我需要将文件下载到非本地计算机上的给定位置。这是Web浏览器的正常流程，我将这样做：
我希望能够绕过该文件并执行以下操作：
>>> path_to_download_path = PATH
>>> button = driver.find_element_by_css("...")
>>> button.click()
--> And the file is automatically downloaded to my PATH (or wherever I choose)
或者click还有一种更简单的方式，我可以自动下载文件的内容吗？
我该怎么做？
答案 0 :(得分：1)
你必须检查网站上的javascript并了解它是如何工作的，然后你可以覆盖它来做类似的事情，但即使这样，浏览器安全总是会弹出一个对话框，要求你确认下载。这让你有两个选择（据我所知）：
我无法真正帮助细节，因为我不知道python，但希望这有帮助......
答案 1 :(得分：1)
使用selenium webdriver
使用firefox配置文件下载文件。这个配置文件跳过firefox的对话框。 在线： -
pro.setPreference("browser.downLoad.folderList", 0);
browser.download.folderList的值可以设置为0,1或2.当设置为0时，Firefox会将通过浏览器下载的所有文件保存在用户的桌面上。设置为1时，这些下载内容存储在“下载”文件夹中。设置为2时，将再次使用为最近下载指定的位置。
您需要实施的Firefox个人资料代码： -
FirefoxProfile pro=new FirefoxProfile();
pro.setPreference("browser.downLoad.folderList", 0);
pro.setPreference("browser.helperApps.neverAsk.saveToDisk", "Applications/zip");
WebDriver driver=new FirefoxDriver(pro);
driver.get("http://selenium-release.storage.googleapis.com/2.47/selenium-java-2.47.1.zip");
希望它会对你有所帮助:)。
答案 2 :(得分：0)
初始化驱动程序时，请务必设置下载首选项。
对于Firefox：
ff_prof.set_preference( "browser.download.manager.showWhenStarting", False )
ff_prof.set_preference( "browser.download.folderList", 2 )
ff_prof.set_preference( "browser.download.useDownloadDir", True )
ff_prof.set_preference( "browser.download.dir", self.driver_settings['download_folder'] )
##
# if FF still shows the download dialog, make sure that the filetype is included below
# filetype string options can be found in '~/.mozilla/$USER_PROFILE/mimeTypes.rdf'
##
mime_types = ("application/pdf", "text/html")
ff_prof.set_preference( "browser.helperApps.neverAsk.saveToDisk", (", ".join( mime_types )) )
ff_prof.set_preference( "browser.helperApps.neverAsk.openFile", (", ".join( mime_types )) )
对于Chrome：
capabilities['chromeOptions']['prefs']['download.prompt_for_download'] = False
capabilities['chromeOptions']['prefs']['download.default_directory'] = self.driver_settings['download_folder']
转发下载：
下面是我用来将文件从self.driver_settings['download_folder']（上面设置）重定向到您真正想要文件的位置的代码（to_path可以是现有文件夹或文件路径）。如果您使用的是Linux，我建议您使用tmpfs，以便在{ram}中保留/tmp，然后将self.driver_settings['download_folder']设置为"/tmp/driver_downloads/"。请注意，以下函数假定self.driver_settings['download_folder']始终作为空文件夹开始（这是它如何定位正在下载的文件，因为它是目录中唯一的文件）。
def moveDriverDownload(self, to_path, allowable_extensions, allow_rename_if_exists=False, timeout_seconds=None):
if timeout_seconds is None:
timeout_seconds = 30
wait_delta = timedelta( seconds=timeout_seconds )
start_download_time = datetime.now()
hasTimedOut = lambda: datetime.now() - start_download_time > wait_delta
assert isinstance(allowable_extensions, list) or isinstance(allowable_extensions, tuple) or isinstance(allowable_extensions, set), "instead of a list, found allowable_extensions type of '{}'".format(type(allowable_extensions))
allowable_extensions = [ elem.lower().strip() for elem in allowable_extensions ]
allowable_extensions = [ elem if elem.startswith(".") else "."+elem for elem in allowable_extensions ]
if not ".part" in allowable_extensions:
allowable_extensions.append( ".part" )
re_extension_str = "(?:" + ("$)|(?:".join( re.escape(elem) for elem in allowable_extensions )) + "$)"
getFiles = lambda: next( os.walk( self.driver_settings['download_folder'] ) )[2]
while True:
if hasTimedOut():
del allowable_extensions[ allowable_extensions.index(".part") ]
raise DownloadTimeoutError( "timed out after {} seconds while waiting on file download with extension in {}".format(timeout_seconds, allowable_extensions) )
time.sleep( 0.5 )
file_list = [ elem for elem in getFiles() if re.search( re_extension_str, elem ) ]
if len(file_list) > 0:
break
file_list = [ re.search( r"(?i)^(.*?)(?:\.part)?$", elem ).groups()[0] for elem in file_list ]
if len(file_list) > 1:
if len(file_list) == 2:
if file_list[0] != file_list[1]:
raise Exception( "file_list[0] != file_list[1] <==> {} != {}".format(file_list[0], file_list[1]) )
else:
raise Exception( "len(file_list) > 1. found {}".format(file_list) )
file_path = "%s%s" %(self.driver_settings['download_folder'], file_list[0])
# see if the file is still being downloaded by checking if it's open by any programs
if platform.system() == "Linux":
openProcess = lambda: subprocess.Popen( 'lsof | grep "%s"' %file_path, shell=True, stdout=subprocess.PIPE, stdin=subprocess.PIPE, stderr=subprocess.PIPE )
fileIsFinished = lambda txt: txt.strip() == ""
elif platform.system() == "Windows":
# 'handle' program must be in PATH
# https://technet.microsoft.com/en-us/sysinternals/bb896655
openProcess = lambda: subprocess.Popen( 'handle "%s"' %file_path.replace("/", "\\"), shell=True, stdout=subprocess.PIPE, stdin=subprocess.PIPE, stderr=subprocess.PIPE )
fileIsFinished = lambda txt: bool( re.search("(?i)No matching handles found", txt) )
else:
raise Exception( "unrecognised platform.system() of '{}'".format(platform.system()) )
while True:
lsof_process = openProcess()
lsof_result = lsof_process.communicate()
if len(lsof_result) != 2:
raise Exception( "len(lsof_result) != 2. found {}".format(lsof_result) )
if lsof_result[1].strip() != "":
raise Exception( 'lsof_result[1].strip() != "". found {}'.format(lsof_result) )
if fileIsFinished( lsof_result[0] ):
break
if hasTimedOut():
raise Exception( "timed out after {} seconds waiting for '{}' to be freed from writing. found lsof/handle of '{}'".format(timeout_seconds, file_path, lsof_result[0]) )
time.sleep( 0.5 )
to_path = to_path.replace("\\", "/")
if os.path.isdir( to_path ):
if not to_path.endswith("/"):
to_path += "/"
to_path += file_list[0]
i = 2
while os.path.exists( to_path ):
if not allow_rename_if_exists:
raise Exception( "{} already exists".format(to_path) )
to_path = re.sub( "^(.*/)(.*?)(?:-" + str(i-1) + r")?(|\..*?)?$", r"\1\2-%i\3" %i, to_path )
i += 1
shutil.move( file_path, to_path )
return to_path[ to_path.rindex("/")+1: ]