_ Git - youtube-dl/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         og_url = self._og_search_url(webpage, default=None) or self._search_regex(
  41             r'<link[^>]+rel=(["\'])canonical\1[^>]+href=(["\'])(?P<url>.+?)\2',
  42             webpage, 'canonical url', group='url')
  43         full_id = self._search_regex(
  44             r'tvpot\.daum\.net/v/([^/]+)', og_url, 'full id')
  45         query = compat_urllib_parse.urlencode({'vid': full_id})
  46         info = self._download_xml(
  47             'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
  48             'Downloading video info')
  49         urls = self._download_xml(
  50             'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
  51             video_id, 'Downloading video formats info')
  52
  53         formats = []
  54         for format_el in urls.findall('result/output_list/output_list'):
  55             profile = format_el.attrib['profile']
  56             format_query = compat_urllib_parse.urlencode({
  57                 'vid': full_id,
  58                 'profile': profile,
  59             })
  60             url_doc = self._download_xml(
  61                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
  62                 video_id, note='Downloading video data for %s format' % profile)
  63             format_url = url_doc.find('result/url').text
  64             formats.append({
  65                 'url': format_url,
  66                 'format_id': profile,
  67             })
  68
  69         return {
  70             'id': video_id,
  71             'title': info.find('TITLE').text,
  72             'formats': formats,
  73             'thumbnail': self._og_search_thumbnail(webpage),
  74             'description': info.find('CONTENTS').text,
  75             'duration': int(info.find('DURATION').text),
  76             'upload_date': info.find('REGDTTM').text[:8],
  77         }