mirror of
https://github.com/tnypxl/rollup.git
synced 2025-12-15 15:03:17 +00:00
fix: Move HTML to Markdown conversion to scraper.go
This commit is contained in:
@@ -174,13 +174,9 @@ func extractAndConvertContent(urlStr string) (string, error) {
|
||||
}
|
||||
}
|
||||
|
||||
// Create a new converter
|
||||
converter := md.NewConverter("", true, nil)
|
||||
|
||||
// Convert HTML to Markdown
|
||||
markdown, err := converter.ConvertString(content)
|
||||
markdown, err := scraper.ProcessHTMLContent(content, scraper.Config{})
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("error converting HTML to Markdown: %v", err)
|
||||
return "", fmt.Errorf("error processing HTML content: %v", err)
|
||||
}
|
||||
|
||||
parsedURL, err := url.Parse(urlStr)
|
||||
|
||||
@@ -11,7 +11,7 @@ import (
|
||||
|
||||
"github.com/PuerkitoBio/goquery"
|
||||
"github.com/playwright-community/playwright-go"
|
||||
"github.com/russross/blackfriday/v2"
|
||||
md "github.com/JohannesKaufmann/html-to-markdown"
|
||||
)
|
||||
|
||||
var logger *log.Logger
|
||||
@@ -231,16 +231,18 @@ func ProcessHTMLContent(htmlContent string, config Config) (string, error) {
|
||||
return "", fmt.Errorf("error extracting content: %v", err)
|
||||
}
|
||||
|
||||
markdown := convertToMarkdown(content)
|
||||
log.Printf("Converted HTML to Markdown (length: %d)\n", len(markdown))
|
||||
return markdown, nil
|
||||
// Create a new converter
|
||||
converter := md.NewConverter("", true, nil)
|
||||
|
||||
// Convert HTML to Markdown
|
||||
markdown, err := converter.ConvertString(content)
|
||||
if err != nil {
|
||||
log.Printf("Error converting HTML to Markdown: %v\n", err)
|
||||
return "", fmt.Errorf("error converting HTML to Markdown: %v", err)
|
||||
}
|
||||
|
||||
func convertToMarkdown(html string) string {
|
||||
// Use a simple HTML-to-Markdown conversion
|
||||
markdown := blackfriday.Run([]byte(html),
|
||||
blackfriday.WithExtensions(blackfriday.CommonExtensions|blackfriday.HardLineBreak))
|
||||
return string(markdown)
|
||||
log.Printf("Converted HTML to Markdown (length: %d)\n", len(markdown))
|
||||
return markdown, nil
|
||||
}
|
||||
|
||||
func scrollPage(page playwright.Page) error {
|
||||
|
||||
Reference in New Issue
Block a user