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

Made testing more robust

This commit is contained in:
danielcliu 2020-01-22 22:35:35 -08:00
parent f9e553ebaf
commit 67604ec46c
2 changed files with 21 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
youtube_transcript_api/_api.py
View File

@ -53,20 +53,13 @@ class YouTubeTranscriptApi():
:param proxies: a dictionary mapping of http and https proxies to be used for the network requests
:type proxies: {'http': str, 'https': str} - http://docs.python-requests.org/en/master/user/advanced/#proxies
:param cookies: a string of the path to a text file containing youtube authorization cookies
:type cookies: str - cookies.txt
:type cookies: str
:return: the list of available transcripts
:rtype TranscriptList:
"""
with requests.Session() as http_client:
if cookies:
try:
cj = cookiejar.MozillaCookieJar()
cj.load(cookies)
http_client.cookies = cj
except IOError as e:
print("Warning: Path for cookies file was not valid. Did not load any cookies")
except FileNotFoundError as e:
print("Warning: Path for cookies file was not valid. Did not load any cookies")
http_client.cookies = cls.load_cookies(cookies)
http_client.proxies = proxies if proxies else {}
return TranscriptListFetcher(http_client).fetch(video_id)
@ -88,7 +81,7 @@ class YouTubeTranscriptApi():
:param proxies: a dictionary mapping of http and https proxies to be used for the network requests
:type proxies: {'http': str, 'https': str} - http://docs.python-requests.org/en/master/user/advanced/#proxies
:param cookies: a string of the path to a text file containing youtube authorization cookies
:type cookies: str - cookies.txt
:type cookies: str
: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]}):
@ -123,8 +116,23 @@ class YouTubeTranscriptApi():
:param proxies: a dictionary mapping of http and https proxies to be used for the network requests
:type proxies: {'http': str, 'https': str} - http://docs.python-requests.org/en/master/user/advanced/#proxies
:param cookies: a string of the path to a text file containing youtube authorization cookies
:type cookies: str - cookies.txt
:type cookies: str
:return: a list of dictionaries containing the 'text', 'start' and 'duration' keys
:rtype [{'text': str, 'start': float, 'end': float}]:
"""
return cls.list_transcripts(video_id, proxies, cookies).find_transcript(languages).fetch()
@classmethod
def load_cookies(cls, cookies):
cj = {}
try:
cj = cookiejar.MozillaCookieJar()
cj.load(cookies)
except IOError as e:
print("Warning: Path for cookies file was not valid. Did not load any cookies")
except FileNotFoundError as e:
print("Warning: Path for cookies file was not valid. Did not load any cookies")
if not cj:
raise IOError
return cj

2
youtube_transcript_api/test/test_api.py
View File

@ -185,6 +185,8 @@ class TestYouTubeTranscriptApi(TestCase):
YouTubeTranscriptApi.get_transcripts(['GJLlxj_dtq8'], cookies=cookies)
YouTubeTranscriptApi.get_transcript.assert_any_call('GJLlxj_dtq8', ('en',), None, cookies)
session_cookies = YouTubeTranscriptApi.load_cookies(cookies)
print("here: ", session_cookies.items())
def test_get_transcript__with_proxies(self):
proxies = {'http': '', 'https:': ''}