X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fnaver.py;h=fbe34defd868694d44f4371825322a41b39019a3;hb=9e1a5b845586a0a5431fb72467142046d8571e6f;hp=4cab30631956b903682fc2de7aa5dd551bcdd4a3;hpb=b2ae513586cdf66b36ef4acc665c5eae17ee54a2;p=youtube-dl diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py index 4cab30631..fbe34defd 100644 --- a/youtube_dl/extractor/naver.py +++ b/youtube_dl/extractor/naver.py @@ -1,10 +1,13 @@ # encoding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor from ..utils import ( compat_urllib_parse, ExtractorError, + clean_html, ) @@ -12,12 +15,13 @@ class NaverIE(InfoExtractor): _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P\d+)' _TEST = { - u'url': u'http://tvcast.naver.com/v/81652', - u'file': u'81652.mp4', - u'info_dict': { - u'title': u'[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번', - u'description': u'합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.', - u'upload_date': u'20130903', + 'url': 'http://tvcast.naver.com/v/81652', + 'info_dict': { + 'id': '81652', + 'ext': 'mp4', + 'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번', + 'description': '합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.', + 'upload_date': '20130903', }, } @@ -26,12 +30,17 @@ class NaverIE(InfoExtractor): video_id = mobj.group(1) webpage = self._download_webpage(url, video_id) m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"', - webpage) + webpage) if m_id is None: - raise ExtractorError(u'couldn\'t extract vid and key') + m_error = re.search( + r'(?s)
\s*(?:)?\s*

(?P.+?)

\s*
', + webpage) + if m_error: + raise ExtractorError(clean_html(m_error.group('msg')), expected=True) + raise ExtractorError('couldn\'t extract vid and key') vid = m_id.group(1) key = m_id.group(2) - query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,}) + query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key, }) query_urls = compat_urllib_parse.urlencode({ 'masterVid': vid, 'protocol': 'p2p', @@ -39,22 +48,27 @@ class NaverIE(InfoExtractor): }) info = self._download_xml( 'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query, - video_id, u'Downloading video info') + video_id, 'Downloading video info') urls = self._download_xml( 'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls, - video_id, u'Downloading video formats info') + video_id, 'Downloading video formats info') formats = [] for format_el in urls.findall('EncodingOptions/EncodingOption'): domain = format_el.find('Domain').text - if domain.startswith('rtmp'): - continue - formats.append({ + f = { 'url': domain + format_el.find('uri').text, 'ext': 'mp4', 'width': int(format_el.find('width').text), 'height': int(format_el.find('height').text), - }) + } + if domain.startswith('rtmp'): + f.update({ + 'ext': 'flv', + 'rtmp_protocol': '1', # rtmpt + }) + formats.append(f) + self._sort_formats(formats) return { 'id': video_id,