最近学习go,爬取网站数据用到正则表达式,做个总结;
Go中正则表达式采用RE2语法(具体是啥咱也不清楚);
字符
. ——匹配任意字符 e.g: abc. 结果: abcd,abcx,abc9;
[] ——匹配括号中任意一个字符 e.g: [abc]d 结果:ad,cd,1d;
- ——[-]中表示范围 e.g: [A-Za-z0-9];
^ ——[^]中表示除括号中的任意字符 e.g:[^xy]a 结果:aa,da,不能为xa,ya;
数量限定
? ——前面单元匹配0或1次;
+ ——前面单元匹配1或多次;
* ——前面单元匹配0或多次;
{,} ——显示个数上下线;e.g : ip地址——[0-9]{1,3}.[0-9]{1,3}.[0-9]{1,3}.[0-9]{1,3};
其他
\ ——转义字符;
| ——条件或;
() ——组成单元 如果字符串本身有括号"[(] aaa. [)]" ;
方法
//参数正则字符串,返回值*Regexp
str := regexp.MustCompile(string)
//参数要查找的数据,查找次数-1为全局,返回值二维数组,查找出的字符串+正则字符串
var result [][]string = str.FindAllStringSubmatch(data, -1)
爬虫
爬取博客园所有文章阅读量,评论,推荐;
package main
import (
"fmt"
"io"
"net/http"
"regexp"
"strconv"
)
var readCount int = 0
var commentCount int = 0
var diggCount int = 0
//http读取网页数据写入result返回
func HttpGet(url string) (result string, err error) {
resp, err1 := http.Get(url)
if err1 != nil {
err = err1
return
}
defer resp.Body.Close()
buf := make([]byte, 4096)
for {
n, err2 := resp.Body.Read(buf)
//fmt.Println(url)
if n == 0 {
break
}
if err2 != nil && err2 != io.EOF {
err = err2
return
}
result += string(buf[:n])
}
return result, err
}
//横向纵向爬取文章标题数据,并累计数值
func SpiderPageDB(index int, page chan int) {
url := "https://www.cnblogs.com/littleperilla/default.html?page=" + strconv.Itoa(index)
result, err := HttpGet(url)
if err != nil {
fmt.Println("HttpGet err:", err)
return
}
str := regexp.MustCompile("post-view-count\">阅读[(](?s:(.*?))[)]</span>")
alls := str.FindAllStringSubmatch(result, -1)
for _, j := range alls {
temp, err := strconv.Atoi(j[1])
if err != nil {
fmt.Println("string2int err:", err)
}
readCount += temp
}
str = regexp.MustCompile("post-comment-count\">评论[(](?s:(.*?))[)]</span>")
alls = str.FindAllStringSubmatch(result, -1)
for _, j := range alls {
temp, err := strconv.Atoi(j[1])
if err != nil {
fmt.Println("string2int err:", err)
}
commentCount += temp
}
str = regexp.MustCompile("post-digg-count\">推荐[(](?s:(.*?))[)]</span>")
alls = str.FindAllStringSubmatch(result, -1)
for _, j := range alls {
temp, err := strconv.Atoi(j[1])
if err != nil {
fmt.Println("string2int err:", err)
}
diggCount += temp
}
page <- index
}
//主要工作方法
func working(start, end int) {
fmt.Printf("正在从%d到%d爬取中...\n", start, end)
//channel通知主线程是否所有go都结束
page := make(chan int)
//多线程go程同时爬取
for i := start; i <= end; i++ {
go SpiderPageDB(i, page)
}
for i := start; i <= end; i++ {
fmt.Printf("拉取到%d页\n", <-page)
}
}
//入口函数
func main() {
//输入爬取的起始页
var start, end int
fmt.Print("startPos:")
fmt.Scan(&start)
fmt.Print("endPos:")
fmt.Scan(&end)
working(start, end)
fmt.Println("阅读:", readCount)
fmt.Println("评论:", commentCount)
fmt.Println("推荐:", diggCount)
}