User-Agent 访问地址
wget设置user-agent:
wget --user-agent='CCBot/2.0 (https://commoncrawl.org/faq/)' https://ip.useragentinfo.com
curl设置user-agent:
curl -v -I --user-agent 'CCBot/2.0 (https://commoncrawl.org/faq/)' https://ip.useragentinfo.com
kotlin httpclient设置user-agent:
val httpClient = HttpClients.custom().build();
val httpGet = HttpGet("https://ip.useragentinfo.com")
httpGet.setHeader("User-Agent", "CCBot/2.0 (https://commoncrawl.org/faq/)")
try {
    val response = httpClient.execute(httpGet)
    val entity = response.entity
    println(EntityUtils.toString(entity))
    EntityUtils.consumeQuietly(entity)
    response.close()
} catch (e: Exception) {
    httpGet.releaseConnection()
}
java httpclient设置user-agent:
HttpClient httpClient = HttpClients.custom().build();
HttpGet httpGet = new HttpGet("https://ip.useragentinfo.com");
httpGet.setHeader("User-Agent", "CCBot/2.0 (https://commoncrawl.org/faq/)");
try {
    HttpResponse response = httpClient.execute(httpGet);
    HttpEntity entity = response.getEntity();
    // consume the response entity
    System.out.println(EntityUtils.toString(entity));
    EntityUtils.consumeQuietly(entity);
} catch (Exception e) {
    httpGet.releaseConnection();
}
                
kotlin URLConnection设置user-agent:
val url = URL("https://ip.useragentinfo.com")
val connection = url.openConnection()
connection.setRequestProperty("User-agent", "CCBot/2.0 (https://commoncrawl.org/faq/)");
val br = BufferedReader(InputStreamReader(connection.getInputStream()))
val result = StringBuilder()
var line: String?
while (br.readLine().also { line = it } != null) {
    result.append(line)
}
println(result)
                
Python selenium设置user-agent: Selenium文档 chromedriver阿里云镜像下载地址
from selenium import webdriver

if __name__ == '__main__':
    chrome_driver_binary = "/usr/local/bin/chromedriver"  #需根据chromedriver存放位置,修改改行代码。chromedeiver下载地址见上
    chrome_option = webdriver.ChromeOptions()
    chrome_option.add_argument('--headless')  # 16年之后chrome给出了headless解决方案,抢了PhantomJS饭碗

    ua = "CCBot/2.0 (https://commoncrawl.org/faq/)"
    chrome_option.add_argument('user-agent="' + ua + '"')
    browser = webdriver.Chrome(chrome_driver_binary, options=chrome_option, )
    browser.get("https://ip.useragentinfo.com")
    print(browser.title)
    browser.close()
                
Python requests设置user-agent: requests官方网站
import requests
headers = {'user-agent': 'CCBot/2.0 (https://commoncrawl.org/faq/)'}
res = requests.get("https://ip.useragentinfo.com",headers=headers)
print(res.text)
                
Python urllib设置user-agent: Python urllib官方文档
import urllib.request
opener = urllib.request.build_opener()
opener.addheaders = [('User-agent', 'CCBot/2.0 (https://commoncrawl.org/faq/)')]
with opener.open('https://ip.useragentinfo.com') as f:
   print(f.read().decode('utf-8'))
                
 执行上面的代码可能会报证书校验失败,错误内容如下:urllib.error.URLError:<urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1056)> 或者ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1056)
解决方法具体如下:
方法1:使用未经校验的ssl
import urllib.request
import ssl
ssl._create_default_https_context = ssl._create_unverified_context

opener = urllib.request.build_opener()
opener.addheaders = [('User-agent', 'CCBot/2.0 (https://commoncrawl.org/faq/)')]
with opener.open('https://ip.useragentinfo.com') as f:
print(f.read().decode('utf-8'))
                               
方法2:修改为下面的代码
import urllib.request
import ssl
import certifi
req = urllib.request.Request(url='https://ip.useragentinfo.com',headers={"User-Agent":"CCBot/2.0 (https://commoncrawl.org/faq/)"},method="GET")

with urllib.request.urlopen(req, context=ssl.create_default_context(cafile=certifi.where())) as f:
    print(f.read().decode('utf-8'))
                                
Python requests设置user-agent: Scrapy官方文档
# -*- coding: utf-8 -*-
import scrapy


class ExampleSpider(scrapy.Spider):
    name = 'example'
    start_urls = ['https://ip.useragentinfo.com']
    custom_settings = {"DEFAULT_REQUEST_HEADERS": {"User-Agent": "CCBot/2.0 (https://commoncrawl.org/faq/)"}}

    def parse(self, response):
        print(response.css('title').getall())
                
Node.js request设置user-agent: request github地址
let request = require('request');
request({
    url: 'https://ip.useragentinfo.com',
    headers:{
        "User-Agent":"CCBot/2.0 (https://commoncrawl.org/faq/)"
    }
}, function (error, response, body) {
    if (!error && response.statusCode == 200) {
        console.info(body);
    }
});
                
Php Laravel中Guzzle设置user-agent: Guzzle文档
$client = new \GuzzleHttp\Client();
$request = new \GuzzleHttp\Psr7\Request('get', 'https://ip.useragentinfo.com', ['User-Agent' => 'CCBot/2.0 (https://commoncrawl.org/faq/)']);
$response = $client->send($request,['timeout' => 2]);
echo($response->getStatusCode());
                
Android okhttp设置user-agent:(kotlin格式) okhttp github地址
val request = Request.Builder().url("https://ip.useragentinfo.com").addHeader("User-Agent","CCBot/2.0 (https://commoncrawl.org/faq/)").build()
try {
    okHttpClient.newCall(request).execute().use { response ->
        Log.i("test",response.body!!.string())
    }
} catch (e: Exception) {
    Log.i("test",e.message.toString())
}
                
Android Volley设置user-agent:(kotlin格式) Volley github地址

val queue = Volley.newRequestQueue(this)
val url = "https://ip.useragentinfo.com"
val getRequest: StringRequest = object : StringRequest(
    Method.GET, url,
    Response.Listener { response -> // response
        Log.d("Response", response!!.reader().readText())
    },
    Response.ErrorListener { error -> // TODO Auto-generated method stub
        Log.d("ERROR", "error => $error")
    }
) {
    @Throws(AuthFailureError::class)
    override fun getHeaders(): Map<String, String> {
        val params: MutableMap<String, String> = HashMap()
        params["User-Agent"] = "CCBot/2.0 (https://commoncrawl.org/faq/)"
        return params
    }
}
queue.add(getRequest)