youtube-transcript-rb 0.2.0 → 0.2.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.rubocop.yml +9 -0
- data/.rubocop_todo.yml +166 -0
- data/README.md +9 -9
- data/lib/youtube-transcript-rb.rb +4 -0
- data/lib/youtube_rb/formatters.rb +263 -0
- data/lib/youtube_rb/transcript/api.rb +7 -11
- data/lib/youtube_rb/transcript/errors.rb +3 -3
- data/lib/youtube_rb/transcript/transcript.rb +2 -2
- data/lib/youtube_rb/transcript/transcript_list.rb +3 -3
- data/lib/youtube_rb/transcript/transcript_list_fetcher.rb +16 -19
- data/lib/youtube_rb/transcript.rb +0 -2
- data/lib/youtube_rb/{transcript/version.rb → version.rb} +1 -3
- data/sig/youtube_rb/transcript.rbs +0 -2
- data/spec/api_spec.rb +8 -8
- data/spec/errors_spec.rb +2 -2
- data/spec/formatters_spec.rb +34 -35
- data/spec/integration_spec.rb +14 -23
- data/spec/spec_helper.rb +51 -51
- data/spec/transcript_list_fetcher_spec.rb +11 -6
- data/spec/transcript_list_spec.rb +15 -18
- data/spec/transcript_spec.rb +9 -10
- metadata +8 -4
- data/lib/youtube_rb/transcript/formatters.rb +0 -267
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 60cad31d1d80bf186d231cf3eed48cd1599f41000a3de1a185e24480421ea0dd
|
|
4
|
+
data.tar.gz: cc370e6e42208f18a0ed456800de0f2e8b470754c63908149171c5558e15500a
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 42f16cf9961a05528f4289886ebb08b2b06cb9060fbecfc6b41ffd4267920ef0d2123afec048c231a4f507bd44a8f1df9e383addbb3390e4e9076d9617bb22ba
|
|
7
|
+
data.tar.gz: b529273917d15dca2f50d28b5c7ea6f04d359c111346bd0ef4547db86b7a016dae83fdefce80b75784b43849931c6595c67833d4977e8b816176bca027883491
|
data/.rubocop.yml
ADDED
data/.rubocop_todo.yml
ADDED
|
@@ -0,0 +1,166 @@
|
|
|
1
|
+
# This configuration was generated by
|
|
2
|
+
# `rubocop --auto-gen-config`
|
|
3
|
+
# on 2026-01-09 13:39:24 UTC using RuboCop version 1.82.1.
|
|
4
|
+
# The point is for the user to remove these configuration records
|
|
5
|
+
# one by one as the offenses are removed from the code base.
|
|
6
|
+
# Note that changes in the inspected code, or installation of new
|
|
7
|
+
# versions of RuboCop, may require this file to be generated again.
|
|
8
|
+
|
|
9
|
+
# Offense count: 3
|
|
10
|
+
# This cop supports safe autocorrection (--autocorrect).
|
|
11
|
+
# Configuration parameters: AllowUnusedKeywordArguments, IgnoreEmptyMethods, IgnoreNotImplementedMethods, NotImplementedExceptions.
|
|
12
|
+
# NotImplementedExceptions: NotImplementedError
|
|
13
|
+
Lint/UnusedMethodArgument:
|
|
14
|
+
Exclude:
|
|
15
|
+
- 'lib/youtube_rb/formatters.rb'
|
|
16
|
+
|
|
17
|
+
# Offense count: 3
|
|
18
|
+
# Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes.
|
|
19
|
+
Metrics/AbcSize:
|
|
20
|
+
Max: 25
|
|
21
|
+
|
|
22
|
+
# Offense count: 1
|
|
23
|
+
# Configuration parameters: CountComments, CountAsOne.
|
|
24
|
+
Metrics/ClassLength:
|
|
25
|
+
Max: 103
|
|
26
|
+
|
|
27
|
+
# Offense count: 2
|
|
28
|
+
# Configuration parameters: AllowedMethods, AllowedPatterns.
|
|
29
|
+
Metrics/CyclomaticComplexity:
|
|
30
|
+
Max: 14
|
|
31
|
+
|
|
32
|
+
# Offense count: 7
|
|
33
|
+
# Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
|
|
34
|
+
Metrics/MethodLength:
|
|
35
|
+
Max: 29
|
|
36
|
+
|
|
37
|
+
# Offense count: 1
|
|
38
|
+
# Configuration parameters: CountKeywordArgs, MaxOptionalParameters.
|
|
39
|
+
Metrics/ParameterLists:
|
|
40
|
+
Max: 7
|
|
41
|
+
|
|
42
|
+
# Offense count: 2
|
|
43
|
+
# Configuration parameters: AllowedMethods, AllowedPatterns.
|
|
44
|
+
Metrics/PerceivedComplexity:
|
|
45
|
+
Max: 15
|
|
46
|
+
|
|
47
|
+
# Offense count: 1
|
|
48
|
+
# Configuration parameters: ExpectMatchingDefinition, CheckDefinitionPathHierarchy, CheckDefinitionPathHierarchyRoots, Regex, IgnoreExecutableScripts, AllowedAcronyms.
|
|
49
|
+
# CheckDefinitionPathHierarchyRoots: lib, spec, test, src
|
|
50
|
+
# AllowedAcronyms: CLI, DSL, ACL, API, ASCII, CPU, CSS, DNS, EOF, GUID, HTML, HTTP, HTTPS, ID, IP, JSON, LHS, QPS, RAM, RHS, RPC, SLA, SMTP, SQL, SSH, TCP, TLS, TTL, UDP, UI, UID, UUID, URI, URL, UTF8, VM, XML, XMPP, XSRF, XSS
|
|
51
|
+
Naming/FileName:
|
|
52
|
+
Exclude:
|
|
53
|
+
- 'Rakefile.rb'
|
|
54
|
+
- 'lib/youtube-transcript-rb.rb'
|
|
55
|
+
|
|
56
|
+
# Offense count: 3
|
|
57
|
+
# Configuration parameters: MinNameLength, AllowNamesEndingInNumbers, AllowedNames, ForbiddenNames.
|
|
58
|
+
# AllowedNames: as, at, by, cc, db, id, if, in, io, ip, of, on, os, pp, to
|
|
59
|
+
Naming/MethodParameterName:
|
|
60
|
+
Exclude:
|
|
61
|
+
- 'lib/youtube_rb/formatters.rb'
|
|
62
|
+
|
|
63
|
+
# Offense count: 2
|
|
64
|
+
RSpec/BeforeAfterAll:
|
|
65
|
+
Exclude:
|
|
66
|
+
- '**/spec/spec_helper.rb'
|
|
67
|
+
- '**/spec/rails_helper.rb'
|
|
68
|
+
- '**/spec/support/**/*.rb'
|
|
69
|
+
- 'spec/integration_spec.rb'
|
|
70
|
+
|
|
71
|
+
# Offense count: 2
|
|
72
|
+
# Configuration parameters: IgnoredMetadata.
|
|
73
|
+
RSpec/DescribeClass:
|
|
74
|
+
Exclude:
|
|
75
|
+
- '**/spec/features/**/*'
|
|
76
|
+
- '**/spec/requests/**/*'
|
|
77
|
+
- '**/spec/routing/**/*'
|
|
78
|
+
- '**/spec/system/**/*'
|
|
79
|
+
- '**/spec/views/**/*'
|
|
80
|
+
- 'spec/integration_spec.rb'
|
|
81
|
+
- 'spec/settings_spec.rb'
|
|
82
|
+
|
|
83
|
+
# Offense count: 30
|
|
84
|
+
# Configuration parameters: CountAsOne.
|
|
85
|
+
RSpec/ExampleLength:
|
|
86
|
+
Max: 22
|
|
87
|
+
|
|
88
|
+
# Offense count: 4
|
|
89
|
+
# This cop supports safe autocorrection (--autocorrect).
|
|
90
|
+
RSpec/ExpectActual:
|
|
91
|
+
Exclude:
|
|
92
|
+
- '**/spec/routing/**/*'
|
|
93
|
+
- 'spec/integration_spec.rb'
|
|
94
|
+
|
|
95
|
+
# Offense count: 2
|
|
96
|
+
# Configuration parameters: Max, AllowedIdentifiers, AllowedPatterns.
|
|
97
|
+
RSpec/IndexedLet:
|
|
98
|
+
Exclude:
|
|
99
|
+
- 'spec/transcript_spec.rb'
|
|
100
|
+
|
|
101
|
+
# Offense count: 91
|
|
102
|
+
RSpec/MultipleExpectations:
|
|
103
|
+
Max: 7
|
|
104
|
+
|
|
105
|
+
# Offense count: 44
|
|
106
|
+
# Configuration parameters: AllowSubject.
|
|
107
|
+
RSpec/MultipleMemoizedHelpers:
|
|
108
|
+
Max: 11
|
|
109
|
+
|
|
110
|
+
# Offense count: 3
|
|
111
|
+
# Configuration parameters: AllowedGroups.
|
|
112
|
+
RSpec/NestedGroups:
|
|
113
|
+
Max: 4
|
|
114
|
+
|
|
115
|
+
# Offense count: 7
|
|
116
|
+
# Configuration parameters: CustomTransform, IgnoreMethods, IgnoreMetadata, InflectorPath, EnforcedInflector.
|
|
117
|
+
# SupportedInflectors: default, active_support
|
|
118
|
+
RSpec/SpecFilePathFormat:
|
|
119
|
+
Exclude:
|
|
120
|
+
- '**/spec/routing/**/*'
|
|
121
|
+
- 'spec/api_spec.rb'
|
|
122
|
+
- 'spec/errors_spec.rb'
|
|
123
|
+
- 'spec/formatters_spec.rb'
|
|
124
|
+
- 'spec/transcript_list_fetcher_spec.rb'
|
|
125
|
+
- 'spec/transcript_list_spec.rb'
|
|
126
|
+
- 'spec/transcript_parser_spec.rb'
|
|
127
|
+
- 'spec/transcript_spec.rb'
|
|
128
|
+
|
|
129
|
+
# Offense count: 10
|
|
130
|
+
# Configuration parameters: IgnoreNameless, IgnoreSymbolicNames.
|
|
131
|
+
RSpec/VerifiedDoubles:
|
|
132
|
+
Exclude:
|
|
133
|
+
- 'spec/api_spec.rb'
|
|
134
|
+
- 'spec/errors_spec.rb'
|
|
135
|
+
- 'spec/transcript_list_fetcher_spec.rb'
|
|
136
|
+
- 'spec/transcript_spec.rb'
|
|
137
|
+
|
|
138
|
+
# Offense count: 1
|
|
139
|
+
# Configuration parameters: AllowedConstants.
|
|
140
|
+
Style/Documentation:
|
|
141
|
+
Exclude:
|
|
142
|
+
- 'spec/**/*'
|
|
143
|
+
- 'test/**/*'
|
|
144
|
+
- 'lib/youtube_rb/transcript.rb'
|
|
145
|
+
|
|
146
|
+
# Offense count: 8
|
|
147
|
+
# This cop supports safe autocorrection (--autocorrect).
|
|
148
|
+
# Configuration parameters: EnforcedStyle, MaxUnannotatedPlaceholdersAllowed, Mode, AllowedMethods, AllowedPatterns.
|
|
149
|
+
# SupportedStyles: annotated, template, unannotated
|
|
150
|
+
Style/FormatStringToken:
|
|
151
|
+
Exclude:
|
|
152
|
+
- 'lib/youtube_rb/formatters.rb'
|
|
153
|
+
|
|
154
|
+
# Offense count: 1168
|
|
155
|
+
# This cop supports safe autocorrection (--autocorrect).
|
|
156
|
+
# Configuration parameters: EnforcedStyle, ConsistentQuotesInMultiline.
|
|
157
|
+
# SupportedStyles: single_quotes, double_quotes
|
|
158
|
+
Style/StringLiterals:
|
|
159
|
+
Enabled: false
|
|
160
|
+
|
|
161
|
+
# Offense count: 6
|
|
162
|
+
# This cop supports safe autocorrection (--autocorrect).
|
|
163
|
+
# Configuration parameters: AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, AllowRBSInlineAnnotation, AllowCopDirectives, AllowedPatterns, SplitStrings.
|
|
164
|
+
# URISchemes: http, https
|
|
165
|
+
Layout/LineLength:
|
|
166
|
+
Max: 142
|
data/README.md
CHANGED
|
@@ -300,11 +300,11 @@ Here is how to import from the `Formatters` module:
|
|
|
300
300
|
require 'youtube_rb/transcript'
|
|
301
301
|
|
|
302
302
|
# Some provided formatter classes, each outputs a different string format.
|
|
303
|
-
YoutubeRb::
|
|
304
|
-
YoutubeRb::
|
|
305
|
-
YoutubeRb::
|
|
306
|
-
YoutubeRb::
|
|
307
|
-
YoutubeRb::
|
|
303
|
+
YoutubeRb::Formatters::JSONFormatter
|
|
304
|
+
YoutubeRb::Formatters::TextFormatter
|
|
305
|
+
YoutubeRb::Formatters::PrettyPrintFormatter
|
|
306
|
+
YoutubeRb::Formatters::WebVTTFormatter
|
|
307
|
+
YoutubeRb::Formatters::SRTFormatter
|
|
308
308
|
```
|
|
309
309
|
|
|
310
310
|
### Formatter Example
|
|
@@ -317,7 +317,7 @@ require 'youtube_rb/transcript'
|
|
|
317
317
|
api = YoutubeRb::Transcript::YouTubeTranscriptApi.new
|
|
318
318
|
transcript = api.fetch(video_id)
|
|
319
319
|
|
|
320
|
-
formatter = YoutubeRb::
|
|
320
|
+
formatter = YoutubeRb::Formatters::JSONFormatter.new
|
|
321
321
|
|
|
322
322
|
# .format_transcript(transcript) turns the transcript into a JSON string.
|
|
323
323
|
json_formatted = formatter.format_transcript(transcript)
|
|
@@ -334,7 +334,7 @@ Since `JSONFormatter` leverages `JSON.generate` you can also forward keyword arg
|
|
|
334
334
|
`.format_transcript(transcript)` such as making your file output prettier:
|
|
335
335
|
|
|
336
336
|
```ruby
|
|
337
|
-
json_formatted = YoutubeRb::
|
|
337
|
+
json_formatted = YoutubeRb::Formatters::JSONFormatter.new.format_transcript(
|
|
338
338
|
transcript,
|
|
339
339
|
indent: ' ',
|
|
340
340
|
space: ' '
|
|
@@ -348,7 +348,7 @@ You can also use the `FormatterLoader` to dynamically load formatters by name:
|
|
|
348
348
|
```ruby
|
|
349
349
|
require 'youtube_rb/transcript'
|
|
350
350
|
|
|
351
|
-
loader = YoutubeRb::
|
|
351
|
+
loader = YoutubeRb::Formatters::FormatterLoader.new
|
|
352
352
|
|
|
353
353
|
# Load by type name: "json", "pretty", "text", "webvtt", "srt"
|
|
354
354
|
formatter = loader.load("json")
|
|
@@ -364,7 +364,7 @@ You can implement your own formatter class. Just inherit from the `Formatter` ba
|
|
|
364
364
|
`format_transcript` and `format_transcripts` methods which should ultimately return a string:
|
|
365
365
|
|
|
366
366
|
```ruby
|
|
367
|
-
class MyCustomFormatter < YoutubeRb::
|
|
367
|
+
class MyCustomFormatter < YoutubeRb::Formatters::Formatter
|
|
368
368
|
def format_transcript(transcript, **options)
|
|
369
369
|
# Do your custom work in here, but return a string.
|
|
370
370
|
'your processed output data as a string.'
|
|
@@ -0,0 +1,263 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
require "json"
|
|
4
|
+
|
|
5
|
+
module YoutubeRb
|
|
6
|
+
# Module containing all transcript formatters
|
|
7
|
+
module Formatters
|
|
8
|
+
# Base formatter class. All formatters should inherit from this class
|
|
9
|
+
# and implement their own format_transcript and format_transcripts methods.
|
|
10
|
+
class Formatter
|
|
11
|
+
# Format a single transcript
|
|
12
|
+
#
|
|
13
|
+
# @param transcript [FetchedTranscript] The transcript to format
|
|
14
|
+
# @param options [Hash] Additional formatting options
|
|
15
|
+
# @return [String] The formatted transcript
|
|
16
|
+
def format_transcript(transcript, **options)
|
|
17
|
+
raise NotImplementedError, "Subclass must implement #format_transcript"
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
# Format multiple transcripts
|
|
21
|
+
#
|
|
22
|
+
# @param transcripts [Array<FetchedTranscript>] The transcripts to format
|
|
23
|
+
# @param options [Hash] Additional formatting options
|
|
24
|
+
# @return [String] The formatted transcripts
|
|
25
|
+
def format_transcripts(transcripts, **options)
|
|
26
|
+
raise NotImplementedError, "Subclass must implement #format_transcripts"
|
|
27
|
+
end
|
|
28
|
+
end
|
|
29
|
+
|
|
30
|
+
# Formats transcript as pretty-printed Ruby data structures
|
|
31
|
+
class PrettyPrintFormatter < Formatter
|
|
32
|
+
# Format a single transcript as pretty-printed output
|
|
33
|
+
#
|
|
34
|
+
# @param transcript [FetchedTranscript] The transcript to format
|
|
35
|
+
# @param options [Hash] Options passed to PP.pp
|
|
36
|
+
# @return [String] Pretty-printed transcript data
|
|
37
|
+
def format_transcript(transcript, **options)
|
|
38
|
+
require "pp"
|
|
39
|
+
PP.pp(transcript.to_raw_data, +"", options[:width] || 79)
|
|
40
|
+
end
|
|
41
|
+
|
|
42
|
+
# Format multiple transcripts as pretty-printed output
|
|
43
|
+
#
|
|
44
|
+
# @param transcripts [Array<FetchedTranscript>] The transcripts to format
|
|
45
|
+
# @param options [Hash] Options passed to PP.pp
|
|
46
|
+
# @return [String] Pretty-printed transcripts data
|
|
47
|
+
def format_transcripts(transcripts, **options)
|
|
48
|
+
require "pp"
|
|
49
|
+
data = transcripts.map(&:to_raw_data)
|
|
50
|
+
PP.pp(data, +"", options[:width] || 79)
|
|
51
|
+
end
|
|
52
|
+
end
|
|
53
|
+
|
|
54
|
+
# Formats transcript as JSON
|
|
55
|
+
class JSONFormatter < Formatter
|
|
56
|
+
# Format a single transcript as JSON
|
|
57
|
+
#
|
|
58
|
+
# @param transcript [FetchedTranscript] The transcript to format
|
|
59
|
+
# @param options [Hash] Options passed to JSON.generate (e.g., :indent, :space)
|
|
60
|
+
# @return [String] JSON representation of the transcript
|
|
61
|
+
def format_transcript(transcript, **options)
|
|
62
|
+
JSON.generate(transcript.to_raw_data, options)
|
|
63
|
+
end
|
|
64
|
+
|
|
65
|
+
# Format multiple transcripts as JSON array
|
|
66
|
+
#
|
|
67
|
+
# @param transcripts [Array<FetchedTranscript>] The transcripts to format
|
|
68
|
+
# @param options [Hash] Options passed to JSON.generate
|
|
69
|
+
# @return [String] JSON array representation of the transcripts
|
|
70
|
+
def format_transcripts(transcripts, **options)
|
|
71
|
+
data = transcripts.map(&:to_raw_data)
|
|
72
|
+
JSON.generate(data, options)
|
|
73
|
+
end
|
|
74
|
+
end
|
|
75
|
+
|
|
76
|
+
# Formats transcript as plain text (text only, no timestamps)
|
|
77
|
+
class TextFormatter < Formatter
|
|
78
|
+
# Format a single transcript as plain text
|
|
79
|
+
#
|
|
80
|
+
# @param transcript [FetchedTranscript] The transcript to format
|
|
81
|
+
# @param options [Hash] Unused options
|
|
82
|
+
# @return [String] Plain text with each line separated by newlines
|
|
83
|
+
def format_transcript(transcript, **options)
|
|
84
|
+
transcript.map(&:text).join("\n")
|
|
85
|
+
end
|
|
86
|
+
|
|
87
|
+
# Format multiple transcripts as plain text
|
|
88
|
+
#
|
|
89
|
+
# @param transcripts [Array<FetchedTranscript>] The transcripts to format
|
|
90
|
+
# @param options [Hash] Unused options
|
|
91
|
+
# @return [String] Plain text with transcripts separated by triple newlines
|
|
92
|
+
def format_transcripts(transcripts, **options)
|
|
93
|
+
transcripts.map { |t| format_transcript(t, **options) }.join("\n\n\n")
|
|
94
|
+
end
|
|
95
|
+
end
|
|
96
|
+
|
|
97
|
+
# Base class for timestamp-based formatters (SRT, WebVTT)
|
|
98
|
+
class TextBasedFormatter < TextFormatter
|
|
99
|
+
# Format a single transcript with timestamps
|
|
100
|
+
#
|
|
101
|
+
# @param transcript [FetchedTranscript] The transcript to format
|
|
102
|
+
# @param options [Hash] Unused options
|
|
103
|
+
# @return [String] Formatted transcript with timestamps
|
|
104
|
+
def format_transcript(transcript, **options)
|
|
105
|
+
lines = []
|
|
106
|
+
snippets = transcript.to_a
|
|
107
|
+
|
|
108
|
+
snippets.each_with_index do |snippet, i|
|
|
109
|
+
end_time = snippet.start + snippet.duration
|
|
110
|
+
|
|
111
|
+
# Use next snippet's start time if it starts before current end time
|
|
112
|
+
end_time = snippets[i + 1].start if i < snippets.length - 1 && snippets[i + 1].start < end_time
|
|
113
|
+
|
|
114
|
+
time_text = "#{seconds_to_timestamp(snippet.start)} --> #{seconds_to_timestamp(end_time)}"
|
|
115
|
+
lines << format_transcript_helper(i, time_text, snippet)
|
|
116
|
+
end
|
|
117
|
+
|
|
118
|
+
format_transcript_header(lines)
|
|
119
|
+
end
|
|
120
|
+
|
|
121
|
+
protected
|
|
122
|
+
|
|
123
|
+
# Format a timestamp from components
|
|
124
|
+
#
|
|
125
|
+
# @param hours [Integer] Hours component
|
|
126
|
+
# @param mins [Integer] Minutes component
|
|
127
|
+
# @param secs [Integer] Seconds component
|
|
128
|
+
# @param ms [Integer] Milliseconds component
|
|
129
|
+
# @return [String] Formatted timestamp
|
|
130
|
+
def format_timestamp(hours, mins, secs, ms)
|
|
131
|
+
raise NotImplementedError, "Subclass must implement #format_timestamp"
|
|
132
|
+
end
|
|
133
|
+
|
|
134
|
+
# Format the transcript header/wrapper
|
|
135
|
+
#
|
|
136
|
+
# @param lines [Array<String>] The formatted lines
|
|
137
|
+
# @return [String] The complete formatted transcript
|
|
138
|
+
def format_transcript_header(lines)
|
|
139
|
+
raise NotImplementedError, "Subclass must implement #format_transcript_header"
|
|
140
|
+
end
|
|
141
|
+
|
|
142
|
+
# Format a single transcript entry
|
|
143
|
+
#
|
|
144
|
+
# @param index [Integer] The entry index (0-based)
|
|
145
|
+
# @param time_text [String] The formatted time range
|
|
146
|
+
# @param snippet [TranscriptSnippet] The snippet to format
|
|
147
|
+
# @return [String] The formatted entry
|
|
148
|
+
def format_transcript_helper(index, time_text, snippet)
|
|
149
|
+
raise NotImplementedError, "Subclass must implement #format_transcript_helper"
|
|
150
|
+
end
|
|
151
|
+
|
|
152
|
+
private
|
|
153
|
+
|
|
154
|
+
# Convert seconds to timestamp string
|
|
155
|
+
#
|
|
156
|
+
# @param time [Float] Time in seconds
|
|
157
|
+
# @return [String] Formatted timestamp
|
|
158
|
+
def seconds_to_timestamp(time)
|
|
159
|
+
time = time.to_f
|
|
160
|
+
hours, remainder = time.divmod(3600)
|
|
161
|
+
mins, secs_float = remainder.divmod(60)
|
|
162
|
+
secs = secs_float.to_i
|
|
163
|
+
ms = ((time - time.to_i) * 1000).round
|
|
164
|
+
|
|
165
|
+
format_timestamp(hours.to_i, mins.to_i, secs, ms)
|
|
166
|
+
end
|
|
167
|
+
end
|
|
168
|
+
|
|
169
|
+
# Formats transcript as SRT (SubRip) subtitle format
|
|
170
|
+
#
|
|
171
|
+
# @example SRT format
|
|
172
|
+
# 1
|
|
173
|
+
# 00:00:00,000 --> 00:00:02,500
|
|
174
|
+
# Hello world
|
|
175
|
+
#
|
|
176
|
+
# 2
|
|
177
|
+
# 00:00:02,500 --> 00:00:05,000
|
|
178
|
+
# This is a test
|
|
179
|
+
#
|
|
180
|
+
class SRTFormatter < TextBasedFormatter
|
|
181
|
+
protected
|
|
182
|
+
|
|
183
|
+
def format_timestamp(hours, mins, secs, ms)
|
|
184
|
+
format("%02d:%02d:%02d,%03d", hours, mins, secs, ms)
|
|
185
|
+
end
|
|
186
|
+
|
|
187
|
+
def format_transcript_header(lines)
|
|
188
|
+
"#{lines.join("\n\n")}\n"
|
|
189
|
+
end
|
|
190
|
+
|
|
191
|
+
def format_transcript_helper(index, time_text, snippet)
|
|
192
|
+
"#{index + 1}\n#{time_text}\n#{snippet.text}"
|
|
193
|
+
end
|
|
194
|
+
end
|
|
195
|
+
|
|
196
|
+
# Formats transcript as WebVTT (Web Video Text Tracks) format
|
|
197
|
+
#
|
|
198
|
+
# @example WebVTT format
|
|
199
|
+
# WEBVTT
|
|
200
|
+
#
|
|
201
|
+
# 00:00:00.000 --> 00:00:02.500
|
|
202
|
+
# Hello world
|
|
203
|
+
#
|
|
204
|
+
# 00:00:02.500 --> 00:00:05.000
|
|
205
|
+
# This is a test
|
|
206
|
+
#
|
|
207
|
+
class WebVTTFormatter < TextBasedFormatter
|
|
208
|
+
protected
|
|
209
|
+
|
|
210
|
+
def format_timestamp(hours, mins, secs, ms)
|
|
211
|
+
format("%02d:%02d:%02d.%03d", hours, mins, secs, ms)
|
|
212
|
+
end
|
|
213
|
+
|
|
214
|
+
def format_transcript_header(lines)
|
|
215
|
+
"WEBVTT\n\n#{lines.join("\n\n")}\n"
|
|
216
|
+
end
|
|
217
|
+
|
|
218
|
+
def format_transcript_helper(index, time_text, snippet)
|
|
219
|
+
"#{time_text}\n#{snippet.text}"
|
|
220
|
+
end
|
|
221
|
+
end
|
|
222
|
+
|
|
223
|
+
# Utility class to load formatters by type name
|
|
224
|
+
class FormatterLoader
|
|
225
|
+
# Mapping of format names to formatter classes
|
|
226
|
+
TYPES = {
|
|
227
|
+
"json" => JSONFormatter,
|
|
228
|
+
"pretty" => PrettyPrintFormatter,
|
|
229
|
+
"text" => TextFormatter,
|
|
230
|
+
"webvtt" => WebVTTFormatter,
|
|
231
|
+
"srt" => SRTFormatter
|
|
232
|
+
}.freeze
|
|
233
|
+
|
|
234
|
+
# Error raised when an unknown formatter type is requested
|
|
235
|
+
class UnknownFormatterType < StandardError
|
|
236
|
+
def initialize(formatter_type)
|
|
237
|
+
super(
|
|
238
|
+
"The format '#{formatter_type}' is not supported. " \
|
|
239
|
+
"Choose one of the following formats: #{TYPES.keys.join(', ')}"
|
|
240
|
+
)
|
|
241
|
+
end
|
|
242
|
+
end
|
|
243
|
+
|
|
244
|
+
# Load a formatter by type name
|
|
245
|
+
#
|
|
246
|
+
# @param formatter_type [String] The formatter type (json, pretty, text, webvtt, srt)
|
|
247
|
+
# @return [Formatter] An instance of the requested formatter
|
|
248
|
+
# @raise [UnknownFormatterType] If the formatter type is not supported
|
|
249
|
+
#
|
|
250
|
+
# @example
|
|
251
|
+
# loader = FormatterLoader.new
|
|
252
|
+
# formatter = loader.load("json")
|
|
253
|
+
# output = formatter.format_transcript(transcript)
|
|
254
|
+
#
|
|
255
|
+
def load(formatter_type = "pretty")
|
|
256
|
+
formatter_type = formatter_type.to_s
|
|
257
|
+
raise UnknownFormatterType, formatter_type unless TYPES.key?(formatter_type)
|
|
258
|
+
|
|
259
|
+
TYPES[formatter_type].new
|
|
260
|
+
end
|
|
261
|
+
end
|
|
262
|
+
end
|
|
263
|
+
end
|
|
@@ -113,17 +113,13 @@ module YoutubeRb
|
|
|
113
113
|
results = {}
|
|
114
114
|
|
|
115
115
|
video_ids.each do |video_id|
|
|
116
|
-
|
|
117
|
-
|
|
118
|
-
|
|
119
|
-
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
|
|
123
|
-
else
|
|
124
|
-
raise
|
|
125
|
-
end
|
|
126
|
-
end
|
|
116
|
+
transcript = fetch(video_id, languages: languages, preserve_formatting: preserve_formatting)
|
|
117
|
+
results[video_id] = transcript
|
|
118
|
+
yield(video_id, transcript) if block_given?
|
|
119
|
+
rescue CouldNotRetrieveTranscript => e
|
|
120
|
+
raise unless continue_on_error
|
|
121
|
+
|
|
122
|
+
yield(video_id, e) if block_given?
|
|
127
123
|
end
|
|
128
124
|
|
|
129
125
|
results
|
|
@@ -40,7 +40,7 @@ module YoutubeRb
|
|
|
40
40
|
def github_referral
|
|
41
41
|
"\n\nIf you are sure that the described cause is not responsible for this error " \
|
|
42
42
|
"and that a transcript should be retrievable, please create an issue at " \
|
|
43
|
-
"https://github.com/
|
|
43
|
+
"https://github.com/stadia/youtube-transcript-rb/issues. " \
|
|
44
44
|
"Please add which version of youtube_transcript_api you are using " \
|
|
45
45
|
"and provide the information needed to replicate the error. " \
|
|
46
46
|
"Also make sure that there are no open issues which already describe your problem!"
|
|
@@ -131,13 +131,13 @@ module YoutubeRb
|
|
|
131
131
|
"2. (NOT RECOMMENDED) If you authenticate your requests using cookies, you " \
|
|
132
132
|
"will be able to continue doing requests for a while. However, YouTube will " \
|
|
133
133
|
"eventually permanently ban the account that you have used to authenticate " \
|
|
134
|
-
"with! So only do this if you don't mind your account being banned!"
|
|
134
|
+
"with! So only do this if you don't mind your account being banned!".freeze
|
|
135
135
|
end
|
|
136
136
|
|
|
137
137
|
# Raised when YouTube blocks the IP specifically
|
|
138
138
|
class IpBlocked < RequestBlocked
|
|
139
139
|
CAUSE_MESSAGE = "#{RequestBlocked::BASE_CAUSE_MESSAGE}" \
|
|
140
|
-
"Ways to work around this are using proxies or rotating residential IPs."
|
|
140
|
+
"Ways to work around this are using proxies or rotating residential IPs.".freeze
|
|
141
141
|
end
|
|
142
142
|
|
|
143
143
|
# Raised when too many requests are made (HTTP 429)
|
|
@@ -69,11 +69,11 @@ module YoutubeRb
|
|
|
69
69
|
#
|
|
70
70
|
# @yield [TranscriptMetadata] each available transcript
|
|
71
71
|
# @return [Enumerator] if no block given
|
|
72
|
-
def each(&
|
|
72
|
+
def each(&)
|
|
73
73
|
return to_enum(:each) unless block_given?
|
|
74
74
|
|
|
75
|
-
@manually_created_transcripts.each_value(&
|
|
76
|
-
@generated_transcripts.each_value(&
|
|
75
|
+
@manually_created_transcripts.each_value(&)
|
|
76
|
+
@generated_transcripts.each_value(&)
|
|
77
77
|
end
|
|
78
78
|
|
|
79
79
|
# Find a transcript for the given language codes.
|
|
@@ -56,10 +56,13 @@ module YoutubeRb
|
|
|
56
56
|
innertube_data = fetch_innertube_data(video_id, api_key)
|
|
57
57
|
extract_captions_json(innertube_data, video_id)
|
|
58
58
|
rescue RequestBlocked => e
|
|
59
|
-
retries = @proxy_config.nil?
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
59
|
+
retries = if @proxy_config.nil?
|
|
60
|
+
0
|
|
61
|
+
else
|
|
62
|
+
(@proxy_config.respond_to?(:retries_when_blocked) ? @proxy_config.retries_when_blocked : 0)
|
|
63
|
+
end
|
|
64
|
+
return fetch_captions_json(video_id, try_number: try_number + 1) if try_number + 1 < retries
|
|
65
|
+
|
|
63
66
|
raise e
|
|
64
67
|
end
|
|
65
68
|
|
|
@@ -72,11 +75,10 @@ module YoutubeRb
|
|
|
72
75
|
# @raise [YouTubeDataUnparsable] if the key cannot be found
|
|
73
76
|
def extract_innertube_api_key(html, video_id)
|
|
74
77
|
match = html.match(/"INNERTUBE_API_KEY":\s*"([a-zA-Z0-9_-]+)"/)
|
|
75
|
-
if match && match[1]
|
|
76
|
-
return match[1]
|
|
77
|
-
end
|
|
78
|
+
return match[1] if match && match[1]
|
|
78
79
|
|
|
79
80
|
raise IpBlocked, video_id if html.include?('class="g-recaptcha"')
|
|
81
|
+
|
|
80
82
|
raise YouTubeDataUnparsable, video_id
|
|
81
83
|
end
|
|
82
84
|
|
|
@@ -90,9 +92,7 @@ module YoutubeRb
|
|
|
90
92
|
assert_playability(innertube_data["playabilityStatus"], video_id)
|
|
91
93
|
|
|
92
94
|
captions_json = innertube_data.dig("captions", "playerCaptionsTracklistRenderer")
|
|
93
|
-
if captions_json.nil? || !captions_json.key?("captionTracks")
|
|
94
|
-
raise TranscriptsDisabled, video_id
|
|
95
|
-
end
|
|
95
|
+
raise TranscriptsDisabled, video_id if captions_json.nil? || !captions_json.key?("captionTracks")
|
|
96
96
|
|
|
97
97
|
captions_json
|
|
98
98
|
end
|
|
@@ -119,9 +119,8 @@ module YoutubeRb
|
|
|
119
119
|
end
|
|
120
120
|
|
|
121
121
|
if status == PlayabilityStatus::ERROR && reason == PlayabilityFailedReason::VIDEO_UNAVAILABLE
|
|
122
|
-
if video_id.start_with?("http://") || video_id.start_with?("https://")
|
|
123
|
-
|
|
124
|
-
end
|
|
122
|
+
raise InvalidVideoId, video_id if video_id.start_with?("http://") || video_id.start_with?("https://")
|
|
123
|
+
|
|
125
124
|
raise VideoUnavailable, video_id
|
|
126
125
|
end
|
|
127
126
|
|
|
@@ -157,9 +156,7 @@ module YoutubeRb
|
|
|
157
156
|
if html.include?('action="https://consent.youtube.com/s"')
|
|
158
157
|
create_consent_cookie(html, video_id)
|
|
159
158
|
html = fetch_html(video_id)
|
|
160
|
-
if html.include?('action="https://consent.youtube.com/s"')
|
|
161
|
-
raise FailedToCreateConsentCookie, video_id
|
|
162
|
-
end
|
|
159
|
+
raise FailedToCreateConsentCookie, video_id if html.include?('action="https://consent.youtube.com/s"')
|
|
163
160
|
end
|
|
164
161
|
|
|
165
162
|
html
|
|
@@ -195,9 +192,9 @@ module YoutubeRb
|
|
|
195
192
|
response = @http_client.post(url) do |req|
|
|
196
193
|
req.headers["Content-Type"] = "application/json"
|
|
197
194
|
req.body = JSON.generate({
|
|
198
|
-
|
|
199
|
-
|
|
200
|
-
|
|
195
|
+
"context" => INNERTUBE_CONTEXT,
|
|
196
|
+
"videoId" => video_id
|
|
197
|
+
})
|
|
201
198
|
end
|
|
202
199
|
|
|
203
200
|
raise_http_errors(response, video_id)
|
|
@@ -1,6 +1,5 @@
|
|
|
1
1
|
# frozen_string_literal: true
|
|
2
2
|
|
|
3
|
-
require_relative "transcript/version"
|
|
4
3
|
require_relative "transcript/settings"
|
|
5
4
|
require_relative "transcript/errors"
|
|
6
5
|
require_relative "transcript/transcript_parser"
|
|
@@ -8,7 +7,6 @@ require_relative "transcript/transcript"
|
|
|
8
7
|
require_relative "transcript/transcript_list"
|
|
9
8
|
require_relative "transcript/transcript_list_fetcher"
|
|
10
9
|
require_relative "transcript/api"
|
|
11
|
-
require_relative "transcript/formatters"
|
|
12
10
|
|
|
13
11
|
module YoutubeRb
|
|
14
12
|
module Transcript
|