简单创建基于Go1.19的站点模板爬虫

package main
 
import (
    "fmt"
    "log"
    "net/http"
    "os"
    "time"
 
    "go.uber.org/zap"
    "go.uber.org/zap/zapcore"
    "golang.org/x/net/html"
)
 
// 初始化日志
func initLogger() (*zap.Logger, error) {
    encoderConfig := zapcore.EncoderConfig{
        TimeKey:        "ts",
        LevelKey:       "level",
        NameKey:        "logger",
        CallerKey:      "caller",
        MessageKey:     "msg",
        StacktraceKey:  "stacktrace",
        LineEnding:     zapcore.DefaultLineEnding,
        EncodeLevel:    zapcore.LowercaseLevelEncoder,
        EncodeTime:     zapcore.EpochMillisTimeEncoder,
        EncodeDuration: zapcore.SecondsDurationEncoder,
    }
    core := zapcore.NewCore(zapcore.NewJSONEncoder(encoderConfig), os.Stdout, zapcore.InfoLevel)
    return zap.New(core), nil
}
 
// 解析HTML并提取链接
func extractLinks(doc *html.Node) (links []string) {
    var f func(*html.Node)
    f = func(n *html.Node) {
        if n.Type == html.ElementNode && n.Data == "a" {
            for _, a := range n.Attr {
                if a.Key == "href" {
                    links = append(links, a.Val)
                }
            }
        }
        for c := n.FirstChild; c != nil; c = c.NextSibling {
            f(c)
        }
    }
    f(doc)
    return links
}
 
// 爬取指定URL的链接
func crawl(logger *zap.Logger, url string) ([]string, error) {
    logger.Info("Crawling", zap.String("url", url))
    resp, err := http.Get(url)
    if err != nil {
        return nil, err
    }
    defer resp.Body.Close()
 
    if resp.StatusCode != 200 {
        return nil, fmt.Errorf("non-200 status code: %v", resp.StatusCode)
    }
 
    doc, err := html.Parse(resp.Body)
    if err != nil {
        return nil, err
    }
 
    links := extractLinks(doc)
    logger.Info("Found links", zap.Int("count", len(links)), zap.Strings("links", links))
    return links, nil
}
 
func main() {
    logger, err := initLogger()
    if err != nil {
        log.Fatalf("Failed to init logger: %v", err)
    }
    defer logger.Sync()
 
    start := time.Now()
    links, err := crawl(logger, "https://example.com")
    if err != nil {
        logger.Error("Crawl failed", zap.Error(err))
    } else {
        logger.Info("Crawl successful", zap.Duration("took", time.Since(start)), zap.Int("num_links", len(links)))
    }
}

这段代码使用了Go 1.19的特性，初始化了一个Zap日志器，并使用html包解析HTML文档以提取链接。这个简单的爬虫示例展示了如何使用Go语言进行基本的网络爬虫工作。