Merge pull request #204 from jdepoix/feature/invalid-video-id-error

added error which is thrown if url is used as the video id

youtube_transcript_api/__init__.py

@@ -13,4 +13,5 @@ from ._errors import (
     CookiesInvalid,
     FailedToCreateConsentCookie,
     YouTubeRequestFailed,
+    InvalidVideoId,
 )

youtube_transcript_api/_errors.py

@@ -53,6 +53,14 @@ class VideoUnavailable(CouldNotRetrieveTranscript):
     CAUSE_MESSAGE = 'The video is no longer available'
 
 
+class InvalidVideoId(CouldNotRetrieveTranscript):
+    CAUSE_MESSAGE = (
+        'You provided an invalid video id. Make sure you are using the video id and NOT the url!\n\n'
+        'Do NOT run: `YouTubeTranscriptApi.get_transcript("https://www.youtube.com/watch?v=1234")`\n'
+        'Instead run: `YouTubeTranscriptApi.get_transcript("1234")`'
+    )
+
+
 class TooManyRequests(CouldNotRetrieveTranscript):
     CAUSE_MESSAGE = (
         'YouTube is receiving too many requests from this IP and now requires solving a captcha to continue. '

youtube_transcript_api/_transcripts.py

@@ -24,6 +24,7 @@ from ._errors import (
     TranslationLanguageNotAvailable,
     NoTranscriptAvailable,
     FailedToCreateConsentCookie,
+    InvalidVideoId,
 )
 from ._settings import WATCH_URL
 
@@ -41,7 +42,6 @@ class TranscriptListFetcher(object):
         self._http_client = http_client
 
     def fetch(self, video_id):
-
         return TranscriptList.build(
             self._http_client,
             video_id,
@@ -52,6 +52,8 @@ class TranscriptListFetcher(object):
         splitted_html = html.split('"captions":')
 
         if len(splitted_html) <= 1:
+            if video_id.startswith('http://') or video_id.startswith('https://'):
+                raise InvalidVideoId(video_id)
             if 'class="g-recaptcha"' in html:
                 raise TooManyRequests(video_id)
             if '"playabilityStatus":' not in html:
@@ -182,7 +184,7 @@ class TranscriptList(object):
 
     def find_generated_transcript(self, language_codes):
         """
-        Finds a automatically generated transcript for a given language code.
+        Finds an automatically generated transcript for a given language code.
 
         :param language_codes: A list of language codes in a descending priority. For example, if this is set to
         ['de', 'en'] it will first try to fetch the german transcript (de) and then fetch the english transcript (en) if

youtube_transcript_api/test/test_api.py

@@ -20,6 +20,7 @@ from youtube_transcript_api import (
     CookiesInvalid,
     FailedToCreateConsentCookie,
     YouTubeRequestFailed,
+    InvalidVideoId,
 )
 
 
@@ -97,6 +98,16 @@ class TestYouTubeTranscriptApi(TestCase):
 
         self.assertTrue(transcript.is_generated)
 
+    def test_list_transcripts__url_as_video_id(self):
+        httpretty.register_uri(
+            httpretty.GET,
+            'https://www.youtube.com/watch',
+            body=load_asset('youtube_transcripts_disabled.html.static')
+        )
+
+        with self.assertRaises(InvalidVideoId):
+            YouTubeTranscriptApi.list_transcripts('https://www.youtube.com/watch?v=GJLlxj_dtq8')
+
     def test_translate_transcript(self):
         transcript = YouTubeTranscriptApi.list_transcripts('GJLlxj_dtq8').find_transcript(['en'])