youtube-dl

commit af62de104f33ebf8b473b3f7935451077fa56ee9
parent cd55c6ccd7b9cd0c48d475330c40f382eb0bc625
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sun, 15 Jan 2017 06:07:35 +0700

[beam:live] Improve and simplify (#10702, closes #11596)

Diffstat:
M
youtube_dl/extractor/beampro.py
 | 
71
+++++++++++++++++++++++++++++++----------------------------------------

1 file changed, 31 insertions(+), 40 deletions(-)
diff --git a/youtube_dl/extractor/beampro.py b/youtube_dl/extractor/beampro.py
@@ -14,25 +14,23 @@ from ..utils import (
 
 class BeamProLiveIE(InfoExtractor):
     IE_NAME = 'Beam:live'
-    _VALID_URL = r'https?://(?:\w+.)?beam.pro/(?P<id>[^?]+)$'
-    _API_CHANNEL = 'https://beam.pro/api/v1/channels/{0}'
-    _API_MANIFEST = 'https://beam.pro/api/v1/channels/{0}/manifest.m3u8'
+    _VALID_URL = r'https?://(?:\w+\.)?beam\.pro/(?P<id>[^/?#&]+)'
     _RATINGS = {'family': 0, 'teen': 13, '18+': 18}
-
     _TEST = {
         'url': 'http://www.beam.pro/niterhayven',
         'info_dict': {
             'id': '261562',
             'ext': 'mp4',
-            'uploader': 'niterhayven',
-            'timestamp': 1483477281,
-            'age_limit': 18,
             'title': 'Introducing The Witcher 3 //  The Grind Starts Now!',
+            'description': 'md5:0b161ac080f15fe05d18a07adb44a74d',
             'thumbnail': r're:https://.*\.jpg$',
+            'timestamp': 1483477281,
             'upload_date': '20170103',
-            'uploader_id': 373396,
-            'description': 'md5:0b161ac080f15fe05d18a07adb44a74d',
+            'uploader': 'niterhayven',
+            'uploader_id': '373396',
+            'age_limit': 18,
             'is_live': True,
+            'view_count': int,
         },
         'skip': 'niterhayven is offline',
         'params': {
@@ -41,42 +39,35 @@ class BeamProLiveIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        channel_id = self._match_id(url)
-        chan_data = self._download_json(self._API_CHANNEL.format(channel_id), channel_id)
+        channel_name = self._match_id(url)
 
-        if not chan_data.get('online'):
-            raise ExtractorError('{0} is offline'.format(channel_id), expected=True)
+        chan = self._download_json(
+            'https://beam.pro/api/v1/channels/%s' % channel_name, channel_name)
 
-        formats = self._extract_m3u8_formats(
-            self._API_MANIFEST.format(chan_data.get('id')), channel_id, ext='mp4')
+        if chan.get('online') is False:
+            raise ExtractorError(
+                '{0} is offline'.format(channel_name), expected=True)
 
-        self._sort_formats(formats)
-        info = {}
-        info['formats'] = formats
-        if chan_data:
-            info.update(self._extract_info(chan_data))
-        if not info.get('title'):
-            info['title'] = self._live_title(channel_id)
-        if not info.get('id'):  # barely possible but just in case
-            info['id'] = compat_str(abs(hash(channel_id)) % (10 ** 8))
+        channel_id = chan['id']
 
-        return info
+        formats = self._extract_m3u8_formats(
+            'https://beam.pro/api/v1/channels/%s/manifest.m3u8' % channel_id,
+            channel_name, ext='mp4', m3u8_id='hls', fatal=False)
+        self._sort_formats(formats)
 
-    def _extract_info(self, info):
-        thumbnail = try_get(info, lambda x: x['thumbnail']['url'], compat_str)
-        username = try_get(info, lambda x: x['user']['url'], compat_str)
-        video_id = compat_str(info['id']) if info.get('id') else None
-        rating = info.get('audience')
+        user_id = chan.get('userId') or try_get(chan, lambda x: x['user']['id'])
 
         return {
-            'id': video_id,
-            'title': info.get('name'),
-            'description': clean_html(info.get('description')),
-            'age_limit': self._RATINGS[rating] if rating in self._RATINGS else None,
-            'is_live': True if info.get('online') else False,
-            'timestamp': parse_iso8601(info.get('updatedAt')),
-            'uploader': info.get('token') or username,
-            'uploader_id': int_or_none(info.get('userId')),
-            'view_count': int_or_none(info.get('viewersTotal')),
-            'thumbnail': thumbnail,
+            'id': compat_str(chan.get('id') or channel_name),
+            'title': self._live_title(chan.get('name') or channel_name),
+            'description': clean_html(chan.get('description')),
+            'thumbnail': try_get(chan, lambda x: x['thumbnail']['url'], compat_str),
+            'timestamp': parse_iso8601(chan.get('updatedAt')),
+            'uploader': chan.get('token') or try_get(
+                chan, lambda x: x['user']['username'], compat_str),
+            'uploader_id': compat_str(user_id) if user_id else None,
+            'age_limit': self._RATINGS.get(chan.get('audience')),
+            'is_live': True,
+            'view_count': int_or_none(chan.get('viewersTotal')),
+            'formats': formats,
         }