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

   1 # encoding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_urllib_parse,
  10 )
  11
  12
  13 class DaumIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:v/|.*?clipid=)(?P<id>[^?#&]+)'
  15     IE_NAME = 'daum.net'
  16
  17     _TESTS = [{
  18         'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
  19         'info_dict': {
  20             'id': '52554690',
  21             'ext': 'mp4',
  22             'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
  23             'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
  24             'upload_date': '20130831',
  25             'duration': 3868,
  26         },
  27     }, {
  28         'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
  29         'only_matching': True,
  30     }, {
  31         'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
  32         'only_matching': True,
  33     }]
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         video_id = mobj.group('id')
  38         canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
  39         webpage = self._download_webpage(canonical_url, video_id)
  40         full_id = self._search_regex(
  41             r'src=["\']http://videofarm\.daum\.net/controller/video/viewer/Video\.html\?.*?vid=(.+?)[&"\']',
  42             webpage, 'full id')
  43         query = compat_urllib_parse.urlencode({'vid': full_id})
  44         info = self._download_xml(
  45             'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
  46             'Downloading video info')
  47         urls = self._download_xml(
  48             'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
  49             video_id, 'Downloading video formats info')
  50
  51         formats = []
  52         for format_el in urls.findall('result/output_list/output_list'):
  53             profile = format_el.attrib['profile']
  54             format_query = compat_urllib_parse.urlencode({
  55                 'vid': full_id,
  56                 'profile': profile,
  57             })
  58             url_doc = self._download_xml(
  59                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
  60                 video_id, note='Downloading video data for %s format' % profile)
  61             format_url = url_doc.find('result/url').text
  62             formats.append({
  63                 'url': format_url,
  64                 'format_id': profile,
  65             })
  66
  67         return {
  68             'id': video_id,
  69             'title': info.find('TITLE').text,
  70             'formats': formats,
  71             'thumbnail': self._og_search_thumbnail(webpage),
  72             'description': info.find('CONTENTS').text,
  73             'duration': int(info.find('DURATION').text),
  74             'upload_date': info.find('REGDTTM').text[:8],
  75         }