：幽灵蛛（pholcus）--header get post学习资料

Posted 2020-08-29 徐长卿学数据分析

 

 转载请注明出处：http://www.cnblogs.com/SSSR/p/6349298.html

get和post参考：http://ju.outofmemory.cn/entry/96382

登录知乎：https://github.com/DeanThompson/zhihu-go

并发：http://studygolang.com/articles/5658 

https://sanwen8.cn/p/5985D5k.html

 

 

分布式爬虫：https://www.v2ex.com/t/179342

爬妹子图：http://www.thinksaas.cn/topics/0/425/425080.html

user agent见以下的例子，随机选择user agent。

 

package http
import (
    "net/http"
    "io/ioutil"
    "fmt"
    //"net/url"
	"log"
	"strings"
	"math/rand"
	"time"
	"regexp"
	"encoding/xml"
	
)

var atagRegExp = regexp.MustCompile(`<a[^>]+[(href)|(HREF)]\\s*\\t*\\n*=\\s*\\t*\\n*[(".+")|(\'.+\')][^>]*>[^<]*</a>`) //以Must前缀的方法或函数都是必须保证一定能执行成功的,否则将引发一次panic
func Spy(url string) {
    defer func() {
        if r := recover(); r != nil {
            log.Println("[E]", r)
        }
    }()
    req, _ := http.NewRequest("GET", url, nil)
    req.Header.Set("User-Agent", GetRandomUserAgent())
    client := http.DefaultClient
    res, e := client.Do(req)
    if e != nil {
        fmt.Errorf("Get请求%s返回错误:%s", url, e)
        return
    }

    if res.StatusCode == 200 {
        body := res.Body
        defer body.Close()
        bodyByte, _ := ioutil.ReadAll(body)
        resStr := string(bodyByte)
        atag := atagRegExp.FindAllString(resStr, -1)
        for _, a := range atag {
            href,_ := GetHref(a)
            if strings.Contains(href, "article/details/") {
                fmt.Println("☆", href)
            }else {
                fmt.Println("□", href)
            }
            //urlChannel <- href
			fmt.Println(href)
        }
    }
}

var userAgent = [...]string{"Mozilla/5.0 (compatible, MSIE 10.0, Windows NT, DigExt)",
    "Mozilla/4.0 (compatible, MSIE 7.0, Windows NT 5.1, 360SE)",
    "Mozilla/4.0 (compatible, MSIE 8.0, Windows NT 6.0, Trident/4.0)",
    "Mozilla/5.0 (compatible, MSIE 9.0, Windows NT 6.1, Trident/5.0,",
    "Opera/9.80 (Windows NT 6.1, U, en) Presto/2.8.131 Version/11.11",
    "Mozilla/4.0 (compatible, MSIE 7.0, Windows NT 5.1, TencentTraveler 4.0)",
    "Mozilla/5.0 (Windows, U, Windows NT 6.1, en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Macintosh, Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/5.0 (Macintosh, U, Intel Mac OS X 10_6_8, en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Linux, U, android 3.0, en-us, Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
    "Mozilla/5.0 (iPad, U, CPU OS 4_3_3 like Mac OS X, en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/4.0 (compatible, MSIE 7.0, Windows NT 5.1, Trident/4.0, SE 2.X MetaSr 1.0, SE 2.X MetaSr 1.0, .NET CLR 2.0.50727, SE 2.X MetaSr 1.0)",
    "Mozilla/5.0 (iPhone, U, CPU iPhone OS 4_3_3 like Mac OS X, en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "MQQBrowser/26 Mozilla/5.0 (Linux, U, Android 2.3.7, zh-cn, MB200 Build/GRJ22, CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1"}

var r = rand.New(rand.NewSource(time.Now().UnixNano()))
func GetRandomUserAgent() string {
    return userAgent[r.Intn(len(userAgent))]
}

func GetHref(atag string) (href,content string) {
    inputReader := strings.NewReader(atag)
    decoder := xml.NewDecoder(inputReader)
    for t, err := decoder.Token(); err == nil; t, err = decoder.Token() {
        switch token := t.(type) {
        // 处理元素开始（标签）
        case xml.StartElement:
            for _, attr := range token.Attr {
                attrName := attr.Name.Local
                attrValue := attr.Value
                if(strings.EqualFold(attrName,"href") || strings.EqualFold(attrName,"HREF")){
                    href = attrValue
                }
            }
        // 处理元素结束（标签）
        case xml.EndElement:
        // 处理字符数据（这里就是元素的文本）
        case xml.CharData:
            content = string([]byte(token))
        default:
            href = ""
            content = ""
        }
    }
    return href, content
}