error handling improved

src/transcript_api.py

@@ -6,28 +6,75 @@ import logging
 
 import requests
 
-
 logger = logging.getLogger(__name__)
 
 
 class YouTubeTranscriptApi():
+    class CouldNotRetrieveTranscript(Exception):
+        """
+        Raised if a transcript could not be retrieved.
+        """
+
+        ERROR_MESSAGE = (
+            'Could not get the transcript for the video {video_url}! '
+            'Most likely subtitles have been disabled by the uploader or the video is no longer '
+            'available.'
+        )
+
+        def __init__(self, video_id):
+            super(YouTubeTranscriptApi.CouldNotRetrieveTranscript, self).__init__(
+                self.ERROR_MESSAGE.format(video_url=_TranscriptFetcher.WATCH_URL.format(video_id=video_id))
+            )
+            self.video_id = video_id
+
+
     @staticmethod
-    def get(*video_ids):
+    def get_transcripts(*video_ids, continue_after_error=False):
+        """
+        Retrieves the transcripts for a list of videos.
+
+        :param video_ids: a list of youtube video ids
+        :type video_ids: [str]
+        :param continue_after_error: if this is set the execution won't be stopped, if an error occurs while retrieving
+        one of the video transcripts
+        :type continue_after_error: bool
+        :return: a tuple containing a dictionary mapping video ids onto their corresponding transcripts, and a list of
+        video ids, which could not be retrieved
+        :rtype: ({str: [{'text': str, 'start': float, 'end': float}]}, [str]}
+        """
         data = {}
+        unretrievable_videos = []
 
         for video_id in video_ids:
             try:
-                data[video_id] = _TranscriptParser(_TranscriptFetcher(video_id).fetch()).parse()
+                data[video_id] = YouTubeTranscriptApi.get_transcript(video_id)
-            except Exception:
+            except Exception as exception:
-                logger.error(
+                if not continue_after_error:
-                    'Could not get the transcript for the video {video_url}! '
+                    raise exception
-                    'Most likely subtitles have been disabled by the uploader or the video is no longer '
-                    'available.'.format(
-                        video_url=_TranscriptFetcher.WATCH_URL.format(video_id=video_id)
-                    )
-                )
 
-        return data
+                unretrievable_videos.append(video_id)
+
+        return data, unretrievable_videos
+
+    @staticmethod
+    def get_transcript(video_id):
+        """
+        Retrieves the transcript for a single video.
+
+        :param video_id: the youtube video id
+        :type video_id: str
+        :return: a list of dictionaries containing the 'text', 'start' and 'duration' keys
+        :rtype: [{'text': str, 'start': float, 'end': float}]
+        """
+        try:
+            return _TranscriptParser(_TranscriptFetcher(video_id).fetch()).parse()
+        except Exception:
+            logger.error(
+                YouTubeTranscriptApi.CouldNotRetrieveTranscript.ERROR_MESSAGE.format(
+                    video_url=_TranscriptFetcher.WATCH_URL.format(video_id=video_id)
+                )
+            )
+            raise YouTubeTranscriptApi.CouldNotRetrieveTranscript(video_id)
 
 
 class _TranscriptFetcher():