youtube_dl/extractor/daum.py

   1 # encoding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 import re
   6 import itertools
   7
   8 from .common import InfoExtractor
   9 from ..compat import (
  10     compat_urllib_parse,
  11     compat_urllib_parse_unquote,
  12 )
  13 from ..utils import (
  14     int_or_none,
  15     str_to_int,
  16     xpath_text,
  17     unescapeHTML,
  18 )
  19
  20
  21 class DaumIE(InfoExtractor):
  22     _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
  23     IE_NAME = 'daum.net'
  24
  25     _TESTS = [{
  26         'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
  27         'info_dict': {
  28             'id': 'vab4dyeDBysyBssyukBUjBz',
  29             'ext': 'mp4',
  30             'title': '마크 헌트 vs 안토니오 실바',
  31             'description': 'Mark Hunt vs Antonio Silva',
  32             'upload_date': '20131217',
  33             'thumbnail': 're:^https?://.*\.(?:jpg|png)',
  34             'duration': 2117,
  35             'view_count': int,
  36             'comment_count': int,
  37         },
  38     }, {
  39         'url': 'http://m.tvpot.daum.net/v/65139429',
  40         'info_dict': {
  41             'id': '65139429',
  42             'ext': 'mp4',
  43             'title': 'md5:a100d65d09cec246d8aa9bde7de45aed',
  44             'description': 'md5:79794514261164ff27e36a21ad229fc5',
  45             'upload_date': '20150604',
  46             'thumbnail': 're:^https?://.*\.(?:jpg|png)',
  47             'duration': 154,
  48             'view_count': int,
  49             'comment_count': int,
  50         },
  51     }, {
  52         'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
  53         'only_matching': True,
  54     }, {
  55         'url': 'http://videofarm.daum.net/controller/player/VodPlayer.swf?vid=vwIpVpCQsT8%24&ref=',
  56         'info_dict': {
  57             'id': 'vwIpVpCQsT8$',
  58             'ext': 'flv',
  59             'title': '01-Korean War ( Trouble on the horizon )',
  60             'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
  61             'upload_date': '20080223',
  62             'thumbnail': 're:^https?://.*\.(?:jpg|png)',
  63             'duration': 249,
  64             'view_count': int,
  65             'comment_count': int,
  66         },
  67     }]
  68
  69     def _real_extract(self, url):
  70         video_id = compat_urllib_parse_unquote(self._match_id(url))
  71         query = compat_urllib_parse.urlencode({'vid': video_id})
  72         movie_data = self._download_json(
  73             'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json?' + query,
  74             video_id, 'Downloading video formats info')
  75
  76         # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid
  77         if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id):
  78             return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id)
  79
  80         info = self._download_xml(
  81             'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
  82             'Downloading video info')
  83
  84         formats = []
  85         for format_el in movie_data['output_list']['output_list']:
  86             profile = format_el['profile']
  87             format_query = compat_urllib_parse.urlencode({
  88                 'vid': video_id,
  89                 'profile': profile,
  90             })
  91             url_doc = self._download_xml(
  92                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
  93                 video_id, note='Downloading video data for %s format' % profile)
  94             format_url = url_doc.find('result/url').text
  95             formats.append({
  96                 'url': format_url,
  97                 'format_id': profile,
  98                 'width': int_or_none(format_el.get('width')),
  99                 'height': int_or_none(format_el.get('height')),
 100                 'filesize': int_or_none(format_el.get('filesize')),
 101             })
 102         self._sort_formats(formats)
 103
 104         return {
 105             'id': video_id,
 106             'title': info.find('TITLE').text,
 107             'formats': formats,
 108             'thumbnail': xpath_text(info, 'THUMB_URL'),
 109             'description': xpath_text(info, 'CONTENTS'),
 110             'duration': int_or_none(xpath_text(info, 'DURATION')),
 111             'upload_date': info.find('REGDTTM').text[:8],
 112             'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')),
 113             'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')),
 114         }
 115
 116
 117 class DaumClipIE(InfoExtractor):
 118     _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
 119     IE_NAME = 'daum.net:clip'
 120
 121     _TESTS = [{
 122         'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
 123         'info_dict': {
 124             'id': '52554690',
 125             'ext': 'mp4',
 126             'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
 127             'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
 128             'upload_date': '20130831',
 129             'thumbnail': 're:^https?://.*\.(?:jpg|png)',
 130             'duration': 3868,
 131             'view_count': int,
 132         },
 133     }, {
 134         'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
 135         'only_matching': True,
 136     }]
 137
 138     def _real_extract(self, url):
 139         video_id = self._match_id(url)
 140         clip_info = self._download_json(
 141             'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
 142             video_id, 'Downloading clip info')['clip_bean']
 143
 144         return {
 145             '_type': 'url_transparent',
 146             'id': video_id,
 147             'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
 148             'title': unescapeHTML(clip_info['title']),
 149             'thumbnail': clip_info.get('thumb_url'),
 150             'description': clip_info.get('contents'),
 151             'duration': int_or_none(clip_info.get('duration')),
 152             'upload_date': clip_info.get('up_date')[:8],
 153             'view_count': int_or_none(clip_info.get('play_count')),
 154             'ie_key': 'Daum',
 155         }
 156
 157
 158 class DaumListIE(InfoExtractor):
 159     def _get_entries(self, list_id, list_id_type):
 160         name = None
 161         entries = []
 162         for pagenum in itertools.count(1):
 163             list_info = self._download_json(
 164                 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?size=48&init=true&order=date&page=%d&%s=%s' % (
 165                     pagenum, list_id_type, list_id), list_id,'Downloading list info - %s' % pagenum)
 166
 167             entries.extend([
 168                 self.url_result(
 169                     'http://tvpot.daum.net/v/%s' % clip['vid'])
 170                 for clip in list_info['clip_list']
 171             ])
 172
 173             if not name:
 174                 name = list_info.get('playlist_bean', {}).get('name') or \
 175                     list_info.get('potInfo', {}).get('name')
 176
 177             if not list_info.get('has_more'):
 178                 break
 179
 180         return name, entries
 181
 182
 183 class DaumPlaylistIE(DaumListIE):
 184     _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View\.do|Top\.tv)\?.*?playlistid=(?P<id>[0-9]+)'
 185     IE_NAME = 'daum.net:playlist'
 186
 187     _TESTS = [{
 188         'note': 'Playlist url with clipid',
 189         'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
 190         'info_dict': {
 191             'id': '6213966',
 192             'title': 'Woorissica Official',
 193         },
 194         'playlist_mincount': 181
 195     }, {
 196         'note': 'Playlist url with clipid - noplaylist',
 197         'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
 198         'info_dict': {
 199             'id': '73806844',
 200             'ext': 'mp4',
 201             'title': '151017 Airport',
 202             'upload_date': '20160117',
 203         },
 204         'params': {
 205             'noplaylist': True,
 206             'skip_download': True,
 207         }
 208     }]
 209
 210     def _real_extract(self, url):
 211         if DaumClipIE.suitable(url) and self._downloader.params.get('noplaylist'):
 212             return self.url_result(url, 'DaumClip')
 213
 214         list_id = self._match_id(url)
 215         self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id)
 216
 217         name, entries = self._get_entries(list_id, 'playlistid')
 218
 219         return self.playlist_result(entries, list_id, name)
 220
 221
 222 class DaumUserIE(DaumListIE):
 223     _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View|Top)\.do\?.*?ownerid=(?P<id>[0-9a-zA-Z]+)'
 224     IE_NAME = 'daum.net:user'
 225
 226     _TESTS = [{
 227         'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0',
 228         'info_dict': {
 229             'id': 'o2scDLIVbHc0',
 230             'title': '마이 리틀 텔레비전',
 231         },
 232         'playlist_mincount': 213
 233     }, {
 234         'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&clipid=73801156',
 235         'info_dict': {
 236             'id': '73801156',
 237             'ext': 'mp4',
 238             'title': '[미공개] 김구라, 오만석이 부릅니다 \'오케피\' - 마이 리틀 텔레비전 20160116',
 239             'upload_date': '20160117',
 240             'description': 'md5:5e91d2d6747f53575badd24bd62b9f36'
 241         },
 242         'params': {
 243             'noplaylist': True,
 244             'skip_download': True,
 245         }
 246     }, {
 247         'note': 'Playlist url has ownerid and playlistid, playlistid takes precedence',
 248         'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&playlistid=6196631',
 249         'info_dict': {
 250             'id': '6196631',
 251             'title': '마이 리틀 텔레비전 - 20160109',
 252         },
 253         'playlist_count': 11
 254     }, {
 255         'url': 'http://tvpot.daum.net/mypot/Top.do?ownerid=o2scDLIVbHc0',
 256         'only_matching': True,
 257     }]
 258
 259     def _real_extract(self, url):
 260         if DaumClipIE.suitable(url) and self._downloader.params.get('noplaylist'):
 261             return self.url_result(url, 'DaumClip')
 262
 263         if DaumPlaylistIE.suitable(url):
 264             return self.url_result(url, 'DaumPlaylist')
 265
 266         list_id = self._match_id(url)
 267         self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id)
 268         name, entries = self._get_entries(list_id, 'ownerid')
 269
 270         return self.playlist_result(entries, list_id, name)