Selenium WebDriver findElement（By.xpath（））の使用方法は？

Question

、私はブラジル議会の公開ウェブサイトから情報を取得しようとしているしてください：投票

のリストと投票セッション、日付とテーブルの名前このサイト：http://www2.camara.leg.br/atividade-legislativa/plenario/chamadaExterna.html?link=http://www.camara.gov.br/internet/votacao/mostraVotacao.asp?ideVotacao=6706&tipo=partido

私は、Python 3を使用し、セレンwebdriverをと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']") 

しかし、私は間違った場所

nome_votacaoを選択してるように見えますが、このエラーメッセージが表示されます：

--------------------------------------------------------------------------- 
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このエラーメッセージ： "2015年10月11日午後08時15分"：

--------------------------------------------------------------------------- 
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 

そしてlist_deputadosは空のリストに

を生成data_votacaoは、このコンテンツを持っていることでした。そして、このXPathは検査中です：// * [@ id = "corpoVotacao"]/p [2]/text（）[1]

nome_votaçãoはこのコンテンツを持っていました： "MPVNº688/2015 - PROJETO DE LEI DECONVERSÃO - 名目Eletrônica "。

そしてlist_deputadosは投票（名前、UF、および）を持つ完全なテーブルを持つことになっていました。投票）、行「Parlamentar」から開始します。このXPath：// * [@ id = "listagem"] /テーブルがあります。そしてクラス= "tabela-2"

誰でも正しい形式のコマンドを知っていますか？またはいくつかのチュートリアルですか？

Answer 1

最初の問題は、すべての関心の要素がiframeの内部にあることです。 だから、最初のあなたはインラインフレームに切り替えることがあります。また

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

XPathは正しくありません。あなたは、次を使用することができます。

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") 

全体コード：

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() 

Answer 2

はまた、あなたが取得した後、暗黙の待ち時間を持つことができ、私には正しいと思われる代わりに代わり //[@id='corpoVotacao']/div[1]/div[1]/div/div/p[1]/text()[1]

最後XPATHのXPATHとして //[@id='corpoVotacao']/p[3]/text()

//*[@id="corpoVotacao"]/div[1]/div[1]/div/div/p[1]/text()[1]のXPATHとして

//*[@id="corpoVotacao"]/p[3]/text()を試すことができます（）要素がUIにロードされていることを確認するだけです。