X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/7ceb2ec430c3363e0140a0519402428f36dc472e..555f0744b172953b2591db57ff5c6bccb4f378d6:/youtube_dl/extractor/naver.py diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py index 9df236d..c10405f 100644 --- a/youtube_dl/extractor/naver.py +++ b/youtube_dl/extractor/naver.py @@ -1,65 +1,78 @@ # encoding: utf-8 +from __future__ import unicode_literals + import re -import xml.etree.ElementTree from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, +) +from ..utils import ( ExtractorError, + clean_html, ) class NaverIE(InfoExtractor): - _VALID_URL = r'https?://tvcast\.naver\.com/v/(?P\d+)' + _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', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = self._match_id(url) 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', 'inKey': key, }) - info_xml = self._download_webpage( + info = self._download_xml( 'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query, - video_id, u'Downloading video info') - urls_xml = self._download_webpage( + 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') - info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')) - urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8')) + 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) - info = { + return { 'id': video_id, 'title': info.find('Subject').text, 'formats': formats, @@ -68,6 +81,3 @@ class NaverIE(InfoExtractor): 'upload_date': info.find('WriteDate').text.replace('.', ''), 'view_count': int(info.find('PlayCount').text), } - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - return info