X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fniconico.py;h=0ca046ac2ee1f8b5d8836362e404c465d9967122;hb=bb865f3a5e7290f0da43d180f068f8715c39e3ae;hp=45cbd4ee97b8cb66e3227d72e0ec7c3f238fa5f6;hpb=9908e0352872b252494747346589922358aa0375;p=youtube-dl diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index 45cbd4ee9..0ca046ac2 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -5,14 +5,18 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, compat_urlparse, - unified_strdate, - parse_duration, - int_or_none, +) +from ..utils import ( ExtractorError, + int_or_none, + parse_duration, + parse_iso8601, + xpath_text, + determine_ext, ) @@ -20,7 +24,7 @@ class NiconicoIE(InfoExtractor): IE_NAME = 'niconico' IE_DESC = 'ニコニコ動画' - _TEST = { + _TESTS = [{ 'url': 'http://www.nicovideo.jp/watch/sm22312215', 'md5': 'd1a75c0823e2f629128c43e1212760f9', 'info_dict': { @@ -30,6 +34,7 @@ class NiconicoIE(InfoExtractor): 'uploader': 'takuya0301', 'uploader_id': '2698420', 'upload_date': '20131123', + 'timestamp': 1385182762, 'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org', 'duration': 33, }, @@ -37,9 +42,41 @@ class NiconicoIE(InfoExtractor): 'username': 'ydl.niconico@gmail.com', 'password': 'youtube-dl', }, - } + }, { + 'url': 'http://www.nicovideo.jp/watch/nm14296458', + 'md5': '8db08e0158457cf852a31519fceea5bc', + 'info_dict': { + 'id': 'nm14296458', + 'ext': 'swf', + 'title': '【鏡音リン】Dance on media【オリジナル】take2!', + 'description': 'md5:689f066d74610b3b22e0f1739add0f58', + 'uploader': 'りょうた', + 'uploader_id': '18822557', + 'upload_date': '20110429', + 'timestamp': 1304065916, + 'duration': 209, + }, + 'params': { + 'username': 'ydl.niconico@gmail.com', + 'password': 'youtube-dl', + }, + }, { + # 'video exists but is marked as "deleted" + 'url': 'http://www.nicovideo.jp/watch/sm10000', + 'md5': '38e53c9aad548f3ecf01ca7680b59b08', + 'info_dict': { + 'id': 'sm10000', + '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＞', + }, + 'params': { + 'username': 'ydl.niconico@gmail.com', + 'password': 'youtube-dl', + } + }] - _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z]{2})?[0-9]+)' + _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P(?:[a-z]{2})?[0-9]+)' _NETRC_MACHINE = 'niconico' # Determine whether the downloader used authentication to download video _AUTHENTICATED = False @@ -74,12 +111,12 @@ class NiconicoIE(InfoExtractor): return True def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = self._match_id(url) - # Get video webpage. We are not actually interested in it, but need - # the cookies in order to be able to download the info webpage - self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id) + # Get video webpage. We are not actually interested in it for normal + # cases, but need the cookies in order to be able to download the + # info webpage + webpage = self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id) video_info = self._download_xml( 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id, @@ -88,7 +125,7 @@ class NiconicoIE(InfoExtractor): if self._AUTHENTICATED: # Get flv info flv_info_webpage = self._download_webpage( - 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id, + 'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1', video_id, 'Downloading flv info') else: # Get external player info @@ -109,22 +146,34 @@ class NiconicoIE(InfoExtractor): flv_info_request, video_id, note='Downloading flv info', errnote='Unable to download flv info') - if 'deleted=' in flv_info_webpage: - raise ExtractorError('The video has been deleted.', - expected=True) - video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0] + 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) + else: + raise ExtractorError('Unable to find video URL') + + video_real_url = flv_info['url'][0] # Start extracting information - title = video_info.find('.//title').text - extension = video_info.find('.//movie_type').text + title = xpath_text(video_info, './/title') + if not title: + title = self._html_search_regex( + r']+class="videoHeaderTitle"[^>]*>([^<]+)', + webpage, 'video title') + + extension = xpath_text(video_info, './/movie_type') + if not extension: + extension = determine_ext(video_real_url) video_format = extension.upper() - thumbnail = video_info.find('.//thumbnail_url').text - description = video_info.find('.//description').text - upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0]) - view_count = int_or_none(video_info.find('.//view_counter').text) - comment_count = int_or_none(video_info.find('.//comment_num').text) - duration = parse_duration(video_info.find('.//length').text) - webpage_url = video_info.find('.//watch_url').text + thumbnail = xpath_text(video_info, './/thumbnail_url') + description = xpath_text(video_info, './/description') + timestamp = parse_iso8601(xpath_text(video_info, './/first_retrieve')) + view_count = int_or_none(xpath_text(video_info, './/view_counter')) + comment_count = int_or_none(xpath_text(video_info, './/comment_num')) + duration = parse_duration(xpath_text(video_info, './/length')) + webpage_url = xpath_text(video_info, './/watch_url') if video_info.find('.//ch_id') is not None: uploader_id = video_info.find('.//ch_id').text @@ -135,7 +184,7 @@ class NiconicoIE(InfoExtractor): else: uploader_id = uploader = None - return { + ret = { 'id': video_id, 'url': video_real_url, 'title': title, @@ -144,13 +193,14 @@ class NiconicoIE(InfoExtractor): 'thumbnail': thumbnail, 'description': description, 'uploader': uploader, - 'upload_date': upload_date, + 'timestamp': timestamp, 'uploader_id': uploader_id, 'view_count': view_count, 'comment_count': comment_count, 'duration': duration, 'webpage_url': webpage_url, } + return dict((k, v) for k, v in ret.items() if v is not None) class NiconicoPlaylistIE(InfoExtractor): @@ -170,12 +220,13 @@ class NiconicoPlaylistIE(InfoExtractor): webpage = self._download_webpage(url, list_id) entries_json = self._search_regex(r'Mylist\.preload\(\d+, (\[.*\])\);', - webpage, 'entries') + webpage, 'entries') entries = json.loads(entries_json) entries = [{ '_type': 'url', 'ie_key': NiconicoIE.ie_key(), - 'url': 'http://www.nicovideo.jp/watch/%s' % entry['item_id'], + 'url': ('http://www.nicovideo.jp/watch/%s' % + entry['item_data']['video_id']), } for entry in entries] return {