(golang)HTTP基本认证机制及使用gocolly登录爬取
内网有个网页用了HTTP基本认证机制,想用gocolly爬取,不知道怎么登录,只好研究HTTP基本认证机制
参考这里:https://www.jb51.net/article/89070.htm
下面开始参考作者dotcoo了:-)
看了<<http权威指南>>第12章HTTP基本认证机制(本站下载地址://www.jb51.net/books/93254.html),感觉讲的蛮详细的,写了一个小小例子测试.
请求响应过程:
==>
GET /hello HTTP/1.1
Host: 127.0.0.1:
<==
HTTP/1.1 Unauthorized
WWW-Authenticate: Basic realm="Dotcoo User Login"
==>
GET /hello HTTP/1.1
Host: 127.0.0.1:
Authorization: Basic YWRtaW46YWRtaW5wd2Q=
<==
HTTP/1.1 OK
Content-Type: text/plain; charset=utf-
golang HTTP基本认证机制的实现代码
package main
import (
"fmt"
"io"
"net/http"
"log"
"encoding/base64"
"strings"
)
// hello world, the web server
func HelloServer(w http.ResponseWriter, req *http.Request) {
auth := req.Header.Get("Authorization")
if auth == "" {
w.Header().Set("WWW-Authenticate", `Basic realm="Dotcoo User Login"`)
w.WriteHeader(http.StatusUnauthorized)
return
}
fmt.Println(auth)
auths := strings.SplitN(auth, " ", )
if len(auths) != {
fmt.Println("error")
return
}
authMethod := auths[]
authB64 := auths[]
switch authMethod {
case "Basic":
authstr, err := base64.StdEncoding.DecodeString(authB64)
if err != nil {
fmt.Println(err)
io.WriteString(w, "Unauthorized!\n")
return
}
fmt.Println(string(authstr))
userPwd := strings.SplitN(string(authstr), ":", )
if len(userPwd) != {
fmt.Println("error")
return
}
username := userPwd[]
password := userPwd[]
fmt.Println("Username:", username)
fmt.Println("Password:", password)
fmt.Println()
default:
fmt.Println("error")
return
}
io.WriteString(w, "hello, world!\n")
}
func main() {
http.HandleFunc("/hello", HelloServer)
err := http.ListenAndServe(":8000", nil)
if err != nil {
log.Fatal("ListenAndServe: ", err)
}
}
试验了上面的例子后,基本明白了HTTP基本认证的过程。但是怎么用gocolly访问呢?
参考:https://stackoverflow.com/questions/50576248/using-colly-framework-i-cant-login-to-the-evernote-account
但是答复者Matías Insaurralde提供的模拟浏览器访问的例子编译不通过,不明白其中的hptsKey的意思。代码放在下面供参考(可跳过):
package evernote import (
"bytes"
"errors"
"fmt"
"io/ioutil"
"net/http"
"net/http/cookiejar"
"net/url"
"regexp"
"strings"
) const (
evernoteLoginURL = "https://www.evernote.com/Login.action"
) var (
evernoteJSParamsExpr = regexp.MustCompile(`document.getElementById\("(.*)"\).value = "(.*)"`)
evernoteRedirectExpr = regexp.MustCompile(`Redirecting to <a href="(.*)">`) errNoMatches = errors.New("No matches")
errRedirectURL = errors.New("Redirect URL not found")
) // EvernoteClient wraps all methods required to interact with the website.
type EvernoteClient struct {
Username string
Password string
httpClient *http.Client // These parameters persist during the login process:
hpts string
hptsh string
} // NewEvernoteClient initializes a new Evernote client.
func NewEvernoteClient(username, password string) *EvernoteClient {
// Allocate a new cookie jar to mimic the browser behavior:
cookieJar, _ := cookiejar.New(nil) // Fill up basic data:
c := &EvernoteClient{
Username: username,
Password: password,
} // When initializing the http.Client, copy default values from http.DefaultClient
// Pass a pointer to the cookie jar that was created earlier:
c.httpClient = &http.Client{
Transport: http.DefaultTransport,
CheckRedirect: http.DefaultClient.CheckRedirect,
Jar: cookieJar,
Timeout: http.DefaultClient.Timeout,
}
return c
} func (e *EvernoteClient) extractJSParams(body []byte) (err error) {
matches := evernoteJSParamsExpr.FindAllSubmatch(body, -)
if len(matches) == {
return errNoMatches
}
for _, submatches := range matches {
if len(submatches) < {
err = errNoMatches
break
}
key := submatches[]
val := submatches[] if bytes.Compare(key, hptsKey) == {
e.hpts = string(val)
}
if bytes.Compare(key, hptshKey) == {
e.hptsh = string(val)
}
}
return nil
} // Login handles the login action.
func (e *EvernoteClient) Login() error {
// First step: fetch the login page as a browser visitor would do:
res, err := e.httpClient.Get(evernoteLoginURL)
if err != nil {
return err
}
if res.Body == nil {
return errors.New("No response body")
}
body, err := ioutil.ReadAll(res.Body)
if err != nil {
return err
}
err = e.extractJSParams(body)
if err != nil {
return err
} // Second step: we have extracted the "hpts" and "hptsh" parameters
// We send a request using only the username and setting "evaluateUsername":
values := &url.Values{}
values.Set("username", e.Username)
values.Set("evaluateUsername", "")
values.Set("analyticsLoginOrigin", "login_action")
values.Set("clipperFlow", "false")
values.Set("showSwitchService", "true")
values.Set("hpts", e.hpts)
values.Set("hptsh", e.hptsh) rawValues := values.Encode()
req, err := http.NewRequest(http.MethodPost, evernoteLoginURL, bytes.NewBufferString(rawValues))
if err != nil {
return err
}
req.Header.Set("Accept", "application/json")
req.Header.Set("Content-Type", "application/x-www-form-urlencoded; charset=UTF-8")
req.Header.Set("x-requested-with", "XMLHttpRequest")
req.Header.Set("referer", evernoteLoginURL)
res, err = e.httpClient.Do(req)
if err != nil {
return err
}
body, err = ioutil.ReadAll(res.Body)
if err != nil {
return err
}
bodyStr := string(body)
if !strings.Contains(bodyStr, `"usePasswordAuth":true`) {
return errors.New("Password auth not enabled")
} // Third step: do the final request, append password to form data:
values.Del("evaluateUsername")
values.Set("password", e.Password)
values.Set("login", "Sign in") rawValues = values.Encode()
req, err = http.NewRequest(http.MethodPost, evernoteLoginURL, bytes.NewBufferString(rawValues))
if err != nil {
return err
}
req.Header.Set("Accept", "text/html")
req.Header.Set("Content-Type", "application/x-www-form-urlencoded; charset=UTF-8")
req.Header.Set("x-requested-with", "XMLHttpRequest")
req.Header.Set("referer", evernoteLoginURL)
res, err = e.httpClient.Do(req)
if err != nil {
return err
} // Check the body in order to find the redirect URL:
body, err = ioutil.ReadAll(res.Body)
if err != nil {
return err
}
bodyStr = string(body)
matches := evernoteRedirectExpr.FindAllStringSubmatch(bodyStr, -)
if len(matches) == {
return errRedirectURL
}
m := matches[]
if len(m) < {
return errRedirectURL
}
redirectURL := m[]
fmt.Println("Login is ok, redirect URL:", redirectURL)
return nil
}
After you successfully get the redirect URL, you should be able to send authenticated requests as long as you keep using the HTTP client that was used for the login process, the cookie jar plays a very important role here. To call this code use: func main() {
evernoteClient := NewEvernoteClient("user@company", "password")
err := evernoteClient.Login()
if err != nil {
panic(err)
}
}
只好自己写,经反复试验,发现对于本文开头自己写的server,只需以下代码即可通过验证,输出了hello,world!(将访问方式改为POST也一样。)
package main import (
"fmt" "io/ioutil"
"net/http"
) // Login handles the login action.
func Login() {
//生成client 参数为默认
client := &http.Client{}
//要访问的url
url := "http://localhost:8000/hello"
//要提交的请求
req, _ := http.NewRequest("GET", url, nil)
//最重要的一句,用户名和密码可随意写
req.SetBasicAuth("aa", "bb")
fmt.Println("POST访问")
//返回结果
res, _ := client.Do(req)
defer res.Body.Close()
fmt.Println("header:")
header := res.Header
fmt.Println(header)
fmt.Println("realm:")
basicRealm := res.Header.Get("Www-Authenticate")
fmt.Println(basicRealm)
fmt.Println("body:")
body, _ := ioutil.ReadAll(res.Body)
fmt.Println(string(body)) } func main() {
Login()
}
查看SetBasicAuth的定义为(liteide中在光标位置按Ctrl+shift+J):
func (r *Request) SetBasicAuth(username, password string) {
r.Header.Set("Authorization", "Basic "+basicAuth(username, password))
}
而basicAuth的定义为
func basicAuth(username, password string) string {
auth := username + ":" + password
return base64.StdEncoding.EncodeToString([]byte(auth))
}
那么,用gocolly访问的代码如下:
package main import (
"encoding/base64"
"fmt"
"net/http" "github.com/gocolly/colly"
) func basicAuth(username, password string) string {
auth := username + ":" + password
return base64.StdEncoding.EncodeToString([]byte(auth))
}
func main() {
c := colly.NewCollector()
h := http.Header{}
h.Set("Authorization", "Basic "+basicAuth("aaaa", "bbbb")) c.OnResponse(func(r *colly.Response) {
//fmt.Println(r)
fmt.Println(string(r.Body))
}) c.Request("GET", "http://localhost:8000/hello", nil, nil, h)
}
注:对于其他网站,也许要用Fiddler抓包,设置相应的header和cookie才行。
(golang)HTTP基本认证机制及使用gocolly登录爬取的更多相关文章
- Golang+chromedp+goquery 简单爬取动态数据
目录 Golang+chromedp+goquery 简单爬取动态数据 Golang的安装 下载golang软件 解压golang 配置golang 重新导入配置 chromedp框架的使用 实际的代 ...
- Atitit HTTP 认证机制基本验证 (Basic Authentication) 和摘要验证 (Digest Authentication)attilax总结
Atitit HTTP认证机制基本验证 (Basic Authentication) 和摘要验证 (Digest Authentication)attilax总结 1.1. 最广泛使用的是基本验证 ( ...
- WPS 认证机制
WPS 认证机制 WPS(Wi-Fi Protected Setup,Wi-Fi保护设置)(有的叫做AOSS.有的叫做QSS,不过功能都一致.)是由Wi-Fi联盟组织实施的认证项目,主要致力于简化无线 ...
- 基于Token的WEB后台认证机制
几种常用的认证机制 HTTP Basic Auth HTTP Basic Auth简单点说明就是每次请求API时都提供用户的username和password,简言之,Basic Auth是配合RES ...
- HTTP中的摘要认证机制
引子: 指定和服务器端交互的HTTP方法,URL地址,即其他请求信息: Method:表示http请求方法,一般使用"GET","POST". url:表示请求 ...
- USB Type-C 应用面临安全性考验,USB-IF 将推动新认证机制
USB 应用已经达到空前盛况,横跨电脑.移动设备.周边设备.影音器材等范畴,是一个极为普遍常见的界面.进入 USB Type-C 世代由于一并推动 USB-PD,过去没有严格执行的认证要求,基于安全性 ...
- 一个NB的安全认证机制
这是一个NB的安全认证机制. 1.这是一个安全认证机制 2.可以防止黑客截获到客户端发送的请求消息,避免了黑客冒充客户端向服务器发送操作的请求. 原理与步骤: 1.客户端与服务器端都会放着一份验证用的 ...
- 【pac4j】OAuth 认证机制 入门篇
1,pac4j是什么? pac4j是一个支持多种支持多种协议的身份认证的Java客户端. 2,pac4j的12种客户端认证机制:目前我只有用过第一和第八种. OAuth (1.0 & 2.0) ...
- web安全认证机制知多少
如今web服务随处可见,成千上万的web程序被部署到公网上供用户访问,有些系统只针对指定用户开放,属于安全级别较高的web应用,他们需要有一种认证机制以保护系统资源的安全,本文将探讨五种常用的认证机制 ...
随机推荐
- Python多版本共存(生产环境)
安装pyenv $ git clone git://github.com/yyuu/pyenv.git ~/.pyenv $ echo 'export PYENV_ROOT="$HOME/. ...
- C++STL模板库适配器之优先级队列
目录 适配器之优先级队列 一丶优先级队列简介(priority_queue) 二丶优先级队列代码演示 1.优先级队列代码以及使用简介 适配器之优先级队列 一丶优先级队列简介(priority_queu ...
- 第41章 CORS - Identity Server 4 中文文档(v1.0.0)
第41章 CORS IdentityServer中的许多端点将通过基于JavaScript的客户端的Ajax调用进行访问.鉴于IdentityServer最有可能托管在与这些客户端不同的源上,这意味着 ...
- SQL Server分页存储过程通用存储过程
CREATE proc [dbo].[p_paging]@tableName varchar(8000), --表名.视图名@indexCol varchar(50) = 'id', ...
- 杭电ACM2009--求数列的和
求数列的和 Time Limit: 2000/1000 MS (Java/Others) Memory Limit: 65536/32768 K (Java/Others)Total Submi ...
- C# 爬虫----Cookies处理(Set-Cookie)
/// <summary> /// Cookie 助手 /// </summary> public class CookieHelper { /// <summary&g ...
- Java开发笔记(七十二)Java8新增的流式处理
通过前面几篇文章的学习,大家应能掌握几种容器类型的常见用法,对于简单的增删改和遍历操作,各容器实例都提供了相应的处理方法,对于实际开发中频繁使用的清单List,还能利用Arrays工具的asList方 ...
- Android开发过程中的坑及解决方法收录(六)
1. file.listFiles 空指针异常 最近在弄个小项目,类似一个文件管理器,需要获得手机存储里的目录之后显示,但是运行过程中出现错误,搜索了资料,得出了以下的解决办法 问题产生的原因: an ...
- Spring笔记04_AOP注解开发_模板_事务
目录 1. Spring基于AspectJ的注解的AOP开发 1. 1 SpringAOP的注解入门 1.2 Spring的AOP的注解通知类型 1.2.1 @Before:前置通知 1.2.2 @A ...
- Selenium自动化-入门1
起初写博客是为了妹子学习,现在发现忽略了最基础的Selenium教程,所以:从本博客开始编辑 Selenium 入门知识.(学好Java) Selenium 入门 1:(学好Java) 录制回放,简单 ...