熟悉了《Golang 网络爬虫框架gocolly/colly 一》和《Golang 网络爬虫框架gocolly/colly 二》之后就可以在网络上爬取大部分数据了。本文接下来将爬取中证指数有限公司提供的行业市盈率。（http://www.csindex.com.cn/zh-CN/downloads/industry-price-earnings-ratio）
定义数据结构体：
type ZhjhHyShyl struct {
Hydm string `json:"行业代码"`
Hymc string `json:"行业名称"`
Zxsj *float64 `json:"最新数据"`
Gpjs int `json:"股票家数"`
Ksjs int `json:"亏损家数"`
Jygy *float64 `json:"近一个月"`
Jsgy *float64 `json:"近三个月"`
Jlgy *float64 `json:"近六个月"`
Jyn *float64 `json:"近一年"`
Zhy []*ZhjhHyShyl `json:"细分行业"`
}
接下来为gocolly调用准备，将用户代理设置为Chrome浏览器，该值可以通过Fiddler工具查看：
c.UserAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299"
还可以利用Fiddler设置更多的Request Header，将爬虫工具伪装成浏览器。
接下来F12调用浏览器调试器查看目标数据的元素，拷贝jQuery选择器，然后改成相对路径。
完成所有的数据抓取代码:
package main
import (
"encoding/json"
"fmt"
"log"
"strconv"
"strings"
"github.com/PuerkitoBio/goquery"
"github.com/gocolly/colly"
)
//证监会行业市盈率
type ZhjhHyShyl struct {
Hydm string `json:"行业代码"`
Hymc string `json:"行业名称"`
Zxsj *float64 `json:"最新数据"`
Gpjs int `json:"股票家数"`
Ksjs int `json:"亏损家数"`
Jygy *float64 `json:"近一个月"`
Jsgy *float64 `json:"近三个月"`
Jlgy *float64 `json:"近六个月"`
Jyn *float64 `json:"近一年"`
Zhy []*ZhjhHyShyl `json:"细分行业"`
}
func main() {
var err error
c := colly.NewCollector()
c.UserAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299"
zjhHyShyl := make([]*ZhjhHyShyl, 0)
c.OnRequest(func(r *colly.Request) {
fmt.Printf("%+v\r\n%+v\r\n", *r, *(r.Headers))
})
c.OnHTML("td>table.list-div-table>tbody>tr", func(e *colly.HTMLElement) {
hyShy := ZhjhHyShyl{
Hydm: e.ChildText("td:first-child"),
Hymc: e.ChildText("td:nth-child(2)"),
}
zxsj, err := strconv.ParseFloat(e.ChildText("td:nth-child(3)"), 64)
if err == nil {
hyShy.Zxsj = &zxsj
}
gpjs, err := strconv.ParseInt(e.ChildText("td:nth-child(4)"), 10, 32)
if err == nil {
hyShy.Gpjs = int(gpjs)
}
ksjs, err := strconv.ParseInt(e.ChildText("td:nth-child(5)"), 10, 32)
if err == nil {
hyShy.Ksjs = int(ksjs)
}
jygy, err := strconv.ParseFloat(e.ChildText("td:nth-child(6)"), 64)
if err == nil {
hyShy.Jygy = &jygy
}
jsgy, err := strconv.ParseFloat(e.ChildText("td:nth-child(7)"), 64)
if err == nil {
hyShy.Jsgy = &jsgy
}
jlgy, err := strconv.ParseFloat(e.ChildText("td:nth-child(8)"), 64)
if err == nil {
hyShy.Jlgy = &jlgy
}
jyn, err := strconv.ParseFloat(e.ChildText("td:nth-child(9)"), 64)
if err == nil {
hyShy.Jyn = &jyn
}
zjhHyShyl = append(zjhHyShyl, &hyShy)
hyShy.Zhy = make([]*ZhjhHyShyl, 0)
e.DOM.Parent().Parent().Next().Find("table.list-div-table>tbody>tr").Each(func(_ int, s *goquery.Selection) {
zhy := ZhjhHyShyl{
Hydm: strings.Trim(s.Find("td:nth-child(1)").Text(), "\r\n\t "),
Hymc: strings.Trim(s.Find("td:nth-child(2)").Text(), "\r\n\t "),
}
zxsj, err := strconv.ParseFloat(strings.Trim(s.Find("td:nth-child(3)").Text(), "\r\n\t "), 64)
if err == nil {
zhy.Zxsj = &zxsj
}
gpjs, err := strconv.ParseInt(strings.Trim(s.Find("td:nth-child(4)").Text(), "\r\n\t "), 10, 32)
if err == nil {
zhy.Gpjs = int(gpjs)
}
ksjs, err := strconv.ParseInt(strings.Trim(s.Find("td:nth-child(5)").Text(), "\r\n\t "), 10, 32)
if err == nil {
zhy.Ksjs = int(ksjs)
}
jygy, err := strconv.ParseFloat(strings.Trim(s.Find("td:nth-child(6)").Text(), "\r\n\t "), 64)
if err == nil {
zhy.Jygy = &jygy
}
jsgy, err := strconv.ParseFloat(strings.Trim(s.Find("td:nth-child(7)").Text(), "\r\n\t "), 64)
if err == nil {
zhy.Jsgy = &jsgy
}
jlgy, err := strconv.ParseFloat(strings.Trim(s.Find("td:nth-child(8)").Text(), "\r\n\t "), 64)
if err == nil {
zhy.Jlgy = &jlgy
}
jyn, err := strconv.ParseFloat(strings.Trim(s.Find("td:nth-child(9)").Text(), "\r\n\t "), 64)
if err == nil {
zhy.Jyn = &jyn
}
hyShy.Zhy = append(hyShy.Zhy, &zhy)
})
})
c.OnScraped(func(_ *colly.Response) {
bData, _ := json.MarshalIndent(zjhHyShyl, "", "\t")
fmt.Println(string(bData))
})
err = c.Visit("http://www.csindex.com.cn/zh-CN/downloads/industry-price-earnings-ratio?date=2017-12-27&type=zjh1")
if err != nil {
log.Fatal(err)
}
}
运行后的部分结果：
{
"行业代码": "D",
"行业名称": "电力、热力、燃气及水的生产和供应业",
"最新数据": 20.12,
"股票家数": 107,
"亏损家数": 5,
"近一个月": 19.51,
"近三个月": 19.7,
"近六个月": 19.87,
"近一年": 18.9,
"细分行业": [{
"行业代码": "44",
"行业名称": "电力、热力生产和供应业",
"最新数据": 18.75,
"股票家数": 70,
"亏损家数": 3,
"近一个月": 18.28,
"近三个月": 18.43,
"近六个月": 18.55,
"近一年": 17.44,
"细分行业": null
}, {
"行业代码": "45",
"行业名称": "燃气生产和供应业",
"最新数据": 28.4,
"股票家数": 22,
"亏损家数": 2,
"近一个月": 25.71,
"近三个月": 25.33,
"近六个月": 25.38,
"近一年": 27.24,
"细分行业": null
}, {
"行业代码": "46",
"行业名称": "水的生产和供应业",
"最新数据": 27.78,
"股票家数": 15,
"亏损家数": 0,
"近一个月": 27.88,
"近三个月": 29.33,
"近六个月": 30.56,
"近一年": 29.64,
"细分行业": null
}]
}