海运的博客

<?php
class DomainAge{
  private $WHOIS_SERVERS=array(
    "com"               =>  array("whois.verisign-grs.com","/Creation Date:(.*)/"),
    "net"               =>  array("whois.verisign-grs.com","/Creation Date:(.*)/"),
    "org"               =>  array("whois.pir.org","/Created On:(.*)/"),
    "info"              =>  array("whois.afilias.info","/Created On:(.*)/"),
    "biz"               =>  array("whois.neulevel.biz","/Domain Registration Date:(.*)/"),
    "us"                =>  array("whois.nic.us","/Domain Registration Date:(.*)/"),
    "uk"                =>  array("whois.nic.uk","/Registered on:(.*)/"),
    "ca"                =>  array("whois.cira.ca","/Creation date:(.*)/"),
    "tel"               =>  array("whois.nic.tel","/Domain Registration Date:(.*)/"),
    "ie"                =>  array("whois.iedr.ie","/registration:(.*)/"),
    "it"                =>  array("whois.nic.it","/Created:(.*)/"),
    "cc"                =>  array("whois.nic.cc","/Creation Date:(.*)/"),
    "ws"                =>  array("whois.nic.ws","/Domain Created:(.*)/"),
    "sc"                =>  array("whois2.afilias-grs.net","/Created On:(.*)/"),
    "mobi"              =>  array("whois.dotmobiregistry.net","/Created On:(.*)/"),
    "pro"               =>  array("whois.registrypro.pro","/Created On:(.*)/"),
    "edu"               =>  array("whois.educause.net","/Domain record activated:(.*)/"),
    "tv"                =>  array("whois.nic.tv","/Creation Date:(.*)/"),
    "travel"            =>  array("whois.nic.travel","/Domain Registration Date:(.*)/"),
    "in"                =>  array("whois.inregistry.net","/Created On:(.*)/"),
    "me"                =>  array("whois.nic.me","/Domain Create Date:(.*)/"),
    "cn"                =>  array("whois.cnnic.cn","/Registration Date:(.*)/"),
    "asia"              =>  array("whois.nic.asia","/Domain Create Date:(.*)/"),
    "ro"                =>  array("whois.rotld.ro","/Registered On:(.*)/"),
    "aero"              =>  array("whois.aero","/Created On:(.*)/"),
    "nu"                =>  array("whois.nic.nu","/created:(.*)/")
  );
  public function age($domain)
  {
    $domain = trim($domain); //remove space from start and end of domain
    if(substr(strtolower($domain), 0, 7) == "http://") $domain = substr($domain, 7); // remove http:// if included
    if(substr(strtolower($domain), 0, 4) == "www.") $domain = substr($domain, 4);//remove www from domain
    if(preg_match("/^([-a-z0-9]{2,100})\.([a-z\.]{2,8})$/i",$domain))
    {
      $domain_parts = explode(".", $domain);
      //取后缀
      $tld = strtolower(array_pop($domain_parts));
      if(!$server=$this->WHOIS_SERVERS[$tld][0]) {
        return false;
      }
      $res=$this->queryWhois($server,$domain);
      if(preg_match($this->WHOIS_SERVERS[$tld][1],$res,$match))
      {
        date_default_timezone_set('UTC');
        $time = time() - strtotime($match[1]);
        $years = floor($time / 31556926);
        $days = floor(($time % 31556926) / 86400);
        if($years == "1") {$y= "1 year";}
        else {$y = $years . " years";}
        if($days == "1") {$d = "1 day";}
        else {$d = $days . " days";}
        return "$y, $d";
      }
      else
        return false;
    }
    else
      return false;
  }
  private function queryWhois($server,$domain)
  {
    $fp = @fsockopen($server, 43, $errno, $errstr, 20) or die("Socket Error " . $errno . " - " . $errstr);
    if($server=="whois.verisign-grs.com")
      $domain="=".$domain;
    //echo $domain;
    fputs($fp, $domain . "\r\n");
    $out = "";
    while(!feof($fp)){
      $out .= fgets($fp);
    }
    fclose($fp);
    //echo $out;
    return $out;
  }
}
$w=new DomainAge();
$age = $w->age("baidu.com");
echo $age."\n";
?>

http://s3.amazonaws.com/alexa-static/top-1m.csv.zip
http://www.quantcast.com/quantcast-top-million.zip

<?php
$text = 'This domain name expired on 12/6/2014 and is pending renewal or deletion.';
$query = "select * from contentanalysis.analyze where text = '".$text."'";
$url = 'http://query.yahooapis.com/v1/public/yql';
$yql_query_url = $url . "?q=" . urlencode($query);
$yql_query_url .= "&format=json";
$yql_query_url .= "&enable_categorizer=true";
$yql_query_url .= "&diagnostics=false";
$yql_query_url .= "&related_entities=true";
$yql_query_url .= "&show_metadata=true";
$ch = curl_init($yql_query_url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER,true);
$result = curl_exec($ch);
curl_close($ch);
$result = json_decode($result);
var_dump($result);
if(!is_null($result->query->results)) {
  foreach($result->query->results->entities as $word) {
    if (is_array($word)) {
      foreach($word as $subword) {
        echo $subword->text->content."\n";
      }
    } else{
      echo $word->text->content."\n";
    }
  }
}
?>

文档：https://developer.yahoo.com/search/content/V2/contentAnalysis.html

Windows下安装setuptools和pip：
https://bootstrap.pypa.io/ez_setup.py
https://bootstrap.pypa.io/get-pip.py

python ez_setup.py
python get-pip.py

安装selenium：

pip install selenium

安装PhantomJS：

https://bitbucket.org/ariya/phantomjs/downloads/phantomjs-1.9.7-linux-x86_64.tar.bz2
tar jxvf phantomjs-1.9.7-linux-x86_64.tar.bz2
cp phantomjs-1.9.7-linux-x86_64/bin/phantomjs /bin/
chmod 755 /bin/phantomjs 

使用示例：

from selenium import webdriver
driver = webdriver.PhantomJS()
driver.get("http://www.baidu.com")
data = driver.title
print data

通过Remote Selenium Server：

from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
driver = webdriver.Remote(
  command_executor='http://192.168.1.3:4444/wd/hub',
  desired_capabilities={'browserName': 'PhantomJS',
                                  'version': '2',
                                  'javascriptEnabled': True})
driver = webdriver.Remote(
   command_executor='http://192.168.1.3:4444/wd/hub',
   desired_capabilities=DesiredCapabilities.PHANTOMJS)
driver.get("http://www.baidu.com")
data = driver.title
print data

PhantomJS和Firefox速度对比：

import unittest
from selenium import webdriver
import time
class TestThree(unittest.TestCase):

    def setUp(self):
        self.startTime = time.time()

    def test_url_fire(self):
        self.driver = webdriver.Firefox()
        self.driver.get("http://www.qq.com")
        self.driver.quit()

    def test_url_phantom(self):
        self.driver = webdriver.PhantomJS()
        self.driver.get("http://www.qq.com")
        self.driver.quit()

    def tearDown(self):
        t = time.time() - self.startTime
        print "%s: %.3f" % (self.id(), t)
        self.driver.quit

if __name__ == '__main__':
    suite = unittest.TestLoader().loadTestsFromTestCase(TestThree)
    unittest.TextTestRunner(verbosity=0).run(suite)

远程连接chrome:

google-chrome --remote-debugging-port=9222 --no-sandbox

import time
from selenium import webdriver
from selenium.webdriver.chrome.options import Options

chrome_options = Options()
chrome_options.add_experimental_option("debuggerAddress", "127.0.0.1:9222")
driver = webdriver.Chrome(options=chrome_options)
driver.get("https://91porn.com")
html = driver.page_source
print(html)
time.sleep(2000)
driver.quit()

远程连接firefox：

firefox -marionette -start-debugger-server 2828

import time
from selenium import webdriver
from selenium.webdriver.firefox.service import Service

firefox_services = Service(executable_path='/usr/bin/geckodriver', port=3000, service_args=['--marionette-port', '2828', '--connect-existing'])
driver = webdriver.Firefox(service=firefox_services)
driver.get("https://91porn.com")
pageSource = driver.page_source
print(pageSource)
driver.quit()


#import time
#from selenium.webdriver import Firefox
#from selenium import webdriver

#driver = webdriver.Firefox()
#driver.get("https://91porn.com")
#html = driver.page_source
#print(html)
#time.sleep(2000)

通过composer安装php-webdriver：

apt install php7.4-cli php-curl php-zip
curl -sS https://getcomposer.org/installer | php --install-dir=/usr/bin/
php composer.phar require php-webdriver/webdriver 

安装java环境和selenium server：

apt install openjdk-14-jre
wget https://selenium-release.storage.googleapis.com/3.141/selenium-server-standalone-3.141.59.jar
java -jar selenium-server-standalone-3.141.59.jar 

安装firefox/chrome浏览器和相应的webdirver：

wget https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb
apt install ./google-chrome-stable_current_amd64.deb 
wget https://chromedriver.storage.googleapis.com/88.0.4324.96/chromedriver_linux64.zip
unzip chromedriver_linux64.zip 
mv chromedriver /usr/bin/
apt install firefox
wget https://github.com/mozilla/geckodriver/releases/download/v0.29.0/geckodriver-v0.29.0-linux64.tar.gz
tar zxf geckodriver-v0.29.0-linux64.tar.gz 
mv geckodriver /usr/bin/

启动浏览器需X环境支持，可使用XVNC或X Window
可以使用Firefox扩展Selenium IDE: PHP Formatters录制脚本。
selenium chrome使用：

<?php
require_once('vendor/autoload.php');
use Facebook\WebDriver\Remote\DesiredCapabilities;
use Facebook\WebDriver\Remote\RemoteWebDriver;
use Facebook\WebDriver\Chrome\ChromeOptions;

$host = 'http://localhost:4444/wd/hub';
$options = new ChromeOptions();
$options->addArguments(array(
        '--no-sandbox',
        '--headless',
        '--start-maximized',
        '--user-data-dir=/tmp/chrome-user-data-dir',
        '--profile-directory=/tmp/chrome-profile-dir',
        '--user-agent=Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.182 Safari/537.36'
));
$caps = DesiredCapabilities::chrome();
$caps->setCapability(ChromeOptions::CAPABILITY, $options);
$driver = RemoteWebDriver::create($host, $caps);
//default
//$driver = RemoteWebDriver::create($host, DesiredCapabilities::chrome());
//$driver->manage()->window()->maximize();
$driver->get('https://www.haiyun.me/');
var_dump($driver->getTitle());
$driver->quit();

selenium firefox使用：

<?php
namespace Facebook\WebDriver;
require 'vendor/autoload.php';
use Facebook\WebDriver\Remote\RemoteWebDriver;
use Facebook\WebDriver\Remote\DesiredCapabilities;
use Facebook\WebDriver\Firefox\FirefoxProfile;
use Facebook\WebDriver\Firefox\FirefoxDriver;

$host = 'http://localhost:4444/wd/hub';
$profile = new FirefoxProfile();
$profile->setPreference('browser.startup.homepage', 'https://github.com/facebook/php-webdriver/');
$profile->setPreference("general.useragent.override", "Mozilla/5.0");
//$profile->addExtension('./vimperator-3.8.2-fx.xpi');
$caps = DesiredCapabilities::firefox(); 
$caps->setCapability(FirefoxDriver::PROFILE, $profile); 
$caps->setCapability('moz:firefoxOptions', ['args' => ['-headless']]);
$caps->setCapability('moz:firefoxOptions', ['args' => ["-profile", "/tmp/firefox_profile"]]);
$driver = RemoteWebDriver::create($host, $caps);

//default
//$driver = RemoteWebDriver::create($host, DesiredCapabilities::firefox());
$driver->manage()->window()->maximize();
$driver->get('https://www.haiyun.me/');
var_dump($driver->getTitle());
$driver->quit();

文档：
https://github.com/php-webdriver/php-webdriver/wiki
https://php-webdriver.github.io/php-webdriver/