tnypxl/rollup
1
0
Fork 0
mirror of https://github.com/tnypxl/rollup.git synced 2025-12-15 23:13:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: remove indentation while preserving HTML structure in ExtractContentWithCSS

Browse Source
This commit is contained in:
Arik Jones (aider)
2024-09-22 17:00:16 -05:00
parent 59994c085c
commit d5a94f5468
1 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
internal/scraper/scraper.go
View File

@@ -564,13 +564,20 @@ func ExtractContentWithCSS(content, includeSelector string, excludeSelectors []s
return "", fmt.Errorf("error extracting content with CSS selector: %v", err) return "", fmt.Errorf("error extracting content with CSS selector: %v", err)
} }
// Trim leading and trailing whitespace, but preserve internal newlines // Trim leading and trailing whitespace
selectedContent = strings.TrimSpace(selectedContent) selectedContent = strings.TrimSpace(selectedContent)
// Normalize newlines // Normalize newlines
selectedContent = strings.ReplaceAll(selectedContent, "\r\n", "\n") selectedContent = strings.ReplaceAll(selectedContent, "\r\n", "\n")
selectedContent = strings.ReplaceAll(selectedContent, "\r", "\n") selectedContent = strings.ReplaceAll(selectedContent, "\r", "\n")
// Remove indentation while preserving structure
lines := strings.Split(selectedContent, "\n")
for i, line := range lines {
lines[i] = strings.TrimSpace(line)
}
selectedContent = strings.Join(lines, "\n")
// Remove any leading or trailing newlines // Remove any leading or trailing newlines
selectedContent = strings.Trim(selectedContent, "\n") selectedContent = strings.Trim(selectedContent, "\n")