package WebCrawler

import (
	"fmt"
	"github.com/PuerkitoBio/goquery"
	"io"
	"net/http"
	"strings"
)

type httpGet struct {
}

func (e *httpGet) tryGet(url string) (*goquery.Document, error) {
	resp, err := http.Get(url)
	if err != nil {
		return nil, err
	}
	defer resp.Body.Close()

	if resp.StatusCode != http.StatusOK {
		return nil, fmt.Errorf("请求失败，状态码：%d", resp.StatusCode)
	}

	doc, err := goquery.NewDocumentFromReader(resp.Body)
	if err != nil {
		return nil, err
	}

	return doc, nil
}

func (e *httpGet) HttpGet(url string, try int) (*goquery.Document, error) {
	// 第一次查询
	doc, err := e.tryGet(url)
	if err == nil {
		return doc, nil
	}

	// 重试
	for i := 0; i < try; i++ {
		doc, err = e.tryGet(url)
		if err != nil {
			continue
		}

		return doc, err
	}

	return nil, err
}

func (e *httpGet) tryGetBin(url string) ([]byte, error) {
	resp, err := http.Get(url)
	if err != nil {
		return nil, err
	}
	defer resp.Body.Close()

	if resp.StatusCode != http.StatusOK {
		return nil, fmt.Errorf("请求失败，状态码：%d", resp.StatusCode)
	}

	body, err := io.ReadAll(resp.Body)
	if err != nil {
		return nil, err
	}

	return body, nil
}

func (e *httpGet) HttpGetBin(url string, try int) ([]byte, error) {
	// 第一次查询
	bin, err := e.tryGetBin(url)
	if err == nil {
		return bin, nil
	}

	// 重试
	for i := 0; i < try; i++ {
		bin, err = e.tryGetBin(url)
		if err != nil {
			continue
		}

		return bin, err
	}

	return nil, err
}

func (e *httpGet) MakeUrl(host, url string) string {
	href := ""
	if strings.HasPrefix(url, "http://") || strings.HasPrefix(url, "https://") {
		href = url
	} else if strings.HasPrefix(url, "/") {
		href = host + url
	} else {
		href = host + "/" + url
	}

	return href
}