golang解析网页利器goquery的使用方法

go get github.com/PuerkitoBio/goquery

package main

import (
 "fmt"
 "log"

 "github.com/PuerkitoBio/goquery"
)

func ExampleScrape() {
 doc, err := goquery.NewDocument("http://metalsucks.net")
 if err != nil {
 log.Fatal(err)
 }

 // Find the review items
 doc.Find(".sidebar-reviews article .content-block").Each(func(i int, s *goquery.Selection) {
 // For each item found, get the band and title
 band := s.Find("a").Text()
 title := s.Find("i").Text()
 fmt.Printf("Review %d: %s - %s\n", i, band, title)
 })
}

func main() {
 ExampleScrape()
}

go get github.com/djimenez/iconv-go

func ExampleScrape() {
 res, err := http.Get(baseUrl)
 if err != nil {
 fmt.Println(err.Error())
 } else {
 defer res.Body.Close()
 utfBody, err := iconv.NewReader(res.Body, "gb2312", "utf-8")
 if err != nil {
  fmt.Println(err.Error())
 } else {
  doc, err := goquery.NewDocumentFromReader(utfBody)
  // 下面就可以用doc去获取网页里的结构数据了
  // 比如
  doc.Find("li").Each(func(i int, s *goquery.Selection) {
  fmt.Println(i, s.Text())
  })
 }
 }
}

baseUrl:="http://baidu.com"
client:=&http.Client{}
req, err := http.NewRequest("GET", baseUrl, nil)
req.Header.Add("User-Agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36")
req.Header.Add("Referer", baseUrl)
req.Header.Add("Cookie", "your cookie") // 也可以通过req.Cookie()的方式来设置cookie
res, err := client.Do(req)
defer res.Body.Close()
//最后直接把res传给goquery就可以来解析网页了
doc, err := goquery.NewDocumentFromResponse(res)