Niconico videos now require logging in', - expected=True) - elif 'error' in flv_info: - raise ExtractorError('%s reports error: %s' % ( - self.IE_NAME, flv_info['error'][0]), expected=True) - else: - raise ExtractorError('Unable to find video URL') + flv_info = compat_urlparse.parse_qs(flv_info_webpage) + if 'url' not in flv_info: + if 'deleted' in flv_info: + raise ExtractorError('The video has been deleted.', + expected=True) + elif 'closed' in flv_info: + raise ExtractorError('Niconico videos now require logging in', + expected=True) + elif 'error' in flv_info: + raise ExtractorError('%s reports error: %s' % ( + self.IE_NAME, flv_info['error'][0]), expected=True) + else: + raise ExtractorError('Unable to find video URL') - video_real_url = flv_info['url'][0] + video_real_url = flv_info['url'][0] + + video_info_xml = self._download_xml( + 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, + video_id, note='Downloading video info page') + + def get_video_info(items): + if not isinstance(items, list): + items = [items] + for item in items: + ret = xpath_text(video_info_xml, './/' + item) + if ret: + return ret # Start extracting information - title = xpath_text(video_info, './/title') + title = get_video_info('title') if not title: title = self._og_search_title(webpage, default=None) if not title: @@ -170,18 +216,19 @@ class NiconicoIE(InfoExtractor): watch_api_data = self._parse_json(watch_api_data_string, video_id) if watch_api_data_string else {} video_detail = watch_api_data.get('videoDetail', {}) - extension = xpath_text(video_info, './/movie_type') + extension = get_video_info(['movie_type', 'movieType']) if not extension: extension = determine_ext(video_real_url) thumbnail = ( - xpath_text(video_info, './/thumbnail_url') or + get_video_info(['thumbnail_url', 'thumbnailURL']) or self._html_search_meta('image', webpage, 'thumbnail', default=None) or video_detail.get('thumbnail')) - description = xpath_text(video_info, './/description') + description = get_video_info('description') - timestamp = parse_iso8601(xpath_text(video_info, './/first_retrieve')) + timestamp = (parse_iso8601(get_video_info('first_retrieve')) or + unified_timestamp(get_video_info('postedDateTime'))) if not timestamp: match = self._html_search_meta('datePublished', webpage, 'date published', default=None) if match: @@ -191,7 +238,7 @@ class NiconicoIE(InfoExtractor): video_detail['postedAt'].replace('/', '-'), delimiter=' ', timezone=datetime.timedelta(hours=9)) - view_count = int_or_none(xpath_text(video_info, './/view_counter')) + view_count = int_or_none(get_video_info(['view_counter', 'viewCount'])) if not view_count: match = self._html_search_regex( r'>Views: ]*>([^<]+)', @@ -200,31 +247,28 @@ class NiconicoIE(InfoExtractor): view_count = int_or_none(match.replace(',', '')) view_count = view_count or video_detail.get('viewCount') - comment_count = int_or_none(xpath_text(video_info, './/comment_num')) + comment_count = (int_or_none(get_video_info('comment_num')) or + video_detail.get('commentCount') or + try_get(api_data, lambda x: x['thread']['commentCount'])) if not comment_count: match = self._html_search_regex( r'>Comments: ]*>([^<]+)', webpage, 'comment count', default=None) if match: comment_count = int_or_none(match.replace(',', '')) - comment_count = comment_count or video_detail.get('commentCount') duration = (parse_duration( - xpath_text(video_info, './/length') or + get_video_info('length') or self._html_search_meta( 'video:duration', webpage, 'video duration', default=None)) or - video_detail.get('length')) + video_detail.get('length') or + get_video_info('duration')) - webpage_url = xpath_text(video_info, './/watch_url') or url + webpage_url = get_video_info('watch_url') or url - if video_info.find('.//ch_id') is not None: - uploader_id = video_info.find('.//ch_id').text - uploader = video_info.find('.//ch_name').text - elif video_info.find('.//user_id') is not None: - uploader_id = video_info.find('.//user_id').text - uploader = video_info.find('.//user_nickname').text - else: - uploader_id = uploader = None + owner = api_data.get('owner', {}) + uploader_id = get_video_info(['ch_id', 'user_id']) or owner.get('id') + uploader = get_video_info(['ch_name', 'user_nickname']) or owner.get('nickname') return { 'id': video_id, From ee6a611665a1ee8583ce84bd9d36d03b6f697895 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Mon, 7 Aug 2017 00:19:46 +0800 Subject: [PATCH 2/3] [niconico] Support videos with multiple formats (closes #13522) --- ChangeLog | 1 + youtube_dl/extractor/niconico.py | 161 +++++++++++++++++++++++++++---- 2 files changed, 145 insertions(+), 17 deletions(-) diff --git a/ChangeLog b/ChangeLog index 7cd385e68..084e98c0e 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,6 +1,7 @@ version Extractors ++ [niconico] Support videos with multiple formats (#13522) + [niconico] Support HTML5-only videos (#13806) diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index b13dc0035..026329d3e 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -14,8 +14,10 @@ from ..utils import ( dict_get, ExtractorError, int_or_none, + float_or_none, parse_duration, parse_iso8601, + remove_start, try_get, unified_timestamp, urlencode_postdata, @@ -93,11 +95,12 @@ class NiconicoIE(InfoExtractor): }, 'skip': 'The viewing period of the video you were searching for has expired.', }, { - # video not available via `getflv` + # video not available via `getflv`; "old" HTML5 video 'url': 'http://www.nicovideo.jp/watch/sm1151009', + 'md5': '8fa81c364eb619d4085354eab075598a', 'info_dict': { 'id': 'sm1151009', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'マスターシステム本体内蔵のスペハリのメインテーマ（ＰＳＧ版）', 'description': 'md5:6ee077e0581ff5019773e2e714cdd0b7', 'thumbnail': r're:https?://.*', @@ -110,6 +113,25 @@ class NiconicoIE(InfoExtractor): 'comment_count': int, }, 'skip': 'Requires an account', + }, { + # "New" HTML5 video + 'url': 'http://www.nicovideo.jp/watch/sm31464864', + 'md5': '351647b4917660986dc0fa8864085135', + 'info_dict': { + 'id': 'sm31464864', + 'ext': 'mp4', + 'title': '新作TVアニメ「戦姫絶唱シンフォギアAXZ」PV 最高画質', + 'description': 'md5:e52974af9a96e739196b2c1ca72b5feb', + 'timestamp': 1498514060, + 'upload_date': '20170626', + 'uploader': 'ゲス', + 'uploader_id': '40826363', + 'thumbnail': r're:https?://.*', + 'duration': 198, + 'view_count': int, + 'comment_count': int, + }, + 'skip': 'Requires an account', }, { 'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg', 'only_matching': True, @@ -147,6 +169,84 @@ class NiconicoIE(InfoExtractor): self._downloader.report_warning('unable to log in: bad username or password') return login_ok + def _extract_format_for_quality(self, api_data, video_id, audio_quality, video_quality): + def yesno(boolean): + return 'yes' if boolean else 'no' + + session_api_data = api_data['video']['dmcInfo']['session_api'] + session_api_endpoint = session_api_data['urls'][0] + + format_id = '-'.join(map(lambda s: remove_start(s['id'], 'archive_'), [video_quality, audio_quality])) + + session_response = self._download_json( + session_api_endpoint['url'], video_id, + query={'_format': 'json'}, + headers={'Content-Type': 'application/json'}, + note='Downloading JSON metadata for %s' % format_id, + data=json.dumps({ + 'session': { + 'client_info': { + 'player_id': session_api_data['player_id'], + }, + 'content_auth': { + 'auth_type': session_api_data['auth_types'][session_api_data['protocols'][0]], + 'content_key_timeout': session_api_data['content_key_timeout'], + 'service_id': 'nicovideo', + 'service_user_id': session_api_data['service_user_id'] + }, + 'content_id': session_api_data['content_id'], + 'content_src_id_sets': [{ + 'content_src_ids': [{ + 'src_id_to_mux': { + 'audio_src_ids': [audio_quality['id']], + 'video_src_ids': [video_quality['id']], + } + }] + }], + 'content_type': 'movie', + 'content_uri': '', + 'keep_method': { + 'heartbeat': { + 'lifetime': session_api_data['heartbeat_lifetime'] + } + }, + 'priority': session_api_data['priority'], + 'protocol': { + 'name': 'http', + 'parameters': { + 'http_parameters': { + 'parameters': { + 'http_output_download_parameters': { + 'use_ssl': yesno(session_api_endpoint['is_ssl']), + 'use_well_known_port': yesno(session_api_endpoint['is_well_known_port']), + } + } + } + } + }, + 'recipe_id': session_api_data['recipe_id'], + 'session_operation_auth': { + 'session_operation_auth_by_signature': { + 'signature': session_api_data['signature'], + 'token': session_api_data['token'], + } + }, + 'timing_constraint': 'unlimited' + } + })) + + resolution = video_quality.get('resolution', {}) + + return { + 'url': session_response['data']['session']['content_uri'], + 'format_id': format_id, + 'ext': 'mp4', # Session API are used in HTML5, which always serves mp4 + 'abr': float_or_none(audio_quality.get('bitrate'), 1000), + 'vbr': float_or_none(video_quality.get('bitrate'), 1000), + 'height': resolution.get('height'), + 'width': resolution.get('width'), + } + def _real_extract(self, url): video_id = self._match_id(url) @@ -161,13 +261,13 @@ class NiconicoIE(InfoExtractor): api_data = self._parse_json(self._html_search_regex( 'data-api-data="([^"]+)"', webpage, 'API data', default='{}'), video_id) - video_real_url = try_get( - api_data, lambda x: x['video']['smileInfo']['url']) - if video_real_url: - def get_video_info(items): - return dict_get(api_data['video'], items) - else: + def _format_id_from_url(video_url): + return 'economy' if video_real_url.endswith('low') else 'normal' + + try: + video_real_url = api_data['video']['smileInfo']['url'] + except KeyError: # Flash videos # Get flv info flv_info_webpage = self._download_webpage( 'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1', @@ -187,8 +287,6 @@ class NiconicoIE(InfoExtractor): else: raise ExtractorError('Unable to find video URL') - video_real_url = flv_info['url'][0] - video_info_xml = self._download_xml( 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id, note='Downloading video info page') @@ -201,6 +299,41 @@ class NiconicoIE(InfoExtractor): if ret: return ret + video_real_url = flv_info['url'][0] + + extension = get_video_info('movie_type') + if not extension: + extension = determine_ext(video_real_url) + + formats = [{ + 'url': video_real_url, + 'ext': extension, + 'format_id': _format_id_from_url(video_real_url), + }] + else: + formats = [] + + dmc_info = api_data['video'].get('dmcInfo') + if dmc_info: # "New" HTML5 videos + quality_info = dmc_info['quality'] + for audio_quality in quality_info['audios']: + for video_quality in quality_info['videos']: + if not audio_quality['available'] or not video_quality['available']: + continue + formats.append(self._extract_format_for_quality( + api_data, video_id, audio_quality, video_quality)) + + self._sort_formats(formats) + else: # "Old" HTML5 videos + formats = [{ + 'url': video_real_url, + 'ext': 'mp4', + 'format_id': _format_id_from_url(video_real_url), + }] + + def get_video_info(items): + return dict_get(api_data['video'], items) + # Start extracting information title = get_video_info('title') if not title: @@ -216,10 +349,6 @@ class NiconicoIE(InfoExtractor): watch_api_data = self._parse_json(watch_api_data_string, video_id) if watch_api_data_string else {} video_detail = watch_api_data.get('videoDetail', {}) - extension = get_video_info(['movie_type', 'movieType']) - if not extension: - extension = determine_ext(video_real_url) - thumbnail = ( get_video_info(['thumbnail_url', 'thumbnailURL']) or self._html_search_meta('image', webpage, 'thumbnail', default=None) or @@ -272,10 +401,8 @@ class NiconicoIE(InfoExtractor): return { 'id': video_id, - 'url': video_real_url, 'title': title, - 'ext': extension, - 'format_id': 'economy' if video_real_url.endswith('low') else 'normal', + 'formats': formats, 'thumbnail': thumbnail, 'description': description, 'uploader': uploader, From 15d1e8a23dbaa28635cae30ff6c5cfb095b4c7c0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 7 Aug 2017 22:43:42 +0700 Subject: [PATCH 3/3] [dplayit] Fix extraction (closes #13851) --- youtube_dl/extractor/dplay.py | 66 ++++++++++++++++++++++------------- 1 file changed, 42 insertions(+), 24 deletions(-) diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index 1a41760f8..76e784105 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -7,16 +7,18 @@ import time from .common import InfoExtractor from ..compat import ( - compat_urlparse, compat_HTTPError, + compat_str, + compat_urlparse, ) from ..utils import ( - USER_AGENTS, ExtractorError, int_or_none, - unified_strdate, remove_end, + try_get, + unified_strdate, update_url_query, + USER_AGENTS, ) @@ -183,28 +185,44 @@ class DPlayItIE(InfoExtractor): webpage = self._download_webpage(url, display_id) - info_url = self._search_regex( - r'url\s*[:=]\s*["\']((?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)', - webpage, 'video id') - title = remove_end(self._og_search_title(webpage), ' | Dplay') - try: - info = self._download_json( - info_url, display_id, headers={ - 'Authorization': 'Bearer %s' % self._get_cookies(url).get( - 'dplayit_token').value, - 'Referer': url, - }) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403): - info = self._parse_json(e.cause.read().decode('utf-8'), display_id) - error = info['errors'][0] - if error.get('code') == 'access.denied.geoblocked': - self.raise_geo_restricted( - msg=error.get('detail'), countries=self._GEO_COUNTRIES) - raise ExtractorError(info['errors'][0]['detail'], expected=True) - raise + video_id = None + + info = self._search_regex( + r'playback_json\s*:\s*JSON\.parse\s*\(\s*("(?:\\.|[^"\\])+?")', + webpage, 'playback JSON', default=None) + if info: + for _ in range(2): + info = self._parse_json(info, display_id, fatal=False) + if not info: + break + else: + video_id = try_get(info, lambda x: x['data']['id']) + + if not info: + info_url = self._search_regex( + r'url\s*[:=]\s*["\']((?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)', + webpage, 'info url') + + video_id = info_url.rpartition('/')[-1] + + try: + info = self._download_json( + info_url, display_id, headers={ + 'Authorization': 'Bearer %s' % self._get_cookies(url).get( + 'dplayit_token').value, + 'Referer': url, + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403): + info = self._parse_json(e.cause.read().decode('utf-8'), display_id) + error = info['errors'][0] + if error.get('code') == 'access.denied.geoblocked': + self.raise_geo_restricted( + msg=error.get('detail'), countries=self._GEO_COUNTRIES) + raise ExtractorError(info['errors'][0]['detail'], expected=True) + raise hls_url = info['data']['attributes']['streaming']['hls']['url'] @@ -230,7 +248,7 @@ class DPlayItIE(InfoExtractor): season_number = episode_number = upload_date = None return { - 'id': info_url.rpartition('/')[-1], + 'id': compat_str(video_id or display_id), 'display_id': display_id, 'title': title, 'description': self._og_search_description(webpage),