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