rpa

README

Overview

A library of auxiliary tools for rod, the goal is to simplify the process of rod scraping web data through configurability. The final output can be changed by modifying the configuration file without having to recompile the program.

Usage

func main() {
	r := rpa.Crawler{}
	r.AttachDefaultBrowser()
	b := r.Browser
	b.Close()

	url := "https://cn.bing.com/search?q=sample+simple+pdf"
	val, _, err := r.CrawlUrl(url, "./sample/bing.json", true, true)
	if err != nil {
		fmt.Println(err)
	} else {
		s, _ := json.MarshalIndent(val, "", "\t")
		fmt.Println(string(s))
	}
}

Documentation

Index

• func ElementVisible(page *rod.Page, selector string) bool
• func FileExists(name string) (bool, error)
• func NormalizeFilename(name string) string
• func OpenPage(browser *rod.Browser, url string, sleep int64, selector string, sign WaitSign) (page *rod.Page, err error)
• func RemoveContents(dir string) error
• func RenameFileUnique(dir, fileName, ext string, try int) string
• func WaitElementHide(page *rod.Page, selector string, timeoutSeconds int) (err error)
• func WaitElementShow(page *rod.Page, selector string, timeoutSeconds int) (err error)
• func WaitPage(page *rod.Page, sleep int64, selector string, sign WaitSign) (err error)
• func WriteSortedJSONToFile(data interface{}, filename string) error
• type ConfigNode
• type Crawler
  • func (c *Crawler) AttachDefaultBrowser() *rod.Browser
  • func (c *Crawler) AttachEdgedIE() *rod.Browser
  • func (c *Crawler) CrawlPage(page *rod.Page, cfgOrFile interface{}, autoDownload bool, closeTab bool) (*Result, error)
  • func (c *Crawler) CrawlUrl(url string, cfgOrFile interface{}, autoDownload bool, closeTab bool) (*Result, *rod.Page, error)
• type CrawlerConfig
• type DownloadConfig
• type DownloadResult
• type DownloadType
• type ExternalResult
• type PageLoad
• type Result
• type WaitSign

Functions

func ElementVisible

func ElementVisible(page *rod.Page, selector string) bool

ElementVisible detects whether the selected element is existed and visible

func FileExists

func FileExists(name string) (bool, error)

FileExists to check if a file exists

func NormalizeFilename

func NormalizeFilename(name string) string

NormalizeFilename will replace <>:"/\|?* in string

func OpenPage

func OpenPage(browser *rod.Browser, url string, sleep int64, selector string, sign WaitSign) (page *rod.Page, err error)

func RemoveContents

func RemoveContents(dir string) error

RemoveContents will delete all the contents of a directory

func RenameFileUnique

func RenameFileUnique(dir, fileName, ext string, try int) string

RenameFileUnique rename file name if there are duplicate files

func WaitElementHide

func WaitElementHide(page *rod.Page, selector string, timeoutSeconds int) (err error)

WaitElementHide waiting for a certain element on the page to disappear

func WaitElementShow

func WaitElementShow(page *rod.Page, selector string, timeoutSeconds int) (err error)

WaitElementShow waiting for a certain element on the page to appear

func WaitPage

func WaitPage(page *rod.Page, sleep int64, selector string, sign WaitSign) (err error)

func WriteSortedJSONToFile

func WriteSortedJSONToFile(data interface{}, filename string) error

WriteSortedJSONToFile writing indented and key sorted JSON to a file

Types

type ConfigNode

type ConfigNode struct {
	Selector string `json:"selector"`
	Label    string `json:"label"`
	ID       string `json:"id"`
}

type Crawler

type Crawler struct {
	Browser    *rod.Browser
	CfgFetcher func(path string) (*CrawlerConfig, error)
}

func (*Crawler) AttachDefaultBrowser

func (c *Crawler) AttachDefaultBrowser() *rod.Browser

func (*Crawler) AttachEdgedIE

func (c *Crawler) AttachEdgedIE() *rod.Browser

func (*Crawler) CrawlPage

func (c *Crawler) CrawlPage(page *rod.Page, cfgOrFile interface{}, autoDownload bool, closeTab bool) (*Result, error)

func (*Crawler) CrawlUrl

func (c *Crawler) CrawlUrl(url string, cfgOrFile interface{}, autoDownload bool, closeTab bool) (*Result, *rod.Page, error)

type CrawlerConfig

type CrawlerConfig struct {
	PageLoad        PageLoad                 `json:"pageLoad,omitempty"`
	DataSection     []map[string]interface{} `json:"dataSection"`
	SwitchSection   map[string]interface{}   `json:"switchSection,omitempty"`
	DownloadRoot    string                   `json:"downloadRoot,omitempty"`
	DownloadSection []DownloadConfig         `json:"downloadSection,omitempty"`
}

type DownloadConfig

type DownloadConfig struct {
	ConfigNode
	SavePath   string       `json:"savePath,omitempty"`
	NameProper string       `json:"nameProper,omitempty"`
	NameRender string       `json:"nameRender,omitempty"`
	Type       DownloadType `json:"type"`
}

type DownloadResult

type DownloadResult struct {
	Count     int      `json:"count"`
	Errors    []int    `json:"errors"`
	FileNames []string `json:"fileNames"`
	Links     []string `json:"links"`
}

DownloadResult is a part of result section

type DownloadType

type DownloadType string

const (
	DownloadUrl     DownloadType = "url"
	DownloadElement DownloadType = "element"
)

type ExternalResult

type ExternalResult struct {
	Config  string `json:"config"`
	Connect string `json:"connect"`
	ID      string `json:"id"`
}

type PageLoad

type PageLoad struct {
	Wait     WaitSign `json:"wait"`
	Selector string   `json:"selector,omitempty"`
	Sleep    int64    `json:"sleep,omitempty"`
}

type Result

type Result struct {
	Data            map[string]interface{}    `json:"data"`
	DownloadRoot    string                    `json:"downloadRoot"`
	Downloads       map[string]DownloadResult `json:"downloads"`
	ExternalSection map[string]ExternalResult `json:"externalSection"`
}

type WaitSign

type WaitSign string

const (
	WaitShow  WaitSign = "show"
	WaitHide  WaitSign = "hide"
	WaitDelay WaitSign = "wait"
)