版权声明:本文可能为博主原创文章,若标明出处可随便转载。 https://blog.csdn.net/Jailman/article/details/81330417
利用go语言的协程并发优势爬取网页速度相当之快,博客园100页新闻标题只需一秒即可全部爬取
package main
import (
"bytes"
"fmt"
"github.com/PuerkitoBio/goquery"
"log"
"net/http"
"runtime"
"strconv"
"sync"
)
func Scraper(page string) string {
// Request the HTML page.
ScrapeURL := "https://news.cnblogs.com/n/page/" + page
client := &http.Client{}
reqest, _ := http.NewRequest("GET", ScrapeURL, nil)
reqest.Header.Set("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8")
reqest.Header.Set("Accept-Charset", "GBK,utf-8;q=0.7,*;q=0.3")
//reqest.Header.Set("Accept-Encoding", "gzip,deflate,sdch")
reqest.Header.Set("Accept-Language", "zh-CN,zh;q=0.8")
reqest.Header.Set("Cache-Control", "max-age=0")
reqest.Header.Set("Connection", "keep-alive")
reqest.Header.Set("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36")
res, err := client.Do(reqest)
if err != nil {
log.Fatal(err)
}
defer res.Body.Close()
if res.StatusCode != 200 {
log.Fatalf("status code error: %d %s", res.StatusCode, res.Status)
}
// Load the HTML document
doc, err := goquery.NewDocumentFromReader(res.Body)
if err != nil {
log.Fatal(err)
}
// Find the review items
var buffer bytes.Buffer
buffer.WriteString("**********Scraped page " + page + "**********\n")
doc.Find(".content .news_entry").Each(func(i int, s *goquery.Selection) {
// For each item found, get the band and title
title := s.Find("a").Text()
url, _ := s.Find("a").Attr("href")
buffer.WriteString("Review " + strconv.Itoa(i) + ": " + title + "\nhttps://news.cnblogs.com" + url + "\n")
})
return buffer.String()
}
func main() {
runtime.GOMAXPROCS(runtime.NumCPU())
ch := make(chan string, 100)
wg := &sync.WaitGroup{}
var page string
for i := 1; i < 101; i++ {
wg.Add(1)
go func(i int) {
page = strconv.Itoa(i)
fmt.Printf("Scraping page %s...\n", page)
ch <- Scraper(page)
wg.Done()
}(i)
}
wg.Wait()
//print result
for i := 0; i < 101; i++ {
fmt.Println(<-ch)
}
}