我正在使用一个 selenium 脚本,我正在尝试下载一个 Excel 文件并为其指定一个特定的名称。这是我的代码:
无论如何,我可以为正在下载的文件指定一个特定的名称吗?
代码:
#!/usr/bin/python
from selenium import webdriver
from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
profile = FirefoxProfile()
profile.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain, application/vnd.ms-excel, text/csv, text/comma-separated-values, application/octet-stream")
profile.set_preference("browser.download.dir", "C:\\Downloads" )
browser = webdriver.Firefox(firefox_profile=profile)
browser.get('https://test.com/')
browser.find_element_by_partial_link_text("Excel").click() # Download file
最佳答案
这里是另一个简单的解决方案,你可以等到下载完成,然后从 chrome 下载中获取下载的文件名。
Chrome:
# method to get the downloaded file name
def getDownLoadedFileName(waitTime):
driver.execute_script("window.open()")
# switch to new tab
driver.switch_to.window(driver.window_handles[-1])
# navigate to chrome downloads
driver.get('chrome://downloads')
# define the endTime
endTime = time.time()+waitTime
while True:
try:
# get downloaded percentage
downloadPercentage = driver.execute_script(
"return document.querySelector('downloads-manager').shadowRoot.querySelector('#downloadsList downloads-item').shadowRoot.querySelector('#progress').value")
# check if downloadPercentage is 100 (otherwise the script will keep waiting)
if downloadPercentage == 100:
# return the file name once the download is completed
return driver.execute_script("return document.querySelector('downloads-manager').shadowRoot.querySelector('#downloadsList downloads-item').shadowRoot.querySelector('div#content #file-link').text")
except:
pass
time.sleep(1)
if time.time() > endTime:
break
火狐:
def getDownLoadedFileName(waitTime):
driver.execute_script("window.open()")
WebDriverWait(driver,10).until(EC.new_window_is_opened)
driver.switch_to.window(driver.window_handles[-1])
driver.get("about:downloads")
endTime = time.time()+waitTime
while True:
try:
fileName = driver.execute_script("return document.querySelector('#contentAreaDownloadsView .downloadMainArea .downloadContainer description:nth-of-type(1)').value")
if fileName:
return fileName
except:
pass
time.sleep(1)
if time.time() > endTime:
break
单击下载链接/按钮后,只需调用上述方法即可。
# click on download link
browser.find_element_by_partial_link_text("Excel").click()
# get the downloaded file name
latestDownloadedFileName = getDownLoadedFileName(180) #waiting 3 minutes to complete the download
print(latestDownloadedFileName)
JAVA + Chrome:
这里是java中的方法。
public String waitUntilDonwloadCompleted(WebDriver driver) throws InterruptedException {
// Store the current window handle
String mainWindow = driver.getWindowHandle();
// open a new tab
JavascriptExecutor js = (JavascriptExecutor)driver;
js.executeScript("window.open()");
// switch to new tab
// Switch to new window opened
for(String winHandle : driver.getWindowHandles()){
driver.switchTo().window(winHandle);
}
// navigate to chrome downloads
driver.get("chrome://downloads");
JavascriptExecutor js1 = (JavascriptExecutor)driver;
// wait until the file is downloaded
Long percentage = (long) 0;
while ( percentage!= 100) {
try {
percentage = (Long) js1.executeScript("return document.querySelector('downloads-manager').shadowRoot.querySelector('#downloadsList downloads-item').shadowRoot.querySelector('#progress').value");
//System.out.println(percentage);
}catch (Exception e) {
// Nothing to do just wait
}
Thread.sleep(1000);
}
// get the latest downloaded file name
String fileName = (String) js1.executeScript("return document.querySelector('downloads-manager').shadowRoot.querySelector('#downloadsList downloads-item').shadowRoot.querySelector('div#content #file-link').text");
// get the latest downloaded file url
String sourceURL = (String) js1.executeScript("return document.querySelector('downloads-manager').shadowRoot.querySelector('#downloadsList downloads-item').shadowRoot.querySelector('div#content #file-link').href");
// file downloaded location
String donwloadedAt = (String) js1.executeScript("return document.querySelector('downloads-manager').shadowRoot.querySelector('#downloadsList downloads-item').shadowRoot.querySelector('div.is-active.focus-row-active #file-icon-wrapper img').src");
System.out.println("Download deatils");
System.out.println("File Name :-" + fileName);
System.out.println("Donwloaded path :- " + donwloadedAt);
System.out.println("Downloaded from url :- " + sourceURL);
// print the details
System.out.println(fileName);
System.out.println(sourceURL);
// close the downloads tab2
driver.close();
// switch back to main window
driver.switchTo().window(mainWindow);
return fileName;
}
这是在您的 java 脚本中调用它的方法。
// download triggering step
downloadExe.click();
// now waituntil download finish and then get file name
System.out.println(waitUntilDonwloadCompleted(driver));
输出:
Download deatils
File Name :-RubyMine-2019.1.2 (7).exe
Donwloaded path :- chrome://fileicon/C%3A%5CUsers%5Csupputuri%5CDownloads%5CRubyMine-2019.1.2%20(7).exe?scale=1.25x
Downloaded from url :- https://download-cf.jetbrains.com/ruby/RubyMine-2019.1.2.exe
RubyMine-2019.1.2 (7).exe
关于python - Selenium 在下载时给出文件名,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/34548041/