_ 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     compat_urllib_parse_unquote,
  11 )
  12 from ..utils import (
  13     int_or_none,
  14     str_to_int,
  15     xpath_text,
  16 )
  17
  18
  19 class DaumIE(InfoExtractor):
  20     _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
  21     IE_NAME = 'daum.net'
  22
  23     _TESTS = [{
  24         'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
  25         'info_dict': {
  26             'id': 'vab4dyeDBysyBssyukBUjBz',
  27             'ext': 'mp4',
  28             'title': '마크 헌트 vs 안토니오 실바',
  29             'description': 'Mark Hunt vs Antonio Silva',
  30             'upload_date': '20131217',
  31             'duration': 2117,
  32             'view_count': int,
  33             'comment_count': int,
  34         },
  35     }, {
  36         'url': 'http://m.tvpot.daum.net/v/65139429',
  37         'info_dict': {
  38             'id': '65139429',
  39             'ext': 'mp4',
  40             'title': 'md5:a100d65d09cec246d8aa9bde7de45aed',
  41             'description': 'md5:79794514261164ff27e36a21ad229fc5',
  42             'upload_date': '20150604',
  43             'duration': 154,
  44             'view_count': int,
  45             'comment_count': int,
  46         },
  47     }, {
  48         'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
  49         'only_matching': True,
  50     }, {
  51         'url': 'http://videofarm.daum.net/controller/player/VodPlayer.swf?vid=vwIpVpCQsT8%24&ref=',
  52         'info_dict': {
  53             'id': 'vwIpVpCQsT8$',
  54             'ext': 'flv',
  55             'title': '01-Korean War ( Trouble on the horizon )',
  56             'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
  57             'upload_date': '20080223',
  58             'thumbnail': 're:^https?://.*\.jpg$',
  59             'duration': 249,
  60             'view_count': int,
  61             'comment_count': int,
  62         },
  63     }]
  64
  65     def _real_extract(self, url):
  66         video_id = compat_urllib_parse_unquote(self._match_id(url))
  67         query = compat_urllib_parse.urlencode({'vid': video_id})
  68         movie_data = self._download_json(
  69             'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json?' + query,
  70             video_id, 'Downloading video formats info')
  71
  72         # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid
  73         if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id):
  74             return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id)
  75
  76         info = self._download_xml(
  77             'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
  78             'Downloading video info')
  79
  80         formats = []
  81         for format_el in movie_data['output_list']['output_list']:
  82             profile = format_el['profile']
  83             format_query = compat_urllib_parse.urlencode({
  84                 'vid': video_id,
  85                 'profile': profile,
  86             })
  87             url_doc = self._download_xml(
  88                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
  89                 video_id, note='Downloading video data for %s format' % profile)
  90             format_url = url_doc.find('result/url').text
  91             formats.append({
  92                 'url': format_url,
  93                 'format_id': profile,
  94                 'width': int_or_none(format_el.get('width')),
  95                 'height': int_or_none(format_el.get('height')),
  96                 'filesize': int_or_none(format_el.get('filesize')),
  97             })
  98         self._sort_formats(formats)
  99
 100         return {
 101             'id': video_id,
 102             'title': info.find('TITLE').text,
 103             'formats': formats,
 104             'thumbnail': xpath_text(info, 'THUMB_URL'),
 105             'description': xpath_text(info, 'CONTENTS'),
 106             'duration': int_or_none(xpath_text(info, 'DURATION')),
 107             'upload_date': info.find('REGDTTM').text[:8],
 108             'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')),
 109             'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')),
 110         }
 111
 112
 113 class DaumClipIE(InfoExtractor):
 114     _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
 115     IE_NAME = 'daum.net:clip'
 116
 117     _TESTS = [{
 118         'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
 119         'info_dict': {
 120             'id': '52554690',
 121             'ext': 'mp4',
 122             'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
 123             'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
 124             'upload_date': '20130831',
 125             'duration': 3868,
 126             'view_count': int,
 127         },
 128     }, {
 129         'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
 130         'only_matching': True,
 131     }]
 132
 133     def _real_extract(self, url):
 134         video_id = self._match_id(url)
 135         clip_info = self._download_json(
 136             'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
 137             video_id, 'Downloading clip info')['clip_bean']
 138
 139         return {
 140             '_type': 'url_transparent',
 141             'id': video_id,
 142             'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
 143             'title': clip_info['title'],
 144             'thumbnail': clip_info.get('thumb_url'),
 145             'description': clip_info.get('contents'),
 146             'duration': int_or_none(clip_info.get('duration')),
 147             'upload_date': clip_info.get('up_date')[:8],
 148             'view_count': int_or_none(clip_info.get('play_count')),
 149             'ie_key': 'Daum',
 150         }