added FormatterLoader

youtube_transcript_api/_errors.py

@@ -38,12 +38,14 @@ class CouldNotRetrieveTranscript(Exception):
 class VideoUnavailable(CouldNotRetrieveTranscript):
     CAUSE_MESSAGE = 'The video is no longer available'
 
+
 class TooManyRequests(CouldNotRetrieveTranscript):
     CAUSE_MESSAGE = ("YouTube is receiving too many requests from this IP and now requires solving a captcha to continue. One of the following things can be done to work around this:\n\
     - Manually solve the captcha in a browser and export the cookie. Read here how to use that cookie with youtube-transcript-api: https://github.com/jdepoix/youtube-transcript-api#cookies\n\
     - Use a different IP address\n\
     - Wait until the ban on your IP has been lifted")
 
+
 class TranscriptsDisabled(CouldNotRetrieveTranscript):
     CAUSE_MESSAGE = 'Subtitles are disabled for this video'
 

youtube_transcript_api/formatters.py

@@ -1,5 +1,7 @@
 import json
 
+import pprint
+
 
 class Formatter(object):
     """Formatter should be used as an abstract base class.
@@ -22,6 +24,16 @@ class Formatter(object):
             'their own .format() method.')
 
 
+class PrettyPrintFormatter(Formatter):
+    def format(self, **kwargs):
+        """Pretty prints a transcript.
+
+        :return: A pretty printed string representation of the transcript dict.'
+        :rtype str
+        """
+        return pprint.pformat(self._transcript, **kwargs)
+
+
 class JSONFormatter(Formatter):
     def format(self, **kwargs):
         """Converts a transcript into a JSON string.
@@ -72,12 +84,12 @@ class WebVTTFormatter(Formatter):
         """
         lines = []
         for i, line in enumerate(self._transcript):
-            if i < len(self._transcript)-1:
+            if i < len(self._transcript) - 1:
                 # Looks ahead, use next start time since duration value
                 # would create an overlap between start times.
                 time_text = "{} --> {}".format(
                     self._seconds_to_timestamp(line['start']),
-                    self._seconds_to_timestamp(self._transcript[i+1]['start'])
+                    self._seconds_to_timestamp(self._transcript[i + 1]['start'])
                 )
             else:
                 # Reached the end, cannot look ahead, use duration now.
@@ -89,3 +101,27 @@ class WebVTTFormatter(Formatter):
             lines.append("{}\n{}".format(time_text, line['text']))
         
         return "WEBVTT\n\n" + "\n\n".join(lines) + "\n"
+
+
+class FormatterLoader(object):
+    TYPES = {
+        'json': JSONFormatter,
+        'pretty': PrettyPrintFormatter,
+        'text': TextFormatter,
+        'webvvt': WebVTTFormatter,
+    }
+
+    class UnknownFormatterType(Exception):
+        def __init__(self, formatter_type):
+            super(FormatterLoader.UnknownFormatterType, self).__init__(
+                f'The format \'{formatter_type}\' is not supported. '
+                f'Choose one of the following formats: {", ".join(FormatterLoader.TYPES.keys())}'
+            )
+
+    def __init__(self, formatter_type='pretty'):
+        if formatter_type not in FormatterLoader.TYPES.keys():
+            raise FormatterLoader.UnknownFormatterType(formatter_type)
+        self._formatter = FormatterLoader.TYPES[formatter_type]
+
+    def load(self, transcript):
+        return self._formatter(transcript)

youtube_transcript_api/test/test_formatters.py

@@ -1,12 +1,15 @@
-import json
-from mock import MagicMock
 from unittest import TestCase
 
+import json
+
+import pprint
+
 from youtube_transcript_api.formatters import (
     Formatter,
     JSONFormatter,
     TextFormatter,
-    WebVTTFormatter
+    WebVTTFormatter,
+    PrettyPrintFormatter, FormatterLoader
 )
 
 
@@ -35,6 +38,7 @@ class TestFormatters(TestCase):
     def test_webvtt_formatter_starting(self):
         content = WebVTTFormatter(self.transcript).format()
         lines = content.split('\n')
+
         # test starting lines
         self.assertEqual(lines[0], "WEBVTT")
         self.assertEqual(lines[1], "")
@@ -42,16 +46,40 @@ class TestFormatters(TestCase):
     def test_webvtt_formatter_ending(self):
         content = WebVTTFormatter(self.transcript).format()
         lines = content.split('\n')
+
         # test ending lines
         self.assertEqual(lines[-2], self.transcript[-1]['text'])
         self.assertEqual(lines[-1], "")
 
+    def test_pretty_print_formatter(self):
+        content = PrettyPrintFormatter(self.transcript).format()
+
+        self.assertEqual(content, pprint.pformat(self.transcript))
+
     def test_json_formatter(self):
         content = JSONFormatter(self.transcript).format()
+
         self.assertEqual(json.loads(content), self.transcript)
 
     def test_text_formatter(self):
         content = TextFormatter(self.transcript).format()
         lines = content.split('\n')
+
         self.assertEqual(lines[0], self.transcript[0]["text"])
         self.assertEqual(lines[-1], self.transcript[-1]["text"])
+
+    def test_formatter_loader(self):
+        loader = FormatterLoader('json')
+        formatter = loader.load(self.transcript)
+
+        self.assertTrue(isinstance(formatter, JSONFormatter))
+
+    def test_formatter_loader__default_formatter(self):
+        loader = FormatterLoader()
+        formatter = loader.load(self.transcript)
+
+        self.assertTrue(isinstance(formatter, PrettyPrintFormatter))
+
+    def test_formatter_loader__unknown_format(self):
+        with self.assertRaises(FormatterLoader.UnknownFormatterType):
+            FormatterLoader('png')