Merge pull request #9 from jdepoix/feature/ISSUE-8

Feature/issue 8

README.md

@@ -54,7 +54,7 @@ You can also add the `languages` param if you want to make sure the transcripts
 YouTubeTranscriptApi.get_transcripts(video_ids, languages=['de', 'en'])
 ```
 
-It's a list of language codes in a descending priority. In this example it will first try to fetch the german transcript (`'de'`) and then fetch the english transcipt (`'en'`) if it fails to do so. As I can't provide a complete list of all working language codes with full certainty, you may have to play around with the language codes a bit, to find the one which is working for you!
+It's a list of language codes in a descending priority. In this example it will first try to fetch the german transcript (`'de'`) and then fetch the english transcript (`'en'`) if it fails to do so. As I can't provide a complete list of all working language codes with full certainty, you may have to play around with the language codes a bit, to find the one which is working for you!
 
 To get transcripts for a list fo video ids you can call:
 
@@ -72,10 +72,16 @@ Execute the CLI script using the video ids as parameters and the results will be
 youtube_transcript_api <first_video_id> <second_video_id> ...
 ```
 
+The CLI also gives you the option to provide a list of preferred languages:
+
+```
+youtube_transcript_api <first_video_id> <second_video_id> ... --languages de en
+```
+
 If you would prefer to write it into a file or pipe it into another application, you can also output the results as json using the following line:
 
 ```
-youtube_transcript_api --json <first_video_id> <second_video_id> ... > transcripts.json
+youtube_transcript_api <first_video_id> <second_video_id> ... --languages de en --json > transcripts.json
 ```
 
 ## Warning

setup.py

@@ -11,7 +11,7 @@ def get_long_description():
 
 setuptools.setup(
     name="youtube_transcript_api",
-    version="0.1.2",
+    version="0.1.3",
     author="Jonas Depoix",
     author_email="jonas.depoix@web.de",
     description="This is an python API which allows you to get the transcripts/subtitles for a given YouTube video. It also works for automatically generated subtitles and it does not require a headless browser, like other selenium based solutions do!",

youtube_transcript_api/__main__.py

@@ -6,18 +6,57 @@ from pprint import pprint
 
 import logging
 
+import argparse
+
 from ._api import YouTubeTranscriptApi
 
 
+def parse_args(args):
+    parser = argparse.ArgumentParser(
+        description=(
+            'This is an python API which allows you to get the transcripts/subtitles for a given YouTube video. '
+            'It also works for automatically generated subtitles and it does not require a headless browser, like '
+            'other selenium based solutions do!'
+        )
+    )
+    parser.add_argument('video_ids', nargs='*', type=str, help='List of YouTube video IDs.')
+    parser.add_argument(
+        '--languages',
+        nargs='*',
+        default=[],
+        type=str,
+        help=(
+            '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 transcipt (en) if it fails to do so. '
+            'As I can\'t provide a complete list of all working language codes with full certainty, you may have to '
+            'play around with the language codes a bit, to find the one which is working for you!'
+        ),
+    )
+    parser.add_argument(
+        '--json',
+        action='store_const',
+        const=True,
+        default=False,
+        help='If this flag is set the output will be JSON formatted.',
+    )
+
+    return parser.parse_args(args)
+
+
 def main():
     logging.basicConfig()
 
-    if len(sys.argv) <= 1:
+    parsed_args = parse_args(sys.argv[1:])
-        print('No YouTube video id was found')
+    transcripts, _ = YouTubeTranscriptApi.get_transcripts(
-    elif sys.argv[1] == '--json':
+        parsed_args.video_ids,
-        print(json.dumps(YouTubeTranscriptApi.get_transcripts(sys.argv[2:], continue_after_error=True)[0]))
+        languages=parsed_args.languages,
+        continue_after_error=True
+    )
+
+    if parsed_args.json:
+        print(json.dumps(transcripts))
     else:
-        pprint(YouTubeTranscriptApi.get_transcripts(sys.argv[1:], continue_after_error=True)[0])
+        pprint(transcripts)
 
 
 if __name__ == '__main__':