From f8f3b6f2bf5673d96c5743de008bd9f9214156fe Mon Sep 17 00:00:00 2001
From: Grabien <max@grabien.com>
Date: Mon, 27 Sep 2021 22:22:39 +0300
Subject: [PATCH] C-Span links support improvements

---
 youtube_dl/extractor/cspan.py   | 33 +++++++++++++++++++++++++++++----
 youtube_dl/extractor/generic.py | 11 +++++++++++
 2 files changed, 40 insertions(+), 4 deletions(-)

diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
index 2e01aff48..fbd0e7237 100644
--- a/youtube_dl/extractor/cspan.py
+++ b/youtube_dl/extractor/cspan.py
@@ -1,11 +1,14 @@
 from __future__ import unicode_literals
 
+import os
 import re
 
-from .common import InfoExtractor
+from .common import InfoExtractor, compat_str, compat_urllib_parse_unquote
+from .senateisvp import SenateISVPIE
+from .ustream import UstreamIE
 from ..utils import (
-    determine_ext,
     ExtractorError,
+    determine_ext,
     extract_attributes,
     find_xpath_attr,
     get_element_by_attribute,
@@ -18,11 +21,10 @@ from ..utils import (
     str_to_int,
     unescapeHTML,
 )
-from .senateisvp import SenateISVPIE
-from .ustream import UstreamIE
 
 
 class CSpanIE(InfoExtractor):
+    _BASIC_URL = r'https?://(?:www\.)?c-span\.org/'
     _VALID_URL = r'https?://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
     IE_DESC = 'C-SPAN'
     _TESTS = [{
@@ -81,6 +83,29 @@ class CSpanIE(InfoExtractor):
     }]
     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
 
+    @classmethod
+    def is_basic_url(cls, url):
+        if '_BASIC_URL_RE' not in cls.__dict__:
+            cls._BASIC_URL_RE = re.compile(cls._BASIC_URL)
+
+        return cls._BASIC_URL_RE.match(url) is not None
+
+    @classmethod
+    def get_basic_url(cls, url):
+        return "/".join(url.rstrip('/').split('/')[:3])
+
+    @classmethod
+    def _get_id(cls, url):
+        if '_ID_URL_RE' not in cls.__dict__:
+            cls._ID_URL_RE = re.compile(cls._ID_URL)
+
+        if cls._ID_URL_RE.match(url) is not None:
+            m = cls._ID_URL_RE.match(url)
+            assert m
+            return compat_str(m.group('id'))
+        else:
+            return compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_type = None
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index a9c064105..ef4e0b96e 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -48,6 +48,7 @@ from .nexx import (
     NexxIE,
     NexxEmbedIE,
 )
+from .cspan import CSpanIE
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
@@ -3551,6 +3552,16 @@ class GenericIE(InfoExtractor):
             if entry_info_dict.get('formats'):
                 self._sort_formats(entry_info_dict['formats'])
 
+            if CSpanIE.is_basic_url(url):
+                basic_url = CSpanIE.get_basic_url(url)
+                for f in entry_info_dict['formats']:
+                    f.setdefault('http_headers', {})['referer'] = basic_url + "/"
+                    f.setdefault('http_headers', {})['origin'] = basic_url
+                    f.setdefault('http_headers', {})['accept'] = "*/*"
+                    f.setdefault('http_headers', {})['sec-fetch-dest'] = "empty"
+                    f.setdefault('http_headers', {})['sec-fetch-mode'] = "cors"
+                    f.setdefault('http_headers', {})['sec-fetch-site'] = "cross-site"
+
             entries.append(entry_info_dict)
 
         if len(entries) == 1: