未单击 Selenium 4 HtmlUnitDriver 按钮
Selenium 4 HtmlUnitDriver Button not clicked
我将 Selenium 4 和 HtmlUnitDriver 与 java 一起使用，我在执行表单按钮时遇到问题。没有显示错误，但根据输出控制台结果，我确定按钮没有被点击。
我添加了一些系统输出以了解某些元素的结果：
这是我的 class :
package htmldriver;
import com.gargoylesoftware.htmlunit.BrowserVersion;
import java.time.Duration;
import java.util.List;
import java.util.concurrent.TimeUnit;
import org.openqa.selenium.*;
import org.openqa.selenium.htmlunit.HtmlUnitDriver;
import org.openqa.selenium.remote.DesiredCapabilities;
import org.openqa.selenium.support.ui.ExpectedConditions;
import org.openqa.selenium.support.ui.WebDriverWait;
public class htmlUnitYest {
public static void main(String[] args) throws InterruptedException {
// turn off htmlunit warnings
java.util.logging.Logger.getLogger("com.gargoylesoftware.htmlunit").setLevel(java.util.logging.Level.OFF);
java.util.logging.Logger.getLogger("org.apache.http").setLevel(java.util.logging.Level.OFF);
WebDriver driver = new HtmlUnitDriver(BrowserVersion.CHROME, true);
driver.get("http://www.mahakim.ma/Ar/Annonces/RechercherAnnonces/?Page=AnnoncesJudiciaires#");
// This code will print the page title
System.out.println("Page title is: " + driver.getTitle());
WebElement startDate = ((HtmlUnitDriver) driver).findElementById("txtDateD");
WebElement endDate = ((HtmlUnitDriver) driver).findElementById("txtDateF");
WebElement searchButton = ((HtmlUnitDriver) driver).findElementById("btnRechercheAnnByDateTypeJur");
WebElement tabList = ((HtmlUnitDriver) driver).findElementByXPath("//ul[@role=\"tablist\" and @class=\"nav nav-pills TypeJuridiction\"]");
List<WebElement> choices = ((HtmlUnitDriver) driver).findElementsByCssSelector("#TypeJuridiction .TypeJuridiction li");
WebElement resultTab = ((HtmlUnitDriver) driver).findElementById("Res");
WebElement resultDetails = ((HtmlUnitDriver) driver).findElementById("Res_Detail");
startDate.sendKeys("14/03/2022");
endDate.sendKeys("21/03/2022");
int position = 1;
for (WebElement choiceType : choices) {
position += 1;
if ( position < 3 ) {
continue;
}
System.out.println("choiceType: " + choices);
System.out.println("searchButton: " + searchButton);
WebDriverWait wait = new WebDriverWait(driver,Duration.ofSeconds(20));
wait.until(ExpectedConditions.elementToBeClickable(choiceType));
((HtmlUnitDriver) driver).findElementById("btnRechercheAnnByDateTypeJur").click();
driver.manage().timeouts().pageLoadTimeout(Duration.ofSeconds(20));
WebElement ResDiv = ((HtmlUnitDriver) driver).findElementById("Res");
List<WebElement> ColsInResDiv = ((HtmlUnitDriver) driver).findElementsByClassName("col-lg-12");
System.out.println("resultTab: " + ColsInResDiv);
driver.manage().timeouts().pageLoadTimeout(Duration.ofSeconds(10));
// when search button clicked this element will be exist and style of second div.col-lg-12 will become : display inline
List<WebElement> da = ((HtmlUnitDriver) driver).findElementsByCssSelector("#Res .DetailAnnonce");
System.out.println("da: " + da);
List<WebElement> results = ((HtmlUnitDriver) driver).findElementsByXPath(".//a[@class=\"DetailAnnonce\"]");
for (WebElement item : results) {
System.out.println("item: " + item);
WebDriverWait waitArticle = new WebDriverWait(driver,Duration.ofSeconds(20));
waitArticle.until(ExpectedConditions.elementToBeClickable((item)));
List<WebElement> details = resultDetails.findElements(By.xpath(".//a[@class=\"link-pointer\"]"));
for (WebElement article : details) {
System.out.println("article: " + article.toString());
Thread.sleep(1);
waitArticle.until(ExpectedConditions.elementToBeClickable((article)));
WebElement downloadFile = waitArticle.until(ExpectedConditions.elementToBeClickable(((HtmlUnitDriver) driver).findElementByXPath("//a[@class=\"DownFiles\"]")));
downloadFile.click();
WebElement closeModel = waitArticle.until(ExpectedConditions.elementToBeClickable(((HtmlUnitDriver) driver).findElementByXPath("//div[@id=\"ModalPJ\"]//button[@data-dismiss=\"modal\"]")));
closeModel.click();
}
}
position++;
}
// This code will print the page title
System.out.println("Page title is: " + driver.getTitle());
driver.quit();
}
}
这是system.out的输出。在控制台中：
"C:\Program Files\Java\jdk1.8.0_171\bin\java.exe ..."
Page title is: محاكم
choiceType: [<li role="presentation" class="active">, <li role="presentation">, <li role="presentation">]
searchButton: <button id="btnRechercheAnnByDateTypeJur" class="btn btn-primary">
resultTab: [<div class="col-lg-12">, <div class="col-lg-12" style="display: none;">, <div class="col-lg-12 well well-sm" id="Res_Detail">, <div class="footer_sepHoriz col-lg-12">]
da: []
choiceType: [<li role="presentation" class="active">, <li role="presentation">, <li role="presentation">]
searchButton: <button id="btnRechercheAnnByDateTypeJur" class="btn btn-primary">
resultTab: [<div class="col-lg-12">, <div class="col-lg-12" style="display: none;">, <div class="col-lg-12 well well-sm" id="Res_Detail">, <div class="footer_sepHoriz col-lg-12">]
da: []
Page title is: محاكم
Process finished with exit code 0
这是我手动单击搜索按钮时 HTML 页面的屏幕截图：
PS：在浏览器中，当我点击搜索按钮时，它通过 jquery 像这样 $("#btnRechercheAnnByDateTypeJur").click(function (e) {... } 执行，然后调用 ajax 脚本如果有帮助，从服务器获取数据。
编辑：
我的pom.xml文件：
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>webscrapping</groupId>
<artifactId>cap</artifactId>
<version>1.0-SNAPSHOT</version>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>8</source>
<target>8</target>
</configuration>
</plugin>
</plugins>
</build>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
</properties>
<dependencies>
<dependency>
<groupId>org.seleniumhq.selenium</groupId>
<artifactId>selenium-java</artifactId>
<version>2.53.1</version>
</dependency>
</dependencies>
</project>
我检查了你的代码，当你点击它时，它似乎没有正确加载 javascript。 Javascript 对 htmlunit 不是很友好 ;).
剧作家1.20.0可以轻松搞定（如何设置剧作家https://playwright.dev/java/docs/intro）。只需添加您的 pom:
<dependency>
<groupId>com.microsoft.playwright</groupId>
<artifactId>playwright</artifactId>
<version>1.20.0</version>
</dependency>
它的工作，开始下载文件，但在一些下载堆积并且无法打开模态给出错误超时等待这个元素.DownFiles。
明天我会检查我是否能找到问题所在。
public static void main(String[] args) throws InterruptedException {
try (Playwright playwright = Playwright.create()) {
final BrowserType chromium = playwright.chromium();
//you can do it with headless mode or with open browser
final Browser browser = chromium.launch(new BrowserType
.LaunchOptions()
.setHeadless(false));
final Page page = browser.newPage();
page.navigate("http://www.mahakim.ma/Ar/Annonces/RechercherAnnonces/?Page=AnnoncesJudiciaires#");
ElementHandle searchButton = page.querySelector("#btnRechercheAnnByDateTypeJur");
ElementHandle tabList = page.querySelector("//ul[@role=\"tablist\" and @class=\"nav nav-pills TypeJuridiction\"]");
List<ElementHandle> choices = page.querySelectorAll("#TypeJuridiction .TypeJuridiction li");
//start date
page.fill("#txtDateD", "14/03/2022");
//end date
page.fill("#txtDateF", "21/03/2022");
page.querySelector("div[id='TypeJuridiction'] li:nth-child(3)").click();
page.querySelector("#btnRechercheAnnByDateTypeJur").click();
Thread.sleep(3000);
page.querySelector(".DetailAnnonce").click();
Thread.sleep(3000);
List<ElementHandle> results = page.querySelectorAll(".DetailAnnonce-Plus");
for (ElementHandle item : results) {
//click for open modal
try {
item.querySelector(".link-pointer").click();
page.waitForSelector(".DownFiles");
} catch (Exception e) {
System.out.println("Timeout can not open modal " + item.innerHTML());
Thread.sleep(1000);
continue;
}
// Wait for the download to start
Download download = page.waitForDownload(() -> {
// Perform the action that initiates download
page.click(".DownFiles");
});
// Wait for the download process to complete
Path path = download.path();
System.out.println("Downloading the file of: " + path + System.lineSeparator()
+ "item: " + item.innerHTML());
Thread.sleep(2000);
//close modal
page.querySelector(".btn.btn-default").click();
}
System.out.println("Total downloaded files: " + results.size());
}
}
添加于 2022 年 3 月 23 日
解决弹窗问题，改成firefox(headless)效果很好
final BrowserType chromium = playwright.firefox();
final Browser browser = chromium.launch();
我将 Selenium 4 和 HtmlUnitDriver 与 java 一起使用，我在执行表单按钮时遇到问题。没有显示错误，但根据输出控制台结果，我确定按钮没有被点击。
我添加了一些系统输出以了解某些元素的结果：
这是我的 class :
package htmldriver;
import com.gargoylesoftware.htmlunit.BrowserVersion;
import java.time.Duration;
import java.util.List;
import java.util.concurrent.TimeUnit;
import org.openqa.selenium.*;
import org.openqa.selenium.htmlunit.HtmlUnitDriver;
import org.openqa.selenium.remote.DesiredCapabilities;
import org.openqa.selenium.support.ui.ExpectedConditions;
import org.openqa.selenium.support.ui.WebDriverWait;
public class htmlUnitYest {
public static void main(String[] args) throws InterruptedException {
// turn off htmlunit warnings
java.util.logging.Logger.getLogger("com.gargoylesoftware.htmlunit").setLevel(java.util.logging.Level.OFF);
java.util.logging.Logger.getLogger("org.apache.http").setLevel(java.util.logging.Level.OFF);
WebDriver driver = new HtmlUnitDriver(BrowserVersion.CHROME, true);
driver.get("http://www.mahakim.ma/Ar/Annonces/RechercherAnnonces/?Page=AnnoncesJudiciaires#");
// This code will print the page title
System.out.println("Page title is: " + driver.getTitle());
WebElement startDate = ((HtmlUnitDriver) driver).findElementById("txtDateD");
WebElement endDate = ((HtmlUnitDriver) driver).findElementById("txtDateF");
WebElement searchButton = ((HtmlUnitDriver) driver).findElementById("btnRechercheAnnByDateTypeJur");
WebElement tabList = ((HtmlUnitDriver) driver).findElementByXPath("//ul[@role=\"tablist\" and @class=\"nav nav-pills TypeJuridiction\"]");
List<WebElement> choices = ((HtmlUnitDriver) driver).findElementsByCssSelector("#TypeJuridiction .TypeJuridiction li");
WebElement resultTab = ((HtmlUnitDriver) driver).findElementById("Res");
WebElement resultDetails = ((HtmlUnitDriver) driver).findElementById("Res_Detail");
startDate.sendKeys("14/03/2022");
endDate.sendKeys("21/03/2022");
int position = 1;
for (WebElement choiceType : choices) {
position += 1;
if ( position < 3 ) {
continue;
}
System.out.println("choiceType: " + choices);
System.out.println("searchButton: " + searchButton);
WebDriverWait wait = new WebDriverWait(driver,Duration.ofSeconds(20));
wait.until(ExpectedConditions.elementToBeClickable(choiceType));
((HtmlUnitDriver) driver).findElementById("btnRechercheAnnByDateTypeJur").click();
driver.manage().timeouts().pageLoadTimeout(Duration.ofSeconds(20));
WebElement ResDiv = ((HtmlUnitDriver) driver).findElementById("Res");
List<WebElement> ColsInResDiv = ((HtmlUnitDriver) driver).findElementsByClassName("col-lg-12");
System.out.println("resultTab: " + ColsInResDiv);
driver.manage().timeouts().pageLoadTimeout(Duration.ofSeconds(10));
// when search button clicked this element will be exist and style of second div.col-lg-12 will become : display inline
List<WebElement> da = ((HtmlUnitDriver) driver).findElementsByCssSelector("#Res .DetailAnnonce");
System.out.println("da: " + da);
List<WebElement> results = ((HtmlUnitDriver) driver).findElementsByXPath(".//a[@class=\"DetailAnnonce\"]");
for (WebElement item : results) {
System.out.println("item: " + item);
WebDriverWait waitArticle = new WebDriverWait(driver,Duration.ofSeconds(20));
waitArticle.until(ExpectedConditions.elementToBeClickable((item)));
List<WebElement> details = resultDetails.findElements(By.xpath(".//a[@class=\"link-pointer\"]"));
for (WebElement article : details) {
System.out.println("article: " + article.toString());
Thread.sleep(1);
waitArticle.until(ExpectedConditions.elementToBeClickable((article)));
WebElement downloadFile = waitArticle.until(ExpectedConditions.elementToBeClickable(((HtmlUnitDriver) driver).findElementByXPath("//a[@class=\"DownFiles\"]")));
downloadFile.click();
WebElement closeModel = waitArticle.until(ExpectedConditions.elementToBeClickable(((HtmlUnitDriver) driver).findElementByXPath("//div[@id=\"ModalPJ\"]//button[@data-dismiss=\"modal\"]")));
closeModel.click();
}
}
position++;
}
// This code will print the page title
System.out.println("Page title is: " + driver.getTitle());
driver.quit();
}
}
这是system.out的输出。在控制台中：
"C:\Program Files\Java\jdk1.8.0_171\bin\java.exe ..."
Page title is: محاكم
choiceType: [<li role="presentation" class="active">, <li role="presentation">, <li role="presentation">]
searchButton: <button id="btnRechercheAnnByDateTypeJur" class="btn btn-primary">
resultTab: [<div class="col-lg-12">, <div class="col-lg-12" style="display: none;">, <div class="col-lg-12 well well-sm" id="Res_Detail">, <div class="footer_sepHoriz col-lg-12">]
da: []
choiceType: [<li role="presentation" class="active">, <li role="presentation">, <li role="presentation">]
searchButton: <button id="btnRechercheAnnByDateTypeJur" class="btn btn-primary">
resultTab: [<div class="col-lg-12">, <div class="col-lg-12" style="display: none;">, <div class="col-lg-12 well well-sm" id="Res_Detail">, <div class="footer_sepHoriz col-lg-12">]
da: []
Page title is: محاكم
Process finished with exit code 0
这是我手动单击搜索按钮时 HTML 页面的屏幕截图：
PS：在浏览器中，当我点击搜索按钮时，它通过 jquery 像这样 $("#btnRechercheAnnByDateTypeJur").click(function (e) {... } 执行，然后调用 ajax 脚本如果有帮助，从服务器获取数据。
编辑：
我的pom.xml文件：
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>webscrapping</groupId>
<artifactId>cap</artifactId>
<version>1.0-SNAPSHOT</version>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>8</source>
<target>8</target>
</configuration>
</plugin>
</plugins>
</build>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
</properties>
<dependencies>
<dependency>
<groupId>org.seleniumhq.selenium</groupId>
<artifactId>selenium-java</artifactId>
<version>2.53.1</version>
</dependency>
</dependencies>
</project>
我检查了你的代码，当你点击它时，它似乎没有正确加载 javascript。 Javascript 对 htmlunit 不是很友好 ;).
剧作家1.20.0可以轻松搞定（如何设置剧作家https://playwright.dev/java/docs/intro）。只需添加您的 pom:
<dependency>
<groupId>com.microsoft.playwright</groupId>
<artifactId>playwright</artifactId>
<version>1.20.0</version>
</dependency>
它的工作，开始下载文件，但在一些下载堆积并且无法打开模态给出错误超时等待这个元素.DownFiles。
明天我会检查我是否能找到问题所在。
public static void main(String[] args) throws InterruptedException {
try (Playwright playwright = Playwright.create()) {
final BrowserType chromium = playwright.chromium();
//you can do it with headless mode or with open browser
final Browser browser = chromium.launch(new BrowserType
.LaunchOptions()
.setHeadless(false));
final Page page = browser.newPage();
page.navigate("http://www.mahakim.ma/Ar/Annonces/RechercherAnnonces/?Page=AnnoncesJudiciaires#");
ElementHandle searchButton = page.querySelector("#btnRechercheAnnByDateTypeJur");
ElementHandle tabList = page.querySelector("//ul[@role=\"tablist\" and @class=\"nav nav-pills TypeJuridiction\"]");
List<ElementHandle> choices = page.querySelectorAll("#TypeJuridiction .TypeJuridiction li");
//start date
page.fill("#txtDateD", "14/03/2022");
//end date
page.fill("#txtDateF", "21/03/2022");
page.querySelector("div[id='TypeJuridiction'] li:nth-child(3)").click();
page.querySelector("#btnRechercheAnnByDateTypeJur").click();
Thread.sleep(3000);
page.querySelector(".DetailAnnonce").click();
Thread.sleep(3000);
List<ElementHandle> results = page.querySelectorAll(".DetailAnnonce-Plus");
for (ElementHandle item : results) {
//click for open modal
try {
item.querySelector(".link-pointer").click();
page.waitForSelector(".DownFiles");
} catch (Exception e) {
System.out.println("Timeout can not open modal " + item.innerHTML());
Thread.sleep(1000);
continue;
}
// Wait for the download to start
Download download = page.waitForDownload(() -> {
// Perform the action that initiates download
page.click(".DownFiles");
});
// Wait for the download process to complete
Path path = download.path();
System.out.println("Downloading the file of: " + path + System.lineSeparator()
+ "item: " + item.innerHTML());
Thread.sleep(2000);
//close modal
page.querySelector(".btn.btn-default").click();
}
System.out.println("Total downloaded files: " + results.size());
}
}
添加于 2022 年 3 月 23 日
解决弹窗问题，改成firefox(headless)效果很好
final BrowserType chromium = playwright.firefox();
final Browser browser = chromium.launch();