原文連接:Hzy 博客
1.今天就嘗試用colly來爬取豆瓣Top 250!(大家都喜歡拿他來練手…)
直接上代碼了,上面有註釋。
package main
import (
"fmt"
"github.com/PuerkitoBio/goquery"
"github.com/gocolly/colly"
"github.com/gocolly/colly/extensions"
"regexp"
"strings"
"time"
)
func main() {
t := time.Now()
number := 1
c := colly.NewCollector(func(c *colly.Collector) {
extensions.RandomUserAgent(c) // 設置隨機頭
c.Async=true
},
//過濾url,去除不是https://movie.douban.com/top250?start=0&filter= 的url
colly.URLFilters(
regexp.MustCompile("^(https://movie\\.douban\\.com/top250)\\?start=[0-9].*&filter="),
),
) // 創建收集器
// 響應的格式爲HTML,提取頁面中的鏈接
c.OnHTML("a[href]", func(e *colly.HTMLElement) {
link := e.Attr("href")
//fmt.Printf("find link: %s\n", e.Request.AbsoluteURL(link))
c.Visit(e.Request.AbsoluteURL(link))
})
// 獲取電影信息
c.OnHTML("div.info", func(e *colly.HTMLElement) {
e.DOM.Each(func(i int, selection *goquery.Selection) {
movies := selection.Find("span.title").First().Text()
director := strings.Join(strings.Fields(selection.Find("div.bd p").First().Text()), " ")
quote := selection.Find("p.quote span.inq").Text()
fmt.Printf("%d --> %s:%s %s\n", number, movies, director, quote)
number += 1
})
})
c.OnError(func(response *colly.Response, err error) {
fmt.Println(err)
})
c.Visit("https://movie.douban.com/top250?start=0&filter=")
c.Wait()
fmt.Printf("花費時間:%s",time.Since(t))
}
github地址:github地址