[youtube] fix extraction for embed restricted live streams(fixes #16433)

[youtube-dl] / youtube_dl / extractor / imdb.py

diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py
index 3a2b7cec5cebb0d0bc06aec0d93400c4987adc8d..4254219687a1ff54ca15b49bea748f331a3d1f1d 100644 (file)
--- a/youtube_dl/extractor/imdb.py
+++ b/youtube_dl/extractor/imdb.py
@@ -3,28 +3,43 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
+    determine_ext,
     mimetype2ext,
     qualities,
+    remove_end,
 )
 
 
 class ImdbIE(InfoExtractor):
     IE_NAME = 'imdb'
     IE_DESC = 'Internet Movie Database trailers'
-    _VALID_URL = r'https?://(?:www|m)\.imdb\.com/video/[^/]+/vi(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title).+?[/-]vi(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
         'info_dict': {
             'id': '2524815897',
             'ext': 'mp4',
-            'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
+            'title': 'Ice Age: Continental Drift Trailer (No. 2)',
             'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
         }
     }, {
         'url': 'http://www.imdb.com/video/_/vi2524815897',
         'only_matching': True,
+    }, {
+        'url': 'http://www.imdb.com/title/tt1667889/?ref_=ext_shr_eml_vi#lb-vi2524815897',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.imdb.com/videoplayer/vi1562949145',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.imdb.com/title/tt4218696/videoplayer/vi2608641561',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -60,34 +75,40 @@ class ImdbIE(InfoExtractor):
             video_info_list = format_info.get('videoInfoList')
             if not video_info_list or not isinstance(video_info_list, list):
                 continue
-            video_info = video_info_list[0]
-            if not video_info or not isinstance(video_info, dict):
-                continue
-            video_url = video_info.get('videoUrl')
-            if not video_url:
-                continue
-            format_id = format_info.get('ffname')
-            formats.append({
-                'format_id': format_id,
-                'url': video_url,
-                'ext': mimetype2ext(video_info.get('videoMimeType')),
-                'quality': quality(format_id),
-            })
+            for video_info in video_info_list:
+                if not video_info or not isinstance(video_info, dict):
+                    continue
+                video_url = video_info.get('videoUrl')
+                if not video_url or not isinstance(video_url, compat_str):
+                    continue
+                if (video_info.get('videoMimeType') == 'application/x-mpegURL' or
+                        determine_ext(video_url) == 'm3u8'):
+                    formats.extend(self._extract_m3u8_formats(
+                        video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id='hls', fatal=False))
+                    continue
+                format_id = format_info.get('ffname')
+                formats.append({
+                    'format_id': format_id,
+                    'url': video_url,
+                    'ext': mimetype2ext(video_info.get('videoMimeType')),
+                    'quality': quality(format_id),
+                })
         self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': self._og_search_title(webpage),
+            'title': remove_end(self._og_search_title(webpage), ' - IMDb'),
             'formats': formats,
             'description': descr,
-            'thumbnail': format_info['slate'],
+            'thumbnail': format_info.get('slate'),
         }
 
 
 class ImdbListIE(InfoExtractor):
     IE_NAME = 'imdb:list'
     IE_DESC = 'Internet Movie Database lists'
-    _VALID_URL = r'https?://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
+    _VALID_URL = r'https?://(?:www\.)?imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
     _TEST = {
         'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
         'info_dict': {