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

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