Merge pull request #18 from jdepoix/bugfix/ISSUE-17
API no longer logs to error
This commit is contained in:
commit
69812e0024
|
@ -9,16 +9,11 @@ from xml.etree import ElementTree
|
||||||
|
|
||||||
import re
|
import re
|
||||||
|
|
||||||
import logging
|
|
||||||
|
|
||||||
import requests
|
import requests
|
||||||
|
|
||||||
from ._html_unescaping import unescape
|
from ._html_unescaping import unescape
|
||||||
|
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
|
||||||
|
|
||||||
|
|
||||||
class YouTubeTranscriptApi():
|
class YouTubeTranscriptApi():
|
||||||
class CouldNotRetrieveTranscript(Exception):
|
class CouldNotRetrieveTranscript(Exception):
|
||||||
"""
|
"""
|
||||||
|
@ -57,11 +52,11 @@ class YouTubeTranscriptApi():
|
||||||
:param continue_after_error: if this is set the execution won't be stopped, if an error occurs while retrieving
|
: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
|
one of the video transcripts
|
||||||
:type continue_after_error: bool
|
:type continue_after_error: bool
|
||||||
|
: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
|
||||||
:return: a tuple containing a dictionary mapping video ids onto their corresponding transcripts, and a list of
|
:return: a tuple containing a dictionary mapping video ids onto their corresponding transcripts, and a list of
|
||||||
video ids, which could not be retrieved
|
video ids, which could not be retrieved
|
||||||
:rtype: ({str: [{'text': str, 'start': float, 'end': float}]}, [str]}
|
:rtype: ({str: [{'text': str, 'start': float, 'end': float}]}, [str]}
|
||||||
:param proxies: a dictionary mapping of http and https proxies to be used for the network requests
|
|
||||||
:rtype {'http': str, 'https': str} - http://docs.python-requests.org/en/master/user/advanced/#proxies
|
|
||||||
"""
|
"""
|
||||||
data = {}
|
data = {}
|
||||||
unretrievable_videos = []
|
unretrievable_videos = []
|
||||||
|
@ -89,19 +84,14 @@ class YouTubeTranscriptApi():
|
||||||
do so. As I can't provide a complete list of all working language codes with full certainty, you may have 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!
|
play around with the language codes a bit, to find the one which is working for you!
|
||||||
:type languages: [str]
|
:type languages: [str]
|
||||||
|
: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
|
||||||
:return: a list of dictionaries containing the 'text', 'start' and 'duration' keys
|
:return: a list of dictionaries containing the 'text', 'start' and 'duration' keys
|
||||||
:rtype: [{'text': str, 'start': float, 'end': float}]
|
:rtype: [{'text': str, 'start': float, 'end': float}]
|
||||||
:param proxies: a dictionary mapping of http and https proxies to be used for the network requests
|
|
||||||
:rtype {'http': str, 'https': str} - http://docs.python-requests.org/en/master/user/advanced/#proxies
|
|
||||||
"""
|
"""
|
||||||
try:
|
try:
|
||||||
return _TranscriptParser(_TranscriptFetcher(video_id, languages, proxies).fetch()).parse()
|
return _TranscriptParser(_TranscriptFetcher(video_id, languages, proxies).fetch()).parse()
|
||||||
except Exception:
|
except Exception:
|
||||||
logger.error(
|
|
||||||
YouTubeTranscriptApi.CouldNotRetrieveTranscript.ERROR_MESSAGE.format(
|
|
||||||
video_url=_TranscriptFetcher.WATCH_URL.format(video_id=video_id)
|
|
||||||
)
|
|
||||||
)
|
|
||||||
raise YouTubeTranscriptApi.CouldNotRetrieveTranscript(video_id)
|
raise YouTubeTranscriptApi.CouldNotRetrieveTranscript(video_id)
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -18,17 +18,17 @@ class YouTubeTranscriptCli():
|
||||||
if parsed_args.http_proxy != '' or parsed_args.https_proxy != '':
|
if parsed_args.http_proxy != '' or parsed_args.https_proxy != '':
|
||||||
proxies = {"http": parsed_args.http_proxy, "https": parsed_args.https_proxy}
|
proxies = {"http": parsed_args.http_proxy, "https": parsed_args.https_proxy}
|
||||||
|
|
||||||
transcripts, _ = YouTubeTranscriptApi.get_transcripts(
|
transcripts, unretrievable_videos = YouTubeTranscriptApi.get_transcripts(
|
||||||
parsed_args.video_ids,
|
parsed_args.video_ids,
|
||||||
languages=parsed_args.languages,
|
languages=parsed_args.languages,
|
||||||
continue_after_error=True,
|
continue_after_error=True,
|
||||||
proxies=proxies
|
proxies=proxies
|
||||||
)
|
)
|
||||||
|
|
||||||
if parsed_args.json:
|
return '\n\n'.join(
|
||||||
return json.dumps(transcripts)
|
[str(YouTubeTranscriptApi.CouldNotRetrieveTranscript(video_id)) for video_id in unretrievable_videos]
|
||||||
else:
|
+ [json.dumps(transcripts) if parsed_args.json else pprint.pformat(transcripts)]
|
||||||
return pprint.pformat(transcripts)
|
)
|
||||||
|
|
||||||
def _parse_args(self):
|
def _parse_args(self):
|
||||||
parser = argparse.ArgumentParser(
|
parser = argparse.ArgumentParser(
|
||||||
|
|
Loading…
Reference in New Issue