jdepoix / youtube-transcript-api / 95

pending completion

Build # 95

Build Type

Pull #63

travis-ci

Committed by

web-flow

Commit Message

<a href="https://github.com/jdepoix/youtube-transcript-api/commit/<a class=hub.com/jdepoix/youtube-transcript-api/commit/2fe0e4f9766460cf6af4c3760548ab7810648675">2fe0e4f97<a href="https://github.com/jdepoix/youtube-transcript-api/commit/2fe0e4f9766460cf6af4c3760548ab7810648675">">Merge </a><a class="double-link" href="https://github.com/jdepoix/youtube-transcript-api/commit/<a class="double-link" href="https://github.com/jdepoix/youtube-transcript-api/commit/216abbe0233faef79f6b4eaee5e15d902529de4c">216abbe02</a>">216abbe02</a><a href="https://github.com/jdepoix/youtube-transcript-api/commit/2fe0e4f9766460cf6af4c3760548ab7810648675"> into dec09fa48">dec09fa48</a>

Pull Request Pull Request #63: Feature/issue 23 Adding transcript formatters

Run Details

133 of 133 new or added lines in 6 files covered. (100.0%)

589 of 592 relevant lines covered (99.49%)

2.98 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

93.33

/youtube_transcript_api/_api.py

import requests
try:
    import http.cookiejar as cookiejar
    CookieLoadError = (FileNotFoundError, cookiejar.LoadError)
except ImportError:
    import cookielib as cookiejar
    CookieLoadError = IOError

from ._transcripts import TranscriptListFetcher

from ._errors import (
    CookiePathInvalid,
    CookiesInvalid
)
from .formatters import formats


class YouTubeTranscriptApi():
    @classmethod
    def list_transcripts(cls, video_id, proxies=None, cookies=None):
        """
        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.get('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
        :param cookies: a string of the path to a text file containing youtube authorization cookies
        :type cookies: str
        :return: the list of available transcripts
        :rtype TranscriptList:
        """
        with requests.Session() as http_client:
            if cookies:
                http_client.cookies = cls._load_cookies(cookies, video_id)
            http_client.proxies = proxies if proxies else {}
            return TranscriptListFetcher(http_client).fetch(video_id)

    @classmethod
    def get_transcripts(cls, video_ids, languages=('en',),
            continue_after_error=False, proxies=None, cookies=None, format=None):
        """
        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 cookies: a string of the path to a text file containing youtube authorization cookies
        :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]}):
        """
        data = {}
        unretrievable_videos = []

        for video_id in video_ids:
            try:
                data[video_id] = cls.get_transcript(video_id, languages,
                                    proxies, cookies, format=format)
            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,
            cookies=None, format=None):
        """
        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 cookies: a string of the path to a text file containing youtube authorization cookies
        :type cookies: str
        :return: a list of dictionaries containing the 'text', 'start' and 'duration' keys
        :rtype [{'text': str, 'start': float, 'end': float}]:
        """
        Formatter = formats.get_formatter(format)
        transcript = cls.list_transcripts(
            video_id,proxies, cookies).find_transcript(languages).fetch()
        return Formatter.format(transcript)

    @classmethod
    def _load_cookies(cls, cookies, video_id):
        cookie_jar = {}
        try:
            cookie_jar = cookiejar.MozillaCookieJar()
            cookie_jar.load(cookies)
        except CookieLoadError:
            raise CookiePathInvalid(video_id)
        if not cookie_jar:
            raise CookiesInvalid(video_id)
        return cookie_jar 

1	import requests	3✔
2	try:	3✔
3	import http.cookiejar as cookiejar	3✔
4	CookieLoadError = (FileNotFoundError, cookiejar.LoadError)	3✔
5	except ImportError:	×
6	import cookielib as cookiejar	×
7	CookieLoadError = IOError	×
8
9	from ._transcripts import TranscriptListFetcher	3✔
10
11	from ._errors import (	3✔
12	CookiePathInvalid,
13	CookiesInvalid
14	)
15	from .formatters import formats	3✔
16
17
18	class YouTubeTranscriptApi():	3✔
19	@classmethod	3✔
20	def list_transcripts(cls, video_id, proxies=None, cookies=None):	3✔
21	"""
22	Retrieves the list of transcripts which are available for a given video. It returns a `TranscriptList` object
23	which is iterable and provides methods to filter the list of transcripts for specific languages. While iterating
24	over the `TranscriptList` the individual transcripts are represented by `Transcript` objects, which provide
25	metadata and can either be fetched by calling `transcript.fetch()` or translated by calling
26	`transcript.translate('en')`. Example::
27
28	# retrieve the available transcripts
29	transcript_list = YouTubeTranscriptApi.get('video_id')
30
31	# iterate over all available transcripts
32	for transcript in transcript_list:
33	# the Transcript object provides metadata properties
34	print(
35	transcript.video_id,
36	transcript.language,
37	transcript.language_code,
38	# whether it has been manually created or generated by YouTube
39	transcript.is_generated,
40	# a list of languages the transcript can be translated to
41	transcript.translation_languages,
42	)
43
44	# fetch the actual transcript data
45	print(transcript.fetch())
46
47	# translating the transcript will return another transcript object
48	print(transcript.translate('en').fetch())
49
50	# you can also directly filter for the language you are looking for, using the transcript list
51	transcript = transcript_list.find_transcript(['de', 'en'])
52
53	# or just filter for manually created transcripts
54	transcript = transcript_list.find_manually_created_transcript(['de', 'en'])
55
56	# or automatically generated ones
57	transcript = transcript_list.find_generated_transcript(['de', 'en'])
58
59	:param video_id: the youtube video id
60	:type video_id: str
61	:param proxies: a dictionary mapping of http and https proxies to be used for the network requests
62	:type proxies: {'http': str, 'https': str} - http://docs.python-requests.org/en/master/user/advanced/#proxies
63	:param cookies: a string of the path to a text file containing youtube authorization cookies
64	:type cookies: str
65	:return: the list of available transcripts
66	:rtype TranscriptList:
67	"""
68	with requests.Session() as http_client:	3✔
69	if cookies:	3✔
70	http_client.cookies = cls._load_cookies(cookies, video_id)	3✔
71	http_client.proxies = proxies if proxies else {}	3✔
72	return TranscriptListFetcher(http_client).fetch(video_id)	3✔
73
74	@classmethod	3✔
75	def get_transcripts(cls, video_ids, languages=('en',),	3✔
76	continue_after_error=False, proxies=None, cookies=None, format=None):
77	"""
78	Retrieves the transcripts for a list of videos.
79
80	:param video_ids: a list of youtube video ids
81	:type video_ids: list[str]
82	:param languages: A list of language codes in a descending priority. For example, if this is set to ['de', 'en']
83	it will first try to fetch the german transcript (de) and then fetch the english transcript (en) if it fails to
84	do so.
85	:type languages: list[str]
86	:param continue_after_error: if this is set the execution won't be stopped, if an error occurs while retrieving
87	one of the video transcripts
88	:type continue_after_error: bool
89	:param proxies: a dictionary mapping of http and https proxies to be used for the network requests
90	:type proxies: {'http': str, 'https': str} - http://docs.python-requests.org/en/master/user/advanced/#proxies
91	:param cookies: a string of the path to a text file containing youtube authorization cookies
92	:type cookies: str
93	:return: a tuple containing a dictionary mapping video ids onto their corresponding transcripts, and a list of
94	video ids, which could not be retrieved
95	:rtype ({str: [{'text': str, 'start': float, 'end': float}]}, [str]}):
96	"""
97	data = {}	3✔
98	unretrievable_videos = []	3✔
99
100	for video_id in video_ids:	3✔
101	try:	3✔
102	data[video_id] = cls.get_transcript(video_id, languages,	3✔
103	proxies, cookies, format=format)
104	except Exception as exception:	3✔
105	if not continue_after_error:	3✔
106	raise exception	3✔
107
108	unretrievable_videos.append(video_id)	3✔
109
110	return data, unretrievable_videos	3✔
111
112	@classmethod	3✔
113	def get_transcript(cls, video_id, languages=('en',), proxies=None,	3✔
114	cookies=None, format=None):
115	"""
116	Retrieves the transcript for a single video. This is just a shortcut for calling::
117
118	YouTubeTranscriptApi.list_transcripts(video_id, proxies).find_transcript(languages).fetch()
119
120	:param video_id: the youtube video id
121	:type video_id: str
122	:param languages: A list of language codes in a descending priority. For example, if this is set to ['de', 'en']
123	it will first try to fetch the german transcript (de) and then fetch the english transcript (en) if it fails to
124	do so.
125	:type languages: list[str]
126	:param proxies: a dictionary mapping of http and https proxies to be used for the network requests
127	:type proxies: {'http': str, 'https': str} - http://docs.python-requests.org/en/master/user/advanced/#proxies
128	:param cookies: a string of the path to a text file containing youtube authorization cookies
129	:type cookies: str
130	:return: a list of dictionaries containing the 'text', 'start' and 'duration' keys
131	:rtype [{'text': str, 'start': float, 'end': float}]:
132	"""
133	Formatter = formats.get_formatter(format)	3✔
134	transcript = cls.list_transcripts(	3✔
135	video_id,proxies, cookies).find_transcript(languages).fetch()
136	return Formatter.format(transcript)	3✔
137
138	@classmethod	3✔
139	def _load_cookies(cls, cookies, video_id):
140	cookie_jar = {}	3✔
141	try:	3✔
142	cookie_jar = cookiejar.MozillaCookieJar()	3✔
143	cookie_jar.load(cookies)	3✔
144	except CookieLoadError:	3✔
145	raise CookiePathInvalid(video_id)	3✔
146	if not cookie_jar:	3✔
147	raise CookiesInvalid(video_id)	3✔
148	return cookie_jar	3✔

jdepoix / youtube-transcript-api / 95

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous