[vlive] Improve and extract more metadata (Closes #8446)

youtube_dl/extractor/vlive.py

@@ -1,32 +1,27 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import hmac
-from hashlib import sha1
-from base64 import b64encode
-from time import time
-
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
+    dict_get,
-    determine_ext,
+    float_or_none,
-    int_or_none
+    int_or_none,
 )
 from ..compat import compat_urllib_parse
 
 
 class VLiveIE(InfoExtractor):
     IE_NAME = 'vlive'
-    # vlive.tv/video/ links redirect to www.vlive.tv/video/ 
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<id>[0-9]+)'
-    _VALID_URL = r'https?://(?:(www|m)\.)?vlive\.tv/video/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.vlive.tv/video/1326',
         'md5': 'cc7314812855ce56de70a06a27314983',
         'info_dict': {
             'id': '1326',
             'ext': 'mp4',
-            'title': '[V] Girl\'s Day\'s Broadcast',
+            'title': "[V] Girl's Day's Broadcast",
-            'creator': 'Girl\'s Day',
+            'creator': "Girl's Day",
+            'view_count': int,
         },
     }
 
@@ -34,49 +29,60 @@ class VLiveIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(
-            'http://www.vlive.tv/video/%s' % video_id,
+            'http://www.vlive.tv/video/%s' % video_id, video_id)
-            video_id, note='Download video page')
 
         long_video_id = self._search_regex(
-            r'vlive\.tv\.video\.ajax\.request\.handler\.init\("[0-9]+",\s?"[^"]*",\s?"([^"]+)",\s?"[^"]+",\s?"[^"]*",\s?"[^"]*"\)', webpage, 'long_video_id')
+            r'vlive\.tv\.video\.ajax\.request\.handler\.init\(\s*"[0-9]+"\s*,\s*"[^"]*"\s*,\s*"([^"]+)"',
+            webpage, 'long video id')
 
         key = self._search_regex(
-            r'vlive\.tv\.video\.ajax\.request\.handler\.init\("[0-9]+",\s?"[^"]*",\s?"[^"]+",\s?"([^"]+)",\s?"[^"]*",\s?"[^"]*"\)', webpage, 'key')
+            r'vlive\.tv\.video\.ajax\.request\.handler\.init\(\s*"[0-9]+"\s*,\s*"[^"]*"\s*,\s*"[^"]+"\s*,\s*"([^"]+)"',
+            webpage, 'key')
 
         title = self._og_search_title(webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
-        creator = self._html_search_regex(
-            r'<div class="info_area">\s*<strong[^>]+class="name">([^<>]+)</strong>', webpage, 'creator',fatal=False)
 
-        # doct = document type (xml or json), cpt = caption type (vtt or ttml)
+        playinfo = self._download_json(
-        url = "http://global.apis.naver.com/rmcnmv/rmcnmv/vod_play_videoInfo.json?videoId=%s&key=%s&ptc=http&doct=json&cpt=vtt" % (long_video_id, key)
+            'http://global.apis.naver.com/rmcnmv/rmcnmv/vod_play_videoInfo.json?%s'
-        
+            % compat_urllib_parse.urlencode({
-        playinfo = self._download_json(url, video_id, 'Downloading video json')
+                'videoId': long_video_id,
+                'key': key,
+                'ptc': 'http',
+                'doct': 'json',  # document type (xml or json)
+                'cpt': 'vtt',  # captions type (vtt or ttml)
+            }), video_id)
 
-        formats = []
+        formats = [{
-        for vid in playinfo.get('videos', {}).get('list', []):
+            'url': vid['source'],
-            formats.append({
+            'format_id': vid.get('encodingOption', {}).get('name'),
-                'url': vid['source'],
+            'abr': float_or_none(vid.get('bitrate', {}).get('audio')),
-                'ext': 'mp4',
+            'vbr': float_or_none(vid.get('bitrate', {}).get('video')),
-                'abr': vid.get('bitrate', {}).get('audio'),
+            'width': int_or_none(vid.get('encodingOption', {}).get('width')),
-                'vbr': vid.get('bitrate', {}).get('video'),
+            'height': int_or_none(vid.get('encodingOption', {}).get('height')),
-                'format_id': vid.get('encodingOption', {}).get('name'),
+            'filesize': int_or_none(vid.get('size')),
-                'height': int_or_none(vid.get('encodingOption', {}).get('height')),
+        } for vid in playinfo.get('videos', {}).get('list', []) if vid.get('source')]
-                'width': int_or_none(vid.get('encodingOption', {}).get('width')),
-            })
         self._sort_formats(formats)
 
+        thumbnail = self._og_search_thumbnail(webpage)
+        creator = self._html_search_regex(
+            r'<div[^>]+class="info_area"[^>]*>\s*<strong[^>]+class="name"[^>]*>([^<]+)</strong>',
+            webpage, 'creator', fatal=False)
+
+        view_count = int_or_none(playinfo.get('meta', {}).get('count'))
+
         subtitles = {}
         for caption in playinfo.get('captions', {}).get('list', []):
-            subtitles[caption['language']] = [
+            lang = dict_get(caption, ('language', 'locale', 'country', 'label'))
-                {'ext': determine_ext(caption['source'], default_ext='vtt'),
+            if lang and caption.get('source'):
-                 'url': caption['source']}]
+                subtitles[lang] = [{
+                    'ext': 'vtt',
+                    'url': caption['source']}]
 
         return {
             'id': video_id,
             'title': title,
             'creator': creator,
             'thumbnail': thumbnail,
+            'view_count': view_count,
             'formats': formats,
             'subtitles': subtitles,
         }