feat: support headers

README.md

@@ -371,6 +371,14 @@ Using the CLI:
 youtube_transcript_api <first_video_id> <second_video_id> --cookies /path/to/your/cookies.txt
 ```
 
+## Headers
+
+You can pass additional headers to the `list_transcripts` method by providing a dictionary of headers as the `headers` parameter. This can be useful for various purposes, such as specifying the accepted encoding, setting a custom user agent, or including any other necessary headers for the request.
+
+```python
+headers = {'Accept-Encoding': 'gzip, deflate'}
+transcript_list = YouTubeTranscriptApi.list_transcripts(video_id, headers=headers)
+```
 
 ## Warning  
 

youtube_transcript_api/_api.py

@@ -16,7 +16,7 @@
 
 class YouTubeTranscriptApi(object):
     @classmethod
-    def list_transcripts(cls, video_id, proxies=None, cookies=None):
+    def list_transcripts(cls, video_id, proxies=None, cookies=None, headers=None):
         """
         Retrieves the list of transcripts which are available for a given video. It returns a `TranscriptList` object
         which is iterable and provides methods to filter the list of transcripts for specific languages. While iterating
@@ -61,13 +61,16 @@ def list_transcripts(cls, video_id, proxies=None, cookies=None):
         :type proxies: {'http': str, 'https': str} - http://docs.python-requests.org/en/master/user/advanced/#proxies
         :param cookies: a string of the path to a text file containing youtube authorization cookies
         :type cookies: str
+        :param headers: a dictionary of additional headers to include in the requests
+        :type headers: dict
         :return: the list of available transcripts
         :rtype TranscriptList:
         """
         with requests.Session() as http_client:
             if cookies:
                 http_client.cookies = cls._load_cookies(cookies, video_id)
             http_client.proxies = proxies if proxies else {}
+            http_client.headers.update(headers) if headers else {}
             return TranscriptListFetcher(http_client).fetch(video_id)
 
     @classmethod

youtube_transcript_api/_transcripts.py

@@ -88,7 +88,8 @@ def _fetch_video_html(self, video_id):
         return html
 
     def _fetch_html(self, video_id):
-        response = self._http_client.get(WATCH_URL.format(video_id=video_id), headers={'Accept-Language': 'en-US'})
+        self._http_client.headers.update({'Accept-Language': 'en-US'})
+        response = self._http_client.get(WATCH_URL.format(video_id=video_id))
         return unescape(_raise_http_errors(response, video_id).text)
 
 
@@ -288,7 +289,8 @@ def fetch(self, preserve_formatting=False):
         :return: a list of dictionaries containing the 'text', 'start' and 'duration' keys
         :rtype [{'text': str, 'start': float, 'end': float}]:
         """
-        response = self._http_client.get(self._url, headers={'Accept-Language': 'en-US'})
+        self._http_client.headers.update({'Accept-Language': 'en-US'})
+        response = self._http_client.get(self._url)
         return _TranscriptParser(preserve_formatting=preserve_formatting).parse(
             _raise_http_errors(response, self.video_id).text,
         )

youtube_transcript_api/test/test_api.py

@@ -291,6 +291,12 @@ def test_get_transcript__with_cookies(self):
             ]
         )
 
+    def test_get_transcript__with_headers(self):
+        headers = {'Accept-Encoding': 'gzip, deflate'}
+        transcript_list = YouTubeTranscriptApi.list_transcripts('GJLlxj_dtq8', headers=headers)
+        language_codes = {transcript.language_code for transcript in transcript_list}
+        self.assertGreater(len(language_codes), 0)
+
     def test_get_transcript__assertionerror_if_input_not_string(self):
         with self.assertRaises(AssertionError):
             YouTubeTranscriptApi.get_transcript(['video_id_1', 'video_id_2'])