[extractor] Fix _create_request when headers is None

Closes #4164

yt_dlp/extractor/_extractors.py

@@ -563,6 +563,7 @@ from .funimation import (
 )
 from .funk import FunkIE
 from .fusion import FusionIE
+from .fuyintv import FuyinTVIE
 from .gab import (
     GabTVIE,
     GabIE,

yt_dlp/extractor/common.py

@@ -730,14 +730,14 @@ class InfoExtractor:
         else:
             return err.code in variadic(expected_status)
 
-    def _create_request(self, url_or_request, data=None, headers={}, query={}):
+    def _create_request(self, url_or_request, data=None, headers=None, query=None):
         if isinstance(url_or_request, urllib.request.Request):
             return update_Request(url_or_request, data=data, headers=headers, query=query)
         if query:
             url_or_request = update_url_query(url_or_request, query)
-        return sanitized_Request(url_or_request, data, headers)
+        return sanitized_Request(url_or_request, data, headers or {})
 
-    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers={}, query={}, expected_status=None):
+    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers=None, query=None, expected_status=None):
         """
         Return the response handle.
 
@@ -765,8 +765,8 @@ class InfoExtractor:
         # geo unrestricted country. We will do so once we encounter any
         # geo restriction error.
         if self._x_forwarded_for_ip:
-            if 'X-Forwarded-For' not in headers:
+            headers = (headers or {}).copy()
-                headers['X-Forwarded-For'] = self._x_forwarded_for_ip
+            headers.setdefault('X-Forwarded-For', self._x_forwarded_for_ip)
 
         try:
             return self._downloader.urlopen(self._create_request(url_or_request, data, headers, query))

yt_dlp/extractor/fuyintv.py

@@ -0,0 +1,30 @@
+from .common import InfoExtractor
+from ..utils import traverse_obj
+
+
+class FuyinTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?fuyin\.tv/html/(?:\d+)/(?P<id>\d+)\.html'
+    _TESTS = [{
+        'url': 'https://www.fuyin.tv/html/2733/44129.html',
+        'info_dict': {
+            'id': '44129',
+            'ext': 'mp4',
+            'title': '第1集',
+            'description': 'md5:21a3d238dc8d49608e1308e85044b9c3',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        json_data = self._download_json(
+            'https://www.fuyin.tv/api/api/tv.movie/url',
+            video_id, query={'urlid': f'{video_id}'})
+        webpage = self._download_webpage(url, video_id, fatal=False)
+
+        return {
+            'id': video_id,
+            'title': traverse_obj(json_data, ('data', 'title')),
+            'url': json_data['data']['url'],
+            'ext': 'mp4',
+            'description': self._html_search_meta('description', webpage),
+        }

yt_dlp/extractor/videocampus_sachsen.py

@@ -6,14 +6,18 @@ from ..utils import ExtractorError
 
 
 class VideocampusSachsenIE(InfoExtractor):
-    IE_NAME = 'Vimp'
+    IE_NAME = 'ViMP'
     _INSTANCES = (
+        'bergauf.tv',
         'campus.demo.vimp.com',
         'corporate.demo.vimp.com',
         'dancehalldatabase.com',
+        'drehzahl.tv',
         'educhannel.hs-gesundheit.de',
         'emedia.ls.haw-hamburg.de',
         'globale-evolution.net',
+        'hohu.tv',
+        'htvideos.hightechhigh.org',
         'k210039.vimp.mivitec.net',
         'media.cmslegal.com',
         'media.hs-furtwangen.de',
@@ -25,6 +29,7 @@ class VideocampusSachsenIE(InfoExtractor):
         'mportal.europa-uni.de',
         'pacific.demo.vimp.com',
         'slctv.com',
+        'streaming.prairiesouth.ca',
         'tube.isbonline.cn',
         'univideo.uni-kassel.de',
         'ursula2.genetics.emory.edu',
@@ -52,11 +57,15 @@ class VideocampusSachsenIE(InfoExtractor):
         'vimp.weka-fachmedien.de',
         'webtv.univ-montp3.fr',
         'www.b-tu.de/media',
+        'www.bergauf.tv',
         'www.bigcitytv.de',
         'www.cad-videos.de',
+        'www.drehzahl.tv',
         'www.fh-bielefeld.de/medienportal',
+        'www.hohu.tv',
         'www.orvovideo.com',
         'www.rwe.tv',
+        'www.salzi.tv',
         'www.wenglor-media.com',
         'www2.univ-sba.dz',
     )
@@ -73,6 +82,7 @@ class VideocampusSachsenIE(InfoExtractor):
                 'id': 'e6b9349905c1628631f175712250f2a1',
                 'title': 'Konstruktiver Entwicklungsprozess Vorlesung 7',
                 'description': 'Konstruktiver Entwicklungsprozess Vorlesung 7',
+                'thumbnail': 'https://videocampus.sachsen.de/cache/1a985379ad3aecba8097a6902c7daa4e.jpg',
                 'ext': 'mp4',
             },
         },
@@ -82,6 +92,7 @@ class VideocampusSachsenIE(InfoExtractor):
                 'id': 'fc99c527e4205b121cb7c74433469262',
                 'title': 'Was ist selbstgesteuertes Lernen?',
                 'description': 'md5:196aa3b0509a526db62f84679522a2f5',
+                'thumbnail': 'https://videocampus.sachsen.de/cache/6f4a85096ba24cb398e6ce54446b57ae.jpg',
                 'display_id': 'Was-ist-selbstgesteuertes-Lernen',
                 'ext': 'mp4',
             },
@@ -92,6 +103,7 @@ class VideocampusSachsenIE(InfoExtractor):
                 'id': '09d4ed029002eb1bdda610f1103dd54c',
                 'title': 'Tutorial zur Nutzung von Adobe Connect aus Veranstalter-Sicht',
                 'description': 'md5:3d379ca3cc17b9da6784d7f58cca4d58',
+                'thumbnail': 'https://videocampus.sachsen.de/cache/2452498fe8c2d5a7dc79a05d30f407b6.jpg',
                 'display_id': 'Tutorial-zur-Nutzung-von-Adobe-Connect-aus-Veranstalter-Sicht',
                 'ext': 'mp4',
             },
@@ -103,6 +115,7 @@ class VideocampusSachsenIE(InfoExtractor):
                 'id': '0183356e41af7bfb83d7667b20d9b6a3',
                 'title': 'Présentation de la Faculté de droit et des sciences politiques - Journée portes ouvertes 2021/22',
                 'description': 'md5:508958bd93e0ca002ac731d94182a54f',
+                'thumbnail': 'https://www2.univ-sba.dz/cache/4d5d4a0b4189271a8cc6cb5328e14769.jpg',
                 'display_id': 'Presentation-de-la-Faculte-de-droit-et-des-sciences-politiques-Journee-portes-ouvertes-202122',
                 'ext': 'mp4',
             }
@@ -113,6 +126,7 @@ class VideocampusSachsenIE(InfoExtractor):
                 'id': 'c8816f1cc942c12b6cce57c835cffd7c',
                 'title': 'Preisverleihung »Produkte des Jahres 2022«',
                 'description': 'md5:60c347568ca89aa25b772c4ea564ebd3',
+                'thumbnail': 'https://vimp.weka-fachmedien.de/cache/da9f3090e9227b25beacf67ccf94de14.png',
                 'display_id': 'Preisverleihung-Produkte-des-Jahres-2022',
                 'ext': 'mp4',
             },
@@ -124,7 +138,7 @@ class VideocampusSachsenIE(InfoExtractor):
                 'title': 'Was ist selbstgesteuertes Lernen?',
                 'ext': 'mp4',
             },
-        }
+        },
     ]
 
     def _real_extract(self, url):
@@ -139,12 +153,14 @@ class VideocampusSachsenIE(InfoExtractor):
 
         if not (display_id or tmp_id):
             # Title, description from embedded page's meta wouldn't be correct
-            title = self._html_search_regex(r'<img[^>]* title="([^"<]+)"', webpage, 'title', fatal=False)
+            title = self._html_search_regex(r'<video-js[^>]* data-piwik-title="([^"<]+)"', webpage, 'title', fatal=False)
             description = None
+            thumbnail = None
         else:
             title = self._html_search_meta(('og:title', 'twitter:title', 'title'), webpage, fatal=False)
             description = self._html_search_meta(
-                ('og:description', 'twitter:description', 'description'), webpage, default=None)
+                ('og:description', 'twitter:description', 'description'), webpage, fatal=False)
+            thumbnail = self._html_search_meta(('og:image', 'twitter:image'), webpage, fatal=False)
 
         formats, subtitles = [], {}
         try:
@@ -162,7 +178,8 @@ class VideocampusSachsenIE(InfoExtractor):
             'id': video_id,
             'title': title,
             'description': description,
+            'thumbnail': thumbnail,
             'display_id': display_id,
             'formats': formats,
-            'subtitles': subtitles
+            'subtitles': subtitles,
         }

yt_dlp/utils.py

@@ -3015,9 +3015,9 @@ def update_url_query(url, query):
         query=urllib.parse.urlencode(qs, True)))
 
 
-def update_Request(req, url=None, data=None, headers={}, query={}):
+def update_Request(req, url=None, data=None, headers=None, query=None):
     req_headers = req.headers.copy()
-    req_headers.update(headers)
+    req_headers.update(headers or {})
     req_data = data or req.data
     req_url = update_url_query(url or req.get_full_url(), query)
     req_get_method = req.get_method()