Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/naver.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_parse,
   9     ExtractorError,
  10     clean_html,
  11 )
  12
  13
  14 class NaverIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)'
  16
  17     _TEST = {
  18         'url': 'http://tvcast.naver.com/v/81652',
  19         'info_dict': {
  20             'id': '81652',
  21             'ext': 'mp4',
  22             'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번',
  23             'description': '합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.',
  24             'upload_date': '20130903',
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group(1)
  31         webpage = self._download_webpage(url, video_id)
  32         m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
  33             webpage)
  34         if m_id is None:
  35             m_error = re.search(
  36                 r'(?s)<div class="nation_error">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>',
  37                 webpage)
  38             if m_error:
  39                 raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
  40             raise ExtractorError('couldn\'t extract vid and key')
  41         vid = m_id.group(1)
  42         key = m_id.group(2)
  43         query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,})
  44         query_urls = compat_urllib_parse.urlencode({
  45             'masterVid': vid,
  46             'protocol': 'p2p',
  47             'inKey': key,
  48         })
  49         info = self._download_xml(
  50             'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query,
  51             video_id, 'Downloading video info')
  52         urls = self._download_xml(
  53             'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls,
  54             video_id, 'Downloading video formats info')
  55
  56         formats = []
  57         for format_el in urls.findall('EncodingOptions/EncodingOption'):
  58             domain = format_el.find('Domain').text
  59             f = {
  60                 'url': domain + format_el.find('uri').text,
  61                 'ext': 'mp4',
  62                 'width': int(format_el.find('width').text),
  63                 'height': int(format_el.find('height').text),
  64             }
  65             if domain.startswith('rtmp'):
  66                 f.update({
  67                     'ext': 'flv',
  68                     'rtmp_protocol': '1', # rtmpt
  69                 })
  70             formats.append(f)
  71         self._sort_formats(formats)
  72
  73         return {
  74             'id': video_id,
  75             'title': info.find('Subject').text,
  76             'formats': formats,
  77             'description': self._og_search_description(webpage),
  78             'thumbnail': self._og_search_thumbnail(webpage),
  79             'upload_date': info.find('WriteDate').text.replace('.', ''),
  80             'view_count': int(info.find('PlayCount').text),
  81         }