2 from __future__ import unicode_literals
6 from .common import InfoExtractor
13 class NaverIE(InfoExtractor):
14 _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)'
17 'url': 'http://tvcast.naver.com/v/81652',
21 'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번',
22 'description': '합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.',
23 'upload_date': '20130903',
27 def _real_extract(self, url):
28 mobj = re.match(self._VALID_URL, url)
29 video_id = mobj.group(1)
30 webpage = self._download_webpage(url, video_id)
31 m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
34 raise ExtractorError('couldn\'t extract vid and key')
37 query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,})
38 query_urls = compat_urllib_parse.urlencode({
43 info = self._download_xml(
44 'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query,
45 video_id, 'Downloading video info')
46 urls = self._download_xml(
47 'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls,
48 video_id, 'Downloading video formats info')
51 for format_el in urls.findall('EncodingOptions/EncodingOption'):
52 domain = format_el.find('Domain').text
54 'url': domain + format_el.find('uri').text,
56 'width': int(format_el.find('width').text),
57 'height': int(format_el.find('height').text),
59 if domain.startswith('rtmp'):
62 'rtmp_protocol': '1', # rtmpt
65 self._sort_formats(formats)
69 'title': info.find('Subject').text,
71 'description': self._og_search_description(webpage),
72 'thumbnail': self._og_search_thumbnail(webpage),
73 'upload_date': info.find('WriteDate').text.replace('.', ''),
74 'view_count': int(info.find('PlayCount').text),