KeyArgo
/
youtube-transcript-api
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Languages argument defaults to a tuple instead of a list.

This commit is contained in:
danielcliu 2019-11-10 22:44:24 -08:00
parent c7cb3117be
commit d224b02a80
2 changed files with 14 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
youtube_transcript_api/_api.py
View File

@ -40,7 +40,7 @@ class YouTubeTranscriptApi():
self.video_id = video_id self.video_id = video_id
@classmethod @classmethod
def get_transcripts(cls, video_ids, languages=['en'], continue_after_error=False, proxies=None): def get_transcripts(cls, video_ids, languages=('en',), continue_after_error=False, proxies=None):
""" """
Retrieves the transcripts for a list of videos. Retrieves the transcripts for a list of videos.
@ -75,7 +75,7 @@ class YouTubeTranscriptApi():
return data, unretrievable_videos return data, unretrievable_videos
@classmethod @classmethod
def get_transcript(cls, video_id, languages=['en'], proxies=None): def get_transcript(cls, video_id, languages=('en',), proxies=None):
""" """
Retrieves the transcript for a single video. Retrieves the transcript for a single video.
@ -106,7 +106,6 @@ class _TranscriptFetcher():
def __init__(self, video_id, languages, proxies): def __init__(self, video_id, languages, proxies):
self.video_id = video_id self.video_id = video_id
self.languages = languages self.languages = languages
print(languages)
self.proxies = proxies self.proxies = proxies
def fetch(self): def fetch(self):
@ -131,9 +130,16 @@ class _TranscriptFetcher():
return None return None
#Sorting the matched splits by string length because we want non-asr options returned first
#However, we don't want to include the length of the 'name' argument as it could possible throw this off
def _sort_splits(self, matched_split): def _sort_splits(self, matched_split):
"""Returns a value related to a given caption track url.
This function is used to sort the matched splits by string
length because we want non-asr and non-dialect options returned first.
With this in mind, it is remove the 'name' arugument from the url as
it could possibly make the values inaccurate to what we desire.
matched_split: The caption track url we want to return a value for.
"""
return len(re.sub(self.NAME_REGEX, r'\1', matched_split)) return len(re.sub(self.NAME_REGEX, r'\1', matched_split))
def _execute_api_request(self, timedtext_url): def _execute_api_request(self, timedtext_url):

7
youtube_transcript_api/test/test_api.py
View File

@ -99,8 +99,8 @@ class TestYouTubeTranscriptApi(TestCase):
YouTubeTranscriptApi.get_transcripts(['video_id_1', 'video_id_2'], continue_after_error=True) YouTubeTranscriptApi.get_transcripts(['video_id_1', 'video_id_2'], continue_after_error=True)
YouTubeTranscriptApi.get_transcript.assert_any_call(video_id_1, ['en'], None) YouTubeTranscriptApi.get_transcript.assert_any_call(video_id_1, ('en',), None)
YouTubeTranscriptApi.get_transcript.assert_any_call(video_id_2, ['en'], None) YouTubeTranscriptApi.get_transcript.assert_any_call(video_id_2, ('en',), None)
def test_get_transcript__with_proxies(self): def test_get_transcript__with_proxies(self):
proxies = {'http': '', 'https:': ''} proxies = {'http': '', 'https:': ''}
@ -118,5 +118,4 @@ class TestYouTubeTranscriptApi(TestCase):
) )
YouTubeTranscriptApi.get_transcript = MagicMock() YouTubeTranscriptApi.get_transcript = MagicMock()
YouTubeTranscriptApi.get_transcripts(['GJLlxj_dtq8'], proxies=proxies) YouTubeTranscriptApi.get_transcripts(['GJLlxj_dtq8'], proxies=proxies)
print(YouTubeTranscriptApi.get_transcript.mock_calls) YouTubeTranscriptApi.get_transcript.assert_any_call('GJLlxj_dtq8', ('en',), proxies)
YouTubeTranscriptApi.get_transcript.assert_any_call('GJLlxj_dtq8', ['en'], proxies)