parser

Documentation

Index

• type DynamicParser
  • func NewDynamicParser(timeout time.Duration, waitTime int, useHeadless bool) *DynamicParser
  • func (dynamicParser *DynamicParser) ExtractJSFiles(pageURL string) ([]string, error)
  • func (dynamicParser *DynamicParser) GetPageInfo(pageURL string) (*PageInfo, error)
• type PageInfo
• type Parser
  • func NewParser() *Parser
  • func (p *Parser) ExtractInlineJS(html string) []string
  • func (p *Parser) ExtractJSFiles(html, baseURL string) ([]string, error)

Types

type DynamicParser

type DynamicParser struct {
	// contains filtered or unexported fields
}

DynamicParser handles dynamic JavaScript extraction using headless browser

func NewDynamicParser

func NewDynamicParser(timeout time.Duration, waitTime int, useHeadless bool) *DynamicParser

NewDynamicParser creates a new DynamicParser instance

func (*DynamicParser) ExtractJSFiles

func (dynamicParser *DynamicParser) ExtractJSFiles(pageURL string) ([]string, error)

ExtractJSFiles extracts JavaScript files using chromedp

func (*DynamicParser) GetPageInfo

func (dynamicParser *DynamicParser) GetPageInfo(pageURL string) (*PageInfo, error)

GetPageInfo extracts additional page information

type PageInfo

type PageInfo struct {
	URL   string
	Title string
	HTML  string
}

PageInfo contains information about a web page

type Parser

type Parser struct {
	// contains filtered or unexported fields
}

Parser extracts JavaScript files from HTML

func NewParser

func NewParser() *Parser

NewParser creates a new Parser

func (*Parser) ExtractInlineJS

func (p *Parser) ExtractInlineJS(html string) []string

ExtractInlineJS extracts inline JavaScript code blocks

func (*Parser) ExtractJSFiles

func (p *Parser) ExtractJSFiles(html, baseURL string) ([]string, error)

ExtractJSFiles extracts all unique JS file URLs from HTML