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 )
  11
  12
  13 class NaverIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)'
  15
  16     _TEST = {
  17         'url': 'http://tvcast.naver.com/v/81652',
  18         'info_dict': {
  19             'id': '81652',
  20             'ext': 'mp4',
  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',
  24         },
  25     }
  26
  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\("(.+?)", "(.+?)"',
  32             webpage)
  33         if m_id is None:
  34             raise ExtractorError('couldn\'t extract vid and key')
  35         vid = m_id.group(1)
  36         key = m_id.group(2)
  37         query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,})
  38         query_urls = compat_urllib_parse.urlencode({
  39             'masterVid': vid,
  40             'protocol': 'p2p',
  41             'inKey': key,
  42         })
  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')
  49
  50         formats = []
  51         for format_el in urls.findall('EncodingOptions/EncodingOption'):
  52             domain = format_el.find('Domain').text
  53             f = {
  54                 'url': domain + format_el.find('uri').text,
  55                 'ext': 'mp4',
  56                 'width': int(format_el.find('width').text),
  57                 'height': int(format_el.find('height').text),
  58             }
  59             if domain.startswith('rtmp'):
  60                 f.update({
  61                     'ext': 'flv',
  62                     'rtmp_protocol': '1', # rtmpt
  63                 })
  64             formats.append(f)
  65         self._sort_formats(formats)
  66
  67         return {
  68             'id': video_id,
  69             'title': info.find('Subject').text,
  70             'formats': formats,
  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),
  75         }