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         # Test for https://github.com/rg3/youtube-dl/issues/7949
  29         'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=M1O35s8HPOo0&clipid=73147290',
  30         'md5': 'c92d78bcee4424451f1667f275c1dc97',
  31         'info_dict': {
  32             'id': '73147290',
  33             'ext': 'mp4',
  34             'title': '싸이 - 나팔바지 [유희열의 스케치북] 299회 20151218',
  35             'description': '싸이 - 나팔바지',
  36             'upload_date': '20151219',
  37             'duration': 232,
  38         },
  39     }, {
  40         'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
  44         'only_matching': True,
  45     }]
  46
  47     def _real_extract(self, url):
  48         mobj = re.match(self._VALID_URL, url)
  49         video_id = mobj.group('id')
  50         canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
  51         webpage = self._download_webpage(canonical_url, video_id)
  52         og_url = self._og_search_url(webpage, default=None) or self._search_regex(
  53             r'<link[^>]+rel=(["\'])canonical\1[^>]+href=(["\'])(?P<url>.+?)\2',
  54             webpage, 'canonical url', group='url')
  55         full_id = self._search_regex(
  56             r'tvpot\.daum\.net/v/([^/]+)', og_url, 'full id')
  57         query = compat_urllib_parse.urlencode({'vid': full_id})
  58         info = self._download_xml(
  59             'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
  60             'Downloading video info')
  61         urls = self._download_xml(
  62             'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
  63             video_id, 'Downloading video formats info')
  64
  65         formats = []
  66         for format_el in urls.findall('result/output_list/output_list'):
  67             profile = format_el.attrib['profile']
  68             format_query = compat_urllib_parse.urlencode({
  69                 'vid': full_id,
  70                 'profile': profile,
  71             })
  72             url_doc = self._download_xml(
  73                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
  74                 video_id, note='Downloading video data for %s format' % profile)
  75             format_url = url_doc.find('result/url').text
  76             formats.append({
  77                 'url': format_url,
  78                 'format_id': profile,
  79             })
  80
  81         return {
  82             'id': video_id,
  83             'title': info.find('TITLE').text,
  84             'formats': formats,
  85             'thumbnail': self._og_search_thumbnail(webpage),
  86             'description': info.find('CONTENTS').text,
  87             'duration': int(info.find('DURATION').text),
  88             'upload_date': info.find('REGDTTM').text[:8],
  89         }