selenium - 如何使用远程 selenium webdriver 下载文件？

Question

我正在使用远程selenium网络驱动程序来执行一些测试。然而，在某些时候，我需要下载文件并检查其内容。

我使用远程网络驱动程序如下(在python中):

PROXY = ...

prefs = {
    "profile.default_content_settings.popups":0,
    "download.prompt_for_download": "false",
    "download.default_directory": os.getcwd(),
}
chrome_options = Options()
chrome_options.add_argument("--disable-extensions")
chrome_options.add_experimental_option("prefs", prefs)

webdriver.DesiredCapabilities.CHROME['proxy'] = {
  "httpProxy":PROXY,
  "ftpProxy":PROXY,
  "sslProxy":PROXY,
  "noProxy":None,
  "proxyType":"MANUAL",
  "class":"org.openqa.selenium.Proxy",
  "autodetect":False
}
driver = webdriver.Remote(
        command_executor='http://aaa.bbb.ccc:4444/wd/hub',
        desired_capabilities=DesiredCapabilities.CHROME)

使用“普通”网络驱动程序，我可以在本地计算机上毫无问题地下载文件。然后我可以使用测试代码来例如验证下载文件的内容(可能会根据测试参数而变化)。这不是对下载本身的测试，但我需要一种方法来验证生成文件的内容...

但是如何使用远程网络驱动程序来做到这一点呢？我没有在任何地方找到任何有用的东西......

Answer 1

Selenium API 不提供将文件下载到远程计算机上的方法。

但是单独使用 Selenium 仍然是可能的，具体取决于浏览器。

使用 Chrome，可以通过导航 chrome://downloads/ 列出下载的文件并通过注入(inject) <input type="file"> 进行检索在页面中:

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
import os, time, base64


def get_downloaded_files(driver):

  if not driver.current_url.startswith("chrome://downloads"):
    driver.get("chrome://downloads/")

  return driver.execute_script( \
    "return downloads.Manager.get().items_   "
    "  .filter(e => e.state === 'COMPLETE')  "
    "  .map(e => e.filePath || e.file_path); " )


def get_file_content(driver, path):

  elem = driver.execute_script( \
    "var input = window.document.createElement('INPUT'); "
    "input.setAttribute('type', 'file'); "
    "input.hidden = true; "
    "input.onchange = function (e) { e.stopPropagation() }; "
    "return window.document.documentElement.appendChild(input); " )

  elem._execute('sendKeysToElement', {'value': [ path ], 'text': path})

  result = driver.execute_async_script( \
    "var input = arguments[0], callback = arguments[1]; "
    "var reader = new FileReader(); "
    "reader.onload = function (ev) { callback(reader.result) }; "
    "reader.onerror = function (ex) { callback(ex.message) }; "
    "reader.readAsDataURL(input.files[0]); "
    "input.remove(); "
    , elem)

  if not result.startswith('data:') :
    raise Exception("Failed to get file content: %s" % result)

  return base64.b64decode(result[result.find('base64,') + 7:])



capabilities_chrome = { \
    'browserName': 'chrome',
    # 'proxy': { \
     # 'proxyType': 'manual',
     # 'sslProxy': '50.59.162.78:8088',
     # 'httpProxy': '50.59.162.78:8088'
    # },
    'goog:chromeOptions': { \
      'args': [
      ],
      'prefs': { \
        # 'download.default_directory': "",
        # 'download.directory_upgrade': True,
        'download.prompt_for_download': False,
        'plugins.always_open_pdf_externally': True,
        'safebrowsing_for_trusted_sources_enabled': False
      }
    }
  }

driver = webdriver.Chrome(desired_capabilities=capabilities_chrome)
#driver = webdriver.Remote('http://127.0.0.1:5555/wd/hub', capabilities_chrome)

# download a pdf file
driver.get("https://www.mozilla.org/en-US/foundation/documents")
driver.find_element_by_css_selector("[href$='.pdf']").click()

# list all the completed remote files (waits for at least one)
files = WebDriverWait(driver, 20, 1).until(get_downloaded_files)

# get the content of the first file remotely
content = get_file_content(driver, files[0])

# save the content in a local file in the working directory
with open(os.path.basename(files[0]), 'wb') as f:
  f.write(content)

使用 Firefox，可以通过切换上下文，通过脚本调用浏览器 API 来直接列出和检索文件:

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
import os, time, base64

def get_file_names_moz(driver):
  driver.command_executor._commands["SET_CONTEXT"] = ("POST", "/session/$sessionId/moz/context")
  driver.execute("SET_CONTEXT", {"context": "chrome"})
  return driver.execute_async_script("""
    var { Downloads } = Components.utils.import('resource://gre/modules/Downloads.jsm', {});
    Downloads.getList(Downloads.ALL)
      .then(list => list.getAll())
      .then(entries => entries.filter(e => e.succeeded).map(e => e.target.path))
      .then(arguments[0]);
    """)
  driver.execute("SET_CONTEXT", {"context": "content"})

def get_file_content_moz(driver, path):
  driver.execute("SET_CONTEXT", {"context": "chrome"})
  result = driver.execute_async_script("""
    var { OS } = Cu.import("resource://gre/modules/osfile.jsm", {});
    OS.File.read(arguments[0]).then(function(data) {
      var base64 = Cc["@mozilla.org/scriptablebase64encoder;1"].getService(Ci.nsIScriptableBase64Encoder);
      var stream = Cc['@mozilla.org/io/arraybuffer-input-stream;1'].createInstance(Ci.nsIArrayBufferInputStream);
      stream.setData(data.buffer, 0, data.length);
      return base64.encodeToString(stream, data.length);
    }).then(arguments[1]);
    """, path)
  driver.execute("SET_CONTEXT", {"context": "content"})
  return base64.b64decode(result)

capabilities_moz = { \
    'browserName': 'firefox',
    'marionette': True,
    'acceptInsecureCerts': True,
    'moz:firefoxOptions': { \
      'args': [],
      'prefs': {
        # 'network.proxy.type': 1,
        # 'network.proxy.http': '12.157.129.35', 'network.proxy.http_port': 8080,
        # 'network.proxy.ssl':  '12.157.129.35', 'network.proxy.ssl_port':  8080,      
        'browser.download.dir': '',
        'browser.helperApps.neverAsk.saveToDisk': 'application/octet-stream,application/pdf', 
        'browser.download.useDownloadDir': True, 
        'browser.download.manager.showWhenStarting': False, 
        'browser.download.animateNotifications': False, 
        'browser.safebrowsing.downloads.enabled': False, 
        'browser.download.folderList': 2,
        'pdfjs.disabled': True
      }
    }
  }

# launch Firefox
# driver = webdriver.Firefox(capabilities=capabilities_moz)
driver = webdriver.Remote('http://127.0.0.1:5555/wd/hub', capabilities_moz)

# download a pdf file
driver.get("https://www.mozilla.org/en-US/foundation/documents")
driver.find_element_by_css_selector("[href$='.pdf']").click()

# list all the downloaded files (waits for at least one)
files = WebDriverWait(driver, 20, 1).until(get_file_names_moz)

# get the content of the last downloaded file
content = get_file_content_moz(driver, files[0])

# save the content in a local file in the working directory
with open(os.path.basename(files[0]), 'wb') as f:
  f.write(content)