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 ..compat import (
   8     compat_urllib_parse,
   9 )
  10 from ..utils import (
  11     ExtractorError,
  12     clean_html,
  13 )
  14
  15
  16 class NaverIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)'
  18
  19     _TEST = {
  20         'url': 'http://tvcast.naver.com/v/81652',
  21         'info_dict': {
  22             'id': '81652',
  23             'ext': 'mp4',
  24             'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번',
  25             'description': '합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.',
  26             'upload_date': '20130903',
  27         },
  28     }
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32         webpage = self._download_webpage(url, video_id)
  33
  34         m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
  35                          webpage)
  36         if m_id is None:
  37             m_error = re.search(
  38                 r'(?s)<div class="nation_error">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>',
  39                 webpage)
  40             if m_error:
  41                 raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
  42             raise ExtractorError('couldn\'t extract vid and key')
  43         vid = m_id.group(1)
  44         key = m_id.group(2)
  45         query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key, })
  46         query_urls = compat_urllib_parse.urlencode({
  47             'masterVid': vid,
  48             'protocol': 'p2p',
  49             'inKey': key,
  50         })
  51         info = self._download_xml(
  52             'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query,
  53             video_id, 'Downloading video info')
  54         urls = self._download_xml(
  55             'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls,
  56             video_id, 'Downloading video formats info')
  57
  58         formats = []
  59         for format_el in urls.findall('EncodingOptions/EncodingOption'):
  60             domain = format_el.find('Domain').text
  61             f = {
  62                 'url': domain + format_el.find('uri').text,
  63                 'ext': 'mp4',
  64                 'width': int(format_el.find('width').text),
  65                 'height': int(format_el.find('height').text),
  66             }
  67             if domain.startswith('rtmp'):
  68                 f.update({
  69                     'ext': 'flv',
  70                     'rtmp_protocol': '1',  # rtmpt
  71                 })
  72             formats.append(f)
  73         self._sort_formats(formats)
  74
  75         return {
  76             'id': video_id,
  77             'title': info.find('Subject').text,
  78             'formats': formats,
  79             'description': self._og_search_description(webpage),
  80             'thumbnail': self._og_search_thumbnail(webpage),
  81             'upload_date': info.find('WriteDate').text.replace('.', ''),
  82             'view_count': int(info.find('PlayCount').text),
  83         }