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"
    "golang.org/x/net/html/atom"
)
 
// 初始化日志配置
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并提取指定的元素
func extractElements(doc *html.Node, targetAtom atom.Atom) []*html.Node {
    var elements []*html.Node
    var f func(*html.Node)
    f = func(n *html.Node) {
        if n.Type == html.ElementNode && n.DataAtom == targetAtom {
            elements = append(elements, n)
        }
        for c := n.FirstChild; c != nil; c = c.NextSibling {
            f(c)
        }
    }
    f(doc)
    return elements
}
 
// 爬取指定URL的页面内容
func crawlPage(logger *zap.Logger, url string) (string, error) {
    client := &http.Client{Timeout: 10 * time.Second}
    resp, err := client.Get(url)
    if err != nil {
        logger.Error("Error fetching URL", zap.Error(err), zap.String("url", url))
        return "", err
    }
    defer resp.Body.Close()
 
    if resp.StatusCode != http.StatusOK {
        logger.Error("Received non-200 HTTP status code", zap.Int("status_code", resp.StatusCode), zap.String("url", url))
        return "", fmt.Errorf("non-200 status code: %d", resp.StatusCode)
    }
 
    doc, err := html.Parse(resp.Body)
    if err != nil {
        logger.Error("Error parsing HTML", zap.Error(err), zap.String("url", url))
        return "", err
    }
 
    // 假设我们要提取所有的h1元素
    h1Elements := extractElements(doc, atom.H1)
    var content string
    for _, elem := range h1Elements {
        for _, n := range elem.ChildNodes {
            content += n.Data
        }
    }
 
    return content, nil
}
 
func main() {
    logger, err := initLogger()
    if err != nil {
        log.Fatalf("Error initializing logger: %v", err)
    }
    defer logger.Sync()
 
    content, err := crawlPage(logger, "https://example.com")
    if err != nil {
        logger.Error("Crawling failed", zap.E