Merge pull request #136 from ytdl-org/master

[pull] master from ytdl-org:master

youtube_dl/extractor/daum.py

@@ -2,25 +2,21 @@
 
 from __future__ import unicode_literals
 
-import re
 import itertools
 
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
     compat_urllib_parse_unquote,
-    compat_urllib_parse_urlencode,
     compat_urlparse,
 )
-from ..utils import (
-    int_or_none,
-    str_to_int,
-    xpath_text,
-    unescapeHTML,
-)
 
 
-class DaumIE(InfoExtractor):
+class DaumBaseIE(InfoExtractor):
+    _KAKAO_EMBED_BASE = 'http://tv.kakao.com/embed/player/cliplink/'
+
+
+class DaumIE(DaumBaseIE):
     _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
     IE_NAME = 'daum.net'
 
@@ -36,6 +32,9 @@ class DaumIE(InfoExtractor):
             'duration': 2117,
             'view_count': int,
             'comment_count': int,
+            'uploader_id': 186139,
+            'uploader': '콘간지',
+            'timestamp': 1387310323,
         },
     }, {
         'url': 'http://m.tvpot.daum.net/v/65139429',
@@ -44,11 +43,14 @@ class DaumIE(InfoExtractor):
             'ext': 'mp4',
             'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118',
             'description': 'md5:79794514261164ff27e36a21ad229fc5',
-            'upload_date': '20150604',
+            'upload_date': '20150118',
             'thumbnail': r're:^https?://.*\.(?:jpg|png)',
             'duration': 154,
             'view_count': int,
             'comment_count': int,
+            'uploader': 'MBC 예능',
+            'uploader_id': 132251,
+            'timestamp': 1421604228,
         },
     }, {
         'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
@@ -59,12 +61,15 @@ class DaumIE(InfoExtractor):
             'id': 'vwIpVpCQsT8$',
             'ext': 'flv',
             'title': '01-Korean War ( Trouble on the horizon )',
-            'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
+            'description': 'Korean War 01\r\nTrouble on the horizon\r\n전쟁의 먹구름',
             'upload_date': '20080223',
             'thumbnail': r're:^https?://.*\.(?:jpg|png)',
             'duration': 249,
             'view_count': int,
             'comment_count': int,
+            'uploader': '까칠한 墮落始祖 황비홍님의',
+            'uploader_id': 560824,
+            'timestamp': 1203770745,
         },
     }, {
         # Requires dte_type=WEB (#9972)
@@ -73,60 +78,24 @@ class DaumIE(InfoExtractor):
         'info_dict': {
             'id': 's3794Uf1NZeZ1qMpGpeqeRU',
             'ext': 'mp4',
-            'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny) [쇼! 음악중심] 508회 20160611',
-            'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\n\n[쇼! 음악중심] 20160611, 507회',
-            'upload_date': '20160611',
+            'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
+            'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
+            'upload_date': '20170129',
+            'uploader': '쇼! 음악중심',
+            'uploader_id': 2653210,
+            'timestamp': 1485684628,
         },
     }]
 
     def _real_extract(self, url):
         video_id = compat_urllib_parse_unquote(self._match_id(url))
-        movie_data = self._download_json(
-            'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json',
-            video_id, 'Downloading video formats info', query={'vid': video_id, 'dte_type': 'WEB'})
-
-        # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid
-        if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id):
-            return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id)
-
-        info = self._download_xml(
-            'http://tvpot.daum.net/clip/ClipInfoXml.do', video_id,
-            'Downloading video info', query={'vid': video_id})
-
-        formats = []
-        for format_el in movie_data['output_list']['output_list']:
-            profile = format_el['profile']
-            format_query = compat_urllib_parse_urlencode({
-                'vid': video_id,
-                'profile': profile,
-            })
-            url_doc = self._download_xml(
-                'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
-                video_id, note='Downloading video data for %s format' % profile)
-            format_url = url_doc.find('result/url').text
-            formats.append({
-                'url': format_url,
-                'format_id': profile,
-                'width': int_or_none(format_el.get('width')),
-                'height': int_or_none(format_el.get('height')),
-                'filesize': int_or_none(format_el.get('filesize')),
-            })
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': info.find('TITLE').text,
-            'formats': formats,
-            'thumbnail': xpath_text(info, 'THUMB_URL'),
-            'description': xpath_text(info, 'CONTENTS'),
-            'duration': int_or_none(xpath_text(info, 'DURATION')),
-            'upload_date': info.find('REGDTTM').text[:8],
-            'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')),
-            'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')),
-        }
+        if not video_id.isdigit():
+            video_id += '@my'
+        return self.url_result(
+            self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id)
 
 
-class DaumClipIE(InfoExtractor):
+class DaumClipIE(DaumBaseIE):
     _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
     IE_NAME = 'daum.net:clip'
     _URL_TEMPLATE = 'http://tvpot.daum.net/clip/ClipView.do?clipid=%s'
@@ -142,6 +111,9 @@ class DaumClipIE(InfoExtractor):
             'thumbnail': r're:^https?://.*\.(?:jpg|png)',
             'duration': 3868,
             'view_count': int,
+            'uploader': 'GOMeXP',
+            'uploader_id': 6667,
+            'timestamp': 1377911092,
         },
     }, {
         'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
@@ -154,22 +126,8 @@ class DaumClipIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        clip_info = self._download_json(
-            'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
-            video_id, 'Downloading clip info')['clip_bean']
-
-        return {
-            '_type': 'url_transparent',
-            'id': video_id,
-            'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
-            'title': unescapeHTML(clip_info['title']),
-            'thumbnail': clip_info.get('thumb_url'),
-            'description': clip_info.get('contents'),
-            'duration': int_or_none(clip_info.get('duration')),
-            'upload_date': clip_info.get('up_date')[:8],
-            'view_count': int_or_none(clip_info.get('play_count')),
-            'ie_key': 'Daum',
-        }
+        return self.url_result(
+            self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id)
 
 
 class DaumListIE(InfoExtractor):

youtube_dl/extractor/kakao.py

@@ -6,14 +6,15 @@ from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     int_or_none,
+    strip_or_none,
     unified_timestamp,
     update_url_query,
 )
 
 
 class KakaoIE(InfoExtractor):
-    _VALID_URL = r'https?://tv\.kakao\.com/channel/(?P<channel>\d+)/cliplink/(?P<id>\d+)'
-    _API_BASE = 'http://tv.kakao.com/api/v1/ft/cliplinks'
+    _VALID_URL = r'https?://(?:play-)?tv\.kakao\.com/(?:channel/\d+|embed/player)/cliplink/(?P<id>\d+|[^?#&]+@my)'
+    _API_BASE_TMPL = 'http://tv.kakao.com/api/v1/ft/cliplinks/%s/'
 
     _TESTS = [{
         'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083',
@@ -36,7 +37,7 @@ class KakaoIE(InfoExtractor):
             'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
             'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
             'uploader_id': 2653210,
-            'uploader': '쇼 음악중심',
+            'uploader': '쇼! 음악중심',
             'timestamp': 1485684628,
             'upload_date': '20170129',
         }
@@ -44,6 +45,8 @@ class KakaoIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        display_id = video_id.rstrip('@my')
+        api_base = self._API_BASE_TMPL % video_id
 
         player_header = {
             'Referer': update_url_query(
@@ -55,20 +58,22 @@ class KakaoIE(InfoExtractor):
                 })
         }
 
-        QUERY_COMMON = {
+        query = {
             'player': 'monet_html5',
             'referer': url,
             'uuid': '',
             'service': 'kakao_tv',
             'section': '',
             'dteType': 'PC',
+            'fields': ','.join([
+                '-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title',
+                'description', 'channelId', 'createTime', 'duration', 'playCount',
+                'likeCount', 'commentCount', 'tagList', 'channel', 'name',
+                'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault'])
         }
 
-        query = QUERY_COMMON.copy()
-        query['fields'] = 'clipLink,clip,channel,hasPlusFriend,-service,-tagList'
         impress = self._download_json(
-            '%s/%s/impress' % (self._API_BASE, video_id),
-            video_id, 'Downloading video info',
+            api_base + 'impress', display_id, 'Downloading video info',
             query=query, headers=player_header)
 
         clip_link = impress['clipLink']
@@ -78,30 +83,27 @@ class KakaoIE(InfoExtractor):
 
         tid = impress.get('tid', '')
 
-        query = QUERY_COMMON.copy()
         query.update({
+            'fields': '-*,outputList,profile,width,height,label,filesize',
             'tid': tid,
             'profile': 'HIGH',
         })
         raw = self._download_json(
-            '%s/%s/raw' % (self._API_BASE, video_id),
-            video_id, 'Downloading video formats info',
+            api_base + 'raw', display_id, 'Downloading video formats info',
             query=query, headers=player_header)
 
         formats = []
         for fmt in raw.get('outputList', []):
             try:
                 profile_name = fmt['profile']
+                query.update({
+                    'profile': profile_name,
+                    'fields': '-*,url',
+                })
                 fmt_url_json = self._download_json(
-                    '%s/%s/raw/videolocation' % (self._API_BASE, video_id),
-                    video_id,
+                    api_base + 'raw/videolocation', display_id,
                     'Downloading video URL for profile %s' % profile_name,
-                    query={
-                        'service': 'kakao_tv',
-                        'section': '',
-                        'tid': tid,
-                        'profile': profile_name
-                    }, headers=player_header, fatal=False)
+                    query=query, headers=player_header, fatal=False)
 
                 if fmt_url_json is None:
                     continue
@@ -134,9 +136,9 @@ class KakaoIE(InfoExtractor):
             })
 
         return {
-            'id': video_id,
+            'id': display_id,
             'title': title,
-            'description': clip.get('description'),
+            'description': strip_or_none(clip.get('description')),
             'uploader': clip_link.get('channel', {}).get('name'),
             'uploader_id': clip_link.get('channelId'),
             'thumbnails': thumbs,
@@ -146,4 +148,5 @@ class KakaoIE(InfoExtractor):
             'like_count': int_or_none(clip.get('likeCount')),
             'comment_count': int_or_none(clip.get('commentCount')),
             'formats': formats,
+            'tags': clip.get('tagList'),
         }