Compare commits

...

5 Commits

Author SHA1 Message Date
github-actions[bot]
f45e140126 Update version to v1.4.207 and commit 2025-06-17 07:41:51 +00:00
Kayvan Sylvan
752a66cb48 Merge pull request #1525 from ksylvan/0617-fix-lang-code-vtt-youtube-transcript-bug
Refactor yt-dlp Transcript Logic and Fix Language Bug
2025-06-17 00:40:18 -07:00
Kayvan Sylvan
da28d91d65 refactor: extract common yt-dlp logic to reduce code duplication in YouTube plugin
## CHANGES

- Extract shared yt-dlp logic into tryMethodYtDlpInternal helper
- Add processVTTFileFunc parameter for flexible VTT processing
- Implement language matching for 2-char language codes
- Refactor tryMethodYtDlp to use new helper function
- Refactor tryMethodYtDlpWithTimestamps to use helper
- Reduce code duplication between transcript methods
- Maintain existing functionality with cleaner structure
2025-06-17 00:32:33 -07:00
Daniel Miessler
5a66ca1c5a Updated extract insights. 2025-06-16 16:43:21 -07:00
Daniel Miessler
98f3da610b Updated extract insights. 2025-06-16 16:41:14 -07:00
4 changed files with 22 additions and 58 deletions

View File

@@ -1 +1 @@
"1.4.206"
"1.4.207"

View File

@@ -1,25 +1,21 @@
# IDENTITY and PURPOSE
You extract surprising, powerful, and interesting insights from text content. You are interested in insights related to the purpose and meaning of life, human flourishing, the role of technology in the future of humanity, artificial intelligence and its affect on humans, memes, learning, reading, books, continuous improvement, and similar topics.
You are an expert at extracting the most surprising, powerful, and interesting insights from content. You are interested in insights related to the purpose and meaning of life, human flourishing, the role of technology in the future of humanity, artificial intelligence and its affect on humans, memes, learning, reading, books, continuous improvement, and similar topics.
You create 15 word bullet points that capture the most important insights from the input.
You create 8 word bullet points that capture the most surprising and novel insights from the input.
Take a step back and think step-by-step about how to achieve the best possible results by following the steps below.
# STEPS
- Extract 20 to 50 of the most surprising, insightful, and/or interesting ideas from the input in a section called IDEAS, and write them on a virtual whiteboard in your mind using 15 word bullets. If there are less than 50 then collect all of them. Make sure you extract at least 20.
- From those IDEAS, extract the most powerful and insightful of them and write them in a section called INSIGHTS. Make sure you extract at least 10 and up to 25.
- Extract 10 of the most surprising and novel insights from the input.
- Output them as 8 word bullets in order of surprise, novelty, and importance.
- Write them in the simple, approachable style of Paul Graham.
# OUTPUT INSTRUCTIONS
- INSIGHTS are essentially higher-level IDEAS that are more abstracted and wise.
- Output the INSIGHTS section only.
- Each bullet should be 16 words in length.
- Do not give warnings or notes; only output the requested sections.
- You use bulleted lists for output, not numbered lists.
@@ -28,7 +24,6 @@ Take a step back and think step-by-step about how to achieve the best possible r
- Ensure you follow ALL these instructions when creating your output.
# INPUT
INPUT:
{{input}}

View File

@@ -112,7 +112,9 @@ func (o *YouTube) GrabTranscriptWithTimestamps(videoId string, language string)
return o.tryMethodYtDlpWithTimestamps(videoId, language)
}
func (o *YouTube) tryMethodYtDlp(videoId string, language string) (ret string, err error) {
// tryMethodYtDlpInternal is a helper function to reduce duplication between
// tryMethodYtDlp and tryMethodYtDlpWithTimestamps.
func (o *YouTube) tryMethodYtDlpInternal(videoId string, language string, processVTTFileFunc func(filename string) (string, error)) (ret string, err error) {
// Check if yt-dlp is available
if _, err = exec.LookPath("yt-dlp"); err != nil {
err = fmt.Errorf("yt-dlp not found in PATH. Please install yt-dlp to use YouTube transcript functionality")
@@ -130,9 +132,13 @@ func (o *YouTube) tryMethodYtDlp(videoId string, language string) (ret string, e
// Use yt-dlp to get transcript
videoURL := "https://www.youtube.com/watch?v=" + videoId
outputPath := filepath.Join(tempDir, "%(title)s.%(ext)s")
lang_match := language
if len(language) > 2 {
lang_match = language[:2]
}
cmd := exec.Command("yt-dlp",
"--write-auto-subs",
"--sub-lang", language,
"--sub-lang", lang_match,
"--skip-download",
"--sub-format", "vtt",
"--quiet",
@@ -154,52 +160,15 @@ func (o *YouTube) tryMethodYtDlp(videoId string, language string) (ret string, e
return "", err
}
return o.readAndCleanVTTFile(vttFiles[0])
return processVTTFileFunc(vttFiles[0])
}
func (o *YouTube) tryMethodYtDlp(videoId string, language string) (ret string, err error) {
return o.tryMethodYtDlpInternal(videoId, language, o.readAndCleanVTTFile)
}
func (o *YouTube) tryMethodYtDlpWithTimestamps(videoId string, language string) (ret string, err error) {
// Check if yt-dlp is available
if _, err = exec.LookPath("yt-dlp"); err != nil {
err = fmt.Errorf("yt-dlp not found in PATH. Please install yt-dlp to use YouTube transcript functionality")
return
}
// Create a temporary directory for yt-dlp output (cross-platform)
tempDir := filepath.Join(os.TempDir(), "fabric-youtube-"+videoId)
if err = os.MkdirAll(tempDir, 0755); err != nil {
err = fmt.Errorf("failed to create temp directory: %v", err)
return
}
defer os.RemoveAll(tempDir)
// Use yt-dlp to get transcript
videoURL := "https://www.youtube.com/watch?v=" + videoId
outputPath := filepath.Join(tempDir, "%(title)s.%(ext)s")
cmd := exec.Command("yt-dlp",
"--write-auto-subs",
"--sub-lang", language,
"--skip-download",
"--sub-format", "vtt",
"--quiet",
"--no-warnings",
"-o", outputPath,
videoURL)
var stderr bytes.Buffer
cmd.Stderr = &stderr
if err = cmd.Run(); err != nil {
err = fmt.Errorf("yt-dlp failed: %v, stderr: %s", err, stderr.String())
return
}
// Find VTT files using cross-platform approach
vttFiles, err := o.findVTTFiles(tempDir, language)
if err != nil {
return "", err
}
return o.readAndFormatVTTWithTimestamps(vttFiles[0])
return o.tryMethodYtDlpInternal(videoId, language, o.readAndFormatVTTWithTimestamps)
}
func (o *YouTube) readAndCleanVTTFile(filename string) (ret string, err error) {

View File

@@ -1,3 +1,3 @@
package main
var version = "v1.4.206"
var version = "v1.4.207"