flatten scrape config to 'sites:'

* flatten scrape config to 'sites:'. Update unit tests and readme.
* remove check for file_extensions configuration. 
* show progress indication after 5 seconds.
* add documentation to functions
* fix: remove MaxDepth and link extraction functionality
* fix: Remove MaxDepth references from cmd/web.go
This commit is contained in:
tnypxl
2024-10-14 16:09:58 -05:00
committed by GitHub
parent 333b9a366c
commit 02e39baf38
9 changed files with 317 additions and 283 deletions

View File

@@ -7,35 +7,64 @@ import (
"gopkg.in/yaml.v2"
)
// Config represents the configuration for the rollup tool
type Config struct {
FileTypes []string `yaml:"file_types"`
Ignore []string `yaml:"ignore"`
CodeGenerated []string `yaml:"code_generated"`
Scrape ScrapeConfig `yaml:"scrape"`
}
type ScrapeConfig struct {
Sites []SiteConfig `yaml:"sites"`
OutputType string `yaml:"output_type"`
RequestsPerSecond float64 `yaml:"requests_per_second"`
BurstLimit int `yaml:"burst_limit"`
// FileExtensions is a list of file extensions to include in the rollup
FileExtensions []string `yaml:"file_extensions"`
// IgnorePaths is a list of glob patterns for paths to ignore
IgnorePaths []string `yaml:"ignore_paths"`
// CodeGeneratedPaths is a list of glob patterns for code-generated files
CodeGeneratedPaths []string `yaml:"code_generated_paths"`
// Sites is a list of site configurations for web scraping
Sites []SiteConfig `yaml:"sites"`
// OutputType specifies how the output should be generated
OutputType string `yaml:"output_type"`
// RequestsPerSecond limits the rate of web requests
RequestsPerSecond *float64 `yaml:"requests_per_second,omitempty"`
// BurstLimit sets the maximum burst size for rate limiting
BurstLimit *int `yaml:"burst_limit,omitempty"`
}
// SiteConfig contains configuration for scraping a single site
type SiteConfig struct {
BaseURL string `yaml:"base_url"`
CSSLocator string `yaml:"css_locator"`
ExcludeSelectors []string `yaml:"exclude_selectors"`
MaxDepth int `yaml:"max_depth"`
AllowedPaths []string `yaml:"allowed_paths"`
ExcludePaths []string `yaml:"exclude_paths"`
OutputAlias string `yaml:"output_alias"`
PathOverrides []PathOverride `yaml:"path_overrides"`
// BaseURL is the starting point for scraping this site
BaseURL string `yaml:"base_url"`
// CSSLocator is used to extract specific content
CSSLocator string `yaml:"css_locator"`
// ExcludeSelectors lists CSS selectors for content to exclude
ExcludeSelectors []string `yaml:"exclude_selectors"`
// AllowedPaths lists paths that are allowed to be scraped
AllowedPaths []string `yaml:"allowed_paths"`
// ExcludePaths lists paths that should not be scraped
ExcludePaths []string `yaml:"exclude_paths"`
// OutputAlias provides an alternative name for output files
OutputAlias string `yaml:"output_alias"`
// PathOverrides allows for path-specific configurations
PathOverrides []PathOverride `yaml:"path_overrides"`
}
// PathOverride allows for path-specific configurations
type PathOverride struct {
Path string `yaml:"path"`
CSSLocator string `yaml:"css_locator"`
ExcludeSelectors []string `yaml:"exclude_selectors"`
// Path is the URL path this override applies to
Path string `yaml:"path"`
// CSSLocator overrides the site-wide CSS locator for this path
CSSLocator string `yaml:"css_locator"`
// ExcludeSelectors overrides the site-wide exclude selectors for this path
ExcludeSelectors []string `yaml:"exclude_selectors"`
}
func Load(configPath string) (*Config, error) {
@@ -50,15 +79,28 @@ func Load(configPath string) (*Config, error) {
return nil, fmt.Errorf("error parsing config file: %v", err)
}
if err := config.Validate(); err != nil {
return nil, fmt.Errorf("invalid configuration: %v", err)
}
return &config, nil
}
func DefaultConfigPath() string {
return "rollup.yml"
}
// Validate checks the configuration for any invalid values
func (c *Config) Validate() error {
if c.RequestsPerSecond != nil && *c.RequestsPerSecond <= 0 {
return fmt.Errorf("requests_per_second must be positive")
}
func FileExists(filename string) bool {
_, err := os.Stat(filename)
return err == nil
}
if c.BurstLimit != nil && *c.BurstLimit <= 0 {
return fmt.Errorf("burst_limit must be positive")
}
for _, site := range c.Sites {
if site.BaseURL == "" {
return fmt.Errorf("base_url must be specified for each site")
}
}
return nil
}

View File

@@ -9,34 +9,33 @@ import (
func TestLoad(t *testing.T) {
// Create a temporary config file
content := []byte(`
file_types:
- go
- md
ignore:
file_extensions:
- .go
- .md
ignore_paths:
- "*.tmp"
- "**/*.log"
code_generated:
code_generated_paths:
- "generated_*.go"
scrape:
sites:
- base_url: "https://example.com"
css_locator: "main"
exclude_selectors:
- ".ads"
max_depth: 2
allowed_paths:
- "/blog"
exclude_paths:
- "/admin"
output_alias: "example"
path_overrides:
- path: "/special"
css_locator: ".special-content"
exclude_selectors:
- ".sidebar"
output_type: "single"
requests_per_second: 1.0
burst_limit: 5
sites:
- base_url: "https://example.com"
css_locator: "main"
exclude_selectors:
- ".ads"
max_depth: 2
allowed_paths:
- "/blog"
exclude_paths:
- "/admin"
output_alias: "example"
path_overrides:
- path: "/special"
css_locator: ".special-content"
exclude_selectors:
- ".sidebar"
output_type: "single"
requests_per_second: 1.0
burst_limit: 5
`)
tmpfile, err := os.CreateTemp("", "config*.yml")
@@ -59,33 +58,33 @@ scrape:
}
// Check if the loaded config matches the expected values
rps := 1.0
bl := 5
expectedConfig := &Config{
FileTypes: []string{"go", "md"},
Ignore: []string{"*.tmp", "**/*.log"},
CodeGenerated: []string{"generated_*.go"},
Scrape: ScrapeConfig{
Sites: []SiteConfig{
{
BaseURL: "https://example.com",
CSSLocator: "main",
ExcludeSelectors: []string{".ads"},
MaxDepth: 2,
AllowedPaths: []string{"/blog"},
ExcludePaths: []string{"/admin"},
OutputAlias: "example",
PathOverrides: []PathOverride{
{
Path: "/special",
CSSLocator: ".special-content",
ExcludeSelectors: []string{".sidebar"},
},
FileExtensions: []string{".go", ".md"},
IgnorePaths: []string{"*.tmp", "**/*.log"},
CodeGeneratedPaths: []string{"generated_*.go"},
Sites: []SiteConfig{
{
BaseURL: "https://example.com",
CSSLocator: "main",
ExcludeSelectors: []string{".ads"},
MaxDepth: 2,
AllowedPaths: []string{"/blog"},
ExcludePaths: []string{"/admin"},
OutputAlias: "example",
PathOverrides: []PathOverride{
{
Path: "/special",
CSSLocator: ".special-content",
ExcludeSelectors: []string{".sidebar"},
},
},
},
OutputType: "single",
RequestsPerSecond: 1.0,
BurstLimit: 5,
},
OutputType: "single",
RequestsPerSecond: &rps,
BurstLimit: &bl,
}
if !reflect.DeepEqual(config, expectedConfig) {
@@ -93,28 +92,67 @@ scrape:
}
}
func TestDefaultConfigPath(t *testing.T) {
expected := "rollup.yml"
result := DefaultConfigPath()
if result != expected {
t.Errorf("DefaultConfigPath() = %q, want %q", result, expected)
}
}
func TestFileExists(t *testing.T) {
// Test with an existing file
tmpfile, err := os.CreateTemp("", "testfile")
if err != nil {
t.Fatalf("Failed to create temp file: %v", err)
}
defer os.Remove(tmpfile.Name())
if !FileExists(tmpfile.Name()) {
t.Errorf("FileExists(%q) = false, want true", tmpfile.Name())
}
// Test with a non-existing file
if FileExists("non_existing_file.txt") {
t.Errorf("FileExists(\"non_existing_file.txt\") = true, want false")
func TestValidate(t *testing.T) {
tests := []struct {
name string
config Config
wantErr bool
}{
{
name: "Valid config",
config: Config{
FileExtensions: []string{".go"},
Sites: []SiteConfig{
{BaseURL: "https://example.com", MaxDepth: 2},
},
},
wantErr: false,
},
{
name: "No file extensions",
config: Config{},
wantErr: true,
},
{
name: "Invalid requests per second",
config: Config{
FileExtensions: []string{".go"},
RequestsPerSecond: func() *float64 { f := -1.0; return &f }(),
},
wantErr: true,
},
{
name: "Invalid burst limit",
config: Config{
FileExtensions: []string{".go"},
BurstLimit: func() *int { i := -1; return &i }(),
},
wantErr: true,
},
{
name: "Site without base URL",
config: Config{
FileExtensions: []string{".go"},
Sites: []SiteConfig{{}},
},
wantErr: true,
},
{
name: "Negative max depth",
config: Config{
FileExtensions: []string{".go"},
Sites: []SiteConfig{{BaseURL: "https://example.com", MaxDepth: -1}},
},
wantErr: true,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
err := tt.config.Validate()
if (err != nil) != tt.wantErr {
t.Errorf("Validate() error = %v, wantErr %v", err, tt.wantErr)
}
})
}
}

View File

@@ -45,7 +45,6 @@ type SiteConfig struct {
BaseURL string
CSSLocator string
ExcludeSelectors []string
MaxDepth int
AllowedPaths []string
ExcludePaths []string
OutputAlias string
@@ -156,57 +155,6 @@ func scrapeSingleURL(url string, site SiteConfig, results chan<- struct {
}{url, content, nil}
}
func scrapeSite(site SiteConfig, results chan<- struct {
url string
content string
err error
}, limiter *rate.Limiter,
) {
visited := make(map[string]bool)
queue := []string{site.BaseURL}
for len(queue) > 0 {
url := queue[0]
queue = queue[1:]
if visited[url] {
continue
}
visited[url] = true
if !isAllowedURL(url, site) {
continue
}
// Wait for rate limiter before making the request
err := limiter.Wait(context.Background())
if err != nil {
results <- struct {
url string
content string
err error
}{url, "", fmt.Errorf("rate limiter error: %v", err)}
continue
}
cssLocator, excludeSelectors := getOverrides(url, site)
content, err := scrapeURL(url, cssLocator, excludeSelectors)
results <- struct {
url string
content string
err error
}{url, content, err}
if len(visited) < site.MaxDepth {
links, _ := ExtractLinks(url)
for _, link := range links {
if !visited[link] && isAllowedURL(link, site) {
queue = append(queue, link)
}
}
}
}
}
func isAllowedURL(urlStr string, site SiteConfig) bool {
parsedURL, err := url.Parse(urlStr)
@@ -510,40 +458,6 @@ func scrollPage(page playwright.Page) error {
return nil
}
// ExtractLinks extracts all links from the given URL
func ExtractLinks(urlStr string) ([]string, error) {
logger.Printf("Extracting links from URL: %s\n", urlStr)
page, err := browser.NewPage()
if err != nil {
return nil, fmt.Errorf("could not create page: %v", err)
}
defer page.Close()
if _, err = page.Goto(urlStr, playwright.PageGotoOptions{
WaitUntil: playwright.WaitUntilStateNetworkidle,
}); err != nil {
return nil, fmt.Errorf("could not go to page: %v", err)
}
links, err := page.Evaluate(`() => {
const anchors = document.querySelectorAll('a');
return Array.from(anchors).map(a => a.href);
}`)
if err != nil {
return nil, fmt.Errorf("could not extract links: %v", err)
}
var result []string
for _, link := range links.([]interface{}) {
// Normalize URL by removing trailing slash
normalizedLink := strings.TrimRight(link.(string), "/")
result = append(result, normalizedLink)
}
logger.Printf("Extracted %d links\n", len(result))
return result, nil
}
// ExtractContentWithCSS extracts content from HTML using a CSS selector
func ExtractContentWithCSS(content, includeSelector string, excludeSelectors []string) (string, error) {