如何使用Selenium WebDriver findElement(By.xpath())？

Question

拜托，我正在尝试从巴西国会的 public 网站获取信息：投票名称 session、日期和 table 以及投票列表

此站点：http://www2.camara.leg.br/atividade-legislativa/plenario/chamadaExterna.html?link=http://www.camara.gov.br/internet/votacao/mostraVotacao.asp?ideVotacao=6706&tipo=partido

我用了Python 3、selenium webdriver和PhantomJS:

from selenium import webdriver

path_to_phantomjs = '/Users/George/Documents/phantomjs/phantomjs-2.1.1-windows/bin/phantomjs'

browser = webdriver.PhantomJS(executable_path = path_to_phantomjs)

browser.get("http://www2.camara.leg.br/atividade-legislativa/plenario/chamadaExterna.html?link=http://www.camara.gov.br/internet/votacao/mostraVotacao.asp?ideVotacao=6706&tipo=partido")

nome_votacao = browser.find_element_by_xpath("//[@id='corpoVotacao']/p[3]/text()")

data_votacao = browser.find_element_by_xpath("//[@id='corpoVotacao']/div[1]/div[1]/div/div/p[1]/text()[1]")

list_deputados = browser.find_elements_by_xpath(".//table[@class='tabela-2']")

但我好像选错了地点

nome_votacao出现这个错误信息：

---------------------------------------------------------------------------
InvalidSelectorException                  Traceback (most recent call last)
<ipython-input-11-e67933637ae0> in <module>()
----> 1 nome_votacao = browser.find_element_by_xpath("//[@id='corpoVotacao']/p[3]/text()")

c:\users\george\appdata\local\programs\python\python36-32\code\votos\lib\site-packages\selenium\webdriver\remote\webdriver.py in find_element_by_xpath(self, xpath)
    363             driver.find_element_by_xpath('//div/td[1]')
    364         """
--> 365         return self.find_element(by=By.XPATH, value=xpath)
    366 
    367     def find_elements_by_xpath(self, xpath):

c:\users\george\appdata\local\programs\python\python36-32\code\votos\lib\site-packages\selenium\webdriver\remote\webdriver.py in find_element(self, by, value)
    841         return self.execute(Command.FIND_ELEMENT, {
    842             'using': by,
--> 843             'value': value})['value']
    844 
    845     def find_elements(self, by=By.ID, value=None):

c:\users\george\appdata\local\programs\python\python36-32\code\votos\lib\site-packages\selenium\webdriver\remote\webdriver.py in execute(self, driver_command, params)
    306         response = self.command_executor.execute(driver_command, params)
    307         if response:
--> 308             self.error_handler.check_response(response)
    309             response['value'] = self._unwrap_value(
    310                 response.get('value', None))

c:\users\george\appdata\local\programs\python\python36-32\code\votos\lib\site-packages\selenium\webdriver\remote\errorhandler.py in check_response(self, response)
    192         elif exception_class == UnexpectedAlertPresentException and 'alert' in value:
    193             raise exception_class(message, screen, stacktrace, value['alert'].get('text'))
--> 194         raise exception_class(message, screen, stacktrace)
    195 
    196     def _value_or_default(self, obj, key, default):

InvalidSelectorException: Message: {"errorMessage":"Unable to locate an element with the xpath expression //[@id='corpoVotacao']/p[3]/text() because of the following error:\nError: INVALID_EXPRESSION_ERR: DOM XPath Exception 51","request":{"headers":{"Accept":"application/json","Accept-Encoding":"identity","Connection":"close","Content-Length":"118","Content-Type":"application/json;charset=UTF-8","Host":"127.0.0.1:55799","User-Agent":"Python http auth"},"httpVersion":"1.1","method":"POST","post":"{\"using\": \"xpath\", \"value\": \"//[@id='corpoVotacao']/p[3]/text()\", \"sessionId\": \"366665f0-be24-11e7-aa25-75da268b98e2\"}","url":"/element","urlParsed":{"anchor":"","query":"","file":"element","directory":"/","path":"/element","relative":"/element","port":"","host":"","password":"","user":"","userInfo":"","authority":"","protocol":"","source":"/element","queryKey":{},"chunks":["element"]},"urlOriginal":"/session/366665f0-be24-11e7-aa25-75da268b98e2/element"}}
Screenshot: available via screen

data_votacao这个错误信息：

---------------------------------------------------------------------------
InvalidSelectorException                  Traceback (most recent call last)
<ipython-input-12-24c43341f310> in <module>()
----> 1 data_votacao = browser.find_element_by_xpath("//[@id='corpoVotacao']/div[1]/div[1]/div/div/p[1]/text()[1]")

c:\users\george\appdata\local\programs\python\python36-32\code\votos\lib\site-packages\selenium\webdriver\remote\webdriver.py in find_element_by_xpath(self, xpath)
    363             driver.find_element_by_xpath('//div/td[1]')
    364         """
--> 365         return self.find_element(by=By.XPATH, value=xpath)
    366 
    367     def find_elements_by_xpath(self, xpath):

c:\users\george\appdata\local\programs\python\python36-32\code\votos\lib\site-packages\selenium\webdriver\remote\webdriver.py in find_element(self, by, value)
    841         return self.execute(Command.FIND_ELEMENT, {
    842             'using': by,
--> 843             'value': value})['value']
    844 
    845     def find_elements(self, by=By.ID, value=None):

c:\users\george\appdata\local\programs\python\python36-32\code\votos\lib\site-packages\selenium\webdriver\remote\webdriver.py in execute(self, driver_command, params)
    306         response = self.command_executor.execute(driver_command, params)
    307         if response:
--> 308             self.error_handler.check_response(response)
    309             response['value'] = self._unwrap_value(
    310                 response.get('value', None))

c:\users\george\appdata\local\programs\python\python36-32\code\votos\lib\site-packages\selenium\webdriver\remote\errorhandler.py in check_response(self, response)
    192         elif exception_class == UnexpectedAlertPresentException and 'alert' in value:
    193             raise exception_class(message, screen, stacktrace, value['alert'].get('text'))
--> 194         raise exception_class(message, screen, stacktrace)
    195 
    196     def _value_or_default(self, obj, key, default):

InvalidSelectorException: Message: {"errorMessage":"Unable to locate an element with the xpath expression //[@id='corpoVotacao']/div[1]/div[1]/div/div/p[1]/text()[1] because of the following error:\nError: INVALID_EXPRESSION_ERR: DOM XPath Exception 51","request":{"headers":{"Accept":"application/json","Accept-Encoding":"identity","Connection":"close","Content-Length":"143","Content-Type":"application/json;charset=UTF-8","Host":"127.0.0.1:55799","User-Agent":"Python http auth"},"httpVersion":"1.1","method":"POST","post":"{\"using\": \"xpath\", \"value\": \"//[@id='corpoVotacao']/div[1]/div[1]/div/div/p[1]/text()[1]\", \"sessionId\": \"366665f0-be24-11e7-aa25-75da268b98e2\"}","url":"/element","urlParsed":{"anchor":"","query":"","file":"element","directory":"/","path":"/element","relative":"/element","port":"","host":"","password":"","user":"","userInfo":"","authority":"","protocol":"","source":"/element","queryKey":{},"chunks":["element"]},"urlOriginal":"/session/366665f0-be24-11e7-aa25-75da268b98e2/element"}}
Screenshot: available via screen

并且 list_deputados 生成一个空列表

data_votacao 的内容是：“10/11/2015 20:15”。它在检查中有这个 XPath：//*[@id="corpoVotacao"]/p[2]/text()[1]

nome_votação 的内容是："MPV Nº 688/2015 - PROJETO DE LEI DE CONVERSÃO - Nominal Eletrônica"。它在检查中有这个 XPath：//*[@id="corpoVotacao"]/p[3]/text()

而 list_deputados 是从 "Parlamentar" 行开始的完整 table 和选票（姓名、UF 和投票）。它有这个 XPath：//*[@id="listagem"]/table。而 class="tabela-2"

有人知道命令的正确形式吗？或者一些教程？

Answer 1

你能试试吗

//*[@id="corpoVotacao"]/p[3]/text() 作为 XPATH 而不是 //[@id='corpoVotacao']/p[3]/text()

//*[@id="corpoVotacao"]/div[1]/div[1]/div/div/p[1]/text()[1] 作为 XPATH 而不是 //[@id='corpoVotacao']/div[1]/div[1]/div/div/p[1]/text()[1]

last XPATH 对我来说似乎是正确的，你也可以在 get() 之后隐式等待以确保元素加载到 UI。

Answer 2

第一个问题是所有感兴趣的元素都在 iframe 中。所以，首先你必须切换到 iframe:

iframe = driver.find_element_by_xpath("//iframe[@id='ifr']")
driver.switch_to_frame(iframe)

此外，xpath 也不正确。您可以使用以下内容：

nome_votacao = driver.find_element_by_xpath("//*[@id='corpoVotacao']/p[3]")
data_votacao = driver.find_element_by_xpath("//*[@id='corpoVotacao']/div[1]/div[1]/div/div/p[1]")
list_deputados = driver.find_elements_by_xpath("*//div[@id='listagem']/table[@class='tabela-2']/tbody/tr/td")

完整代码：

driver = webdriver.PhantomJS(executable_path=r'/pathTo/phantomjs')
driver.get("http://www2.camara.leg.br/atividade-legislativa/plenario/chamadaExterna.html?link=http://www.camara.gov.br/internet/votacao/mostraVotacao.asp?ideVotacao=6706&tipo=partido")
iframe = driver.find_element_by_xpath("//iframe[@id='ifr']")
driver.switch_to_frame(iframe)

nome_votacao = driver.find_element_by_xpath("//*[@id='corpoVotacao']/p[3]")
data_votacao = driver.find_element_by_xpath("//*[@id='corpoVotacao']/div[1]/div[1]/div/div/p[1]")
list_deputados = driver.find_elements_by_xpath("*//div[@id='listagem']/table[@class='tabela-2']/tbody/tr/td")

print(nome_votacao.text)
print("----------------------------")

print(data_votacao.text)

print("----------------------------")


i=0
maxLen=len(list_deputados)
print("maxLen: " + str(maxLen))
for deputado in list_deputados:
    print("Parlamentar DEM: " + list_deputados[i].text)
    print("UF: " + list_deputados[i+1].text)
    print("Voto: " + list_deputados[i+2].text)
    i=i+2
    print("--------------"+str(i)+"-------------")
    if(i==maxLen-3): #don't consider the last row: Total Solidaried: 11
        break


driver.close()

如何使用Selenium WebDriver findElement(By.xpath())？

How to use the Selenium WebDriver findElement (By.xpath ())?

python

phantomjs

selenium-webdriver