Merge pull request #488 from jdepoix/feature/remove-depcreated-methods

Removed deprecated methods: get_transcript, get_transcripts, list_transcripts

Author: jdepoix

.github/ISSUE_TEMPLATE/bug_report.md

@@ -15,7 +15,7 @@ Steps to reproduce the behavior:
 ### What code / cli command are you executing?
 For example: I am running
 ```
-YouTubeTranscriptApi.get_transcript ...
+YouTubeTranscriptApi().fetch() ...
 ```
 
 ### Which Python version are you using?

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "youtube-transcript-api"
-version = "1.1.1"
+version = "1.2.0"
 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, supports translating subtitles and it does not require a headless browser, like other selenium based solutions do!"
 readme = "README.md"
 license = "MIT"

youtube_transcript_api/_api.py

@@ -1,11 +1,10 @@
-import warnings
 from typing import Optional, Iterable
 
 from requests import Session
 from requests.adapters import HTTPAdapter
 from urllib3 import Retry
 
-from .proxies import ProxyConfig, GenericProxyConfig
+from .proxies import ProxyConfig
 
 from ._transcripts import TranscriptListFetcher, FetchedTranscript, TranscriptList
 
@@ -126,169 +125,3 @@ def list(
             Make sure that this is the actual ID, NOT the full URL to the video!
         """
         return self._fetcher.fetch(video_id)
-
-    @classmethod
-    def list_transcripts(cls, video_id, proxies=None):
-        """
-        DEPRECATED: use the `list` method instead!
-
-        Retrieves the list of transcripts which are available for a given video. It returns a `TranscriptList` object
-        which is iterable and provides methods to filter the list of transcripts for specific languages. While iterating
-        over the `TranscriptList` the individual transcripts are represented by `Transcript` objects, which provide
-        metadata and can either be fetched by calling `transcript.fetch()` or translated by calling
-        `transcript.translate('en')`. Example:
-
-            # retrieve the available transcripts
-            transcript_list = YouTubeTranscriptApi.list_transcripts('video_id')
-
-            # iterate over all available transcripts
-            for transcript in transcript_list:
-                # the Transcript object provides metadata properties
-                print(
-                    transcript.video_id,
-                    transcript.language,
-                    transcript.language_code,
-                    # whether it has been manually created or generated by YouTube
-                    transcript.is_generated,
-                    # a list of languages the transcript can be translated to
-                    transcript.translation_languages,
-                )
-
-                # fetch the actual transcript data
-                print(transcript.fetch())
-
-                # translating the transcript will return another transcript object
-                print(transcript.translate('en').fetch())
-
-            # you can also directly filter for the language you are looking for, using the transcript list
-            transcript = transcript_list.find_transcript(['de', 'en'])
-
-            # or just filter for manually created transcripts
-            transcript = transcript_list.find_manually_created_transcript(['de', 'en'])
-
-            # or automatically generated ones
-            transcript = transcript_list.find_generated_transcript(['de', 'en'])
-
-        :param video_id: the youtube video id
-        :type video_id: 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: the list of available transcripts
-        :rtype TranscriptList:
-        """
-        warnings.warn(
-            "`list_transcripts` is deprecated and will be removed in a future version. "
-            "Use the `list` method instead!",
-            DeprecationWarning,
-        )
-
-        proxy_config = None
-        if proxies:
-            if isinstance(proxies, ProxyConfig):
-                proxy_config = proxies
-            else:
-                proxy_config = GenericProxyConfig(
-                    http_url=proxies.get("http"), https_url=proxies.get("https")
-                )
-
-        ytt_api = YouTubeTranscriptApi(
-            proxy_config=proxy_config,
-        )
-        return ytt_api.list(video_id)
-
-    @classmethod
-    def get_transcripts(
-        cls,
-        video_ids,
-        languages=("en",),
-        continue_after_error=False,
-        proxies=None,
-        preserve_formatting=False,
-    ):
-        """
-        DEPRECATED: use the `fetch` method instead!
-
-        Retrieves the transcripts for a list of videos.
-
-        :param video_ids: a list of youtube video ids
-        :type video_ids: list[str]
-        :param languages: 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 transcript (en) if it fails to
-        do so.
-        :type languages: list[str]
-        :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
-        :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
-        :param preserve_formatting: whether to keep select HTML text formatting
-        :type preserve_formatting: bool
-        :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]}):
-        """
-        warnings.warn(
-            "`get_transcripts` is deprecated and will be removed in a future version. "
-            "Use the `fetch` method instead!",
-            DeprecationWarning,
-        )
-
-        assert isinstance(video_ids, list), "`video_ids` must be a list of strings"
-
-        data = {}
-        unretrievable_videos = []
-
-        for video_id in video_ids:
-            try:
-                data[video_id] = cls.get_transcript(
-                    video_id, languages, proxies, preserve_formatting
-                )
-            except Exception as exception:
-                if not continue_after_error:
-                    raise exception
-
-                unretrievable_videos.append(video_id)
-
-        return data, unretrievable_videos
-
-    @classmethod
-    def get_transcript(
-        cls,
-        video_id,
-        languages=("en",),
-        proxies=None,
-        preserve_formatting=False,
-    ):
-        """
-        DEPRECATED: use the `fetch` method instead!
-
-        Retrieves the transcript for a single video. This is just a shortcut for calling::
-
-            YouTubeTranscriptApi.list_transcripts(video_id, proxies).find_transcript(languages).fetch()
-
-        :param video_id: the youtube video id
-        :type video_id: str
-        :param languages: 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 transcript (en) if it fails to
-        do so.
-        :type languages: list[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
-        :param preserve_formatting: whether to keep select HTML text formatting
-        :type preserve_formatting: bool
-        :return: a list of dictionaries containing the 'text', 'start' and 'duration' keys
-        :rtype [{'text': str, 'start': float, 'end': float}]:
-        """
-        warnings.warn(
-            "`get_transcript` is deprecated and will be removed in a future version. "
-            "Use the `fetch` method instead!",
-            DeprecationWarning,
-        )
-
-        assert isinstance(video_id, str), "`video_id` must be a string"
-        return (
-            cls.list_transcripts(video_id, proxies)
-            .find_transcript(languages)
-            .fetch(preserve_formatting=preserve_formatting)
-            .to_raw_data()
-        )

youtube_transcript_api/_errors.py

@@ -123,8 +123,8 @@ class VideoUnavailable(CouldNotRetrieveTranscript):
 class InvalidVideoId(CouldNotRetrieveTranscript):
     CAUSE_MESSAGE = (
         "You provided an invalid video id. Make sure you are using the video id and NOT the url!\n\n"
-        'Do NOT run: `YouTubeTranscriptApi.get_transcript("https://www.youtube.com/watch?v=1234")`\n'
-        'Instead run: `YouTubeTranscriptApi.get_transcript("1234")`'
+        'Do NOT run: `YouTubeTranscriptApi().fetch("https://www.youtube.com/watch?v=1234")`\n'
+        'Instead run: `YouTubeTranscriptApi().fetch("1234")`'
     )