Hello, please, I'm trying to get information from a public site: name of a vote, date and table with list of votes
This site: link
I used Python 3, selenium webdriver and 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']")
But it seems like I'm wrongly selecting locations
The name_votação appears this error message:
---------------------------------------------------------------------------
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
The data_votacao this error message:
---------------------------------------------------------------------------
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
And the list_deputed generates an empty list
The data_votacao was to have this content: "10/11/2015 20:15". And it has this XPath in the inspect: // * [@ id="bodyVotation"] / p [2] / text () [1]
The name_votación was to have this content: "MPV Nº 688/2015 - DRAFT CONVERSION LAW - Electronic Nominal". And it has this XPath in the inspect: // * [@ id="bodyVotation"] / p [3] / text ()
And the list_deputed the complete table with the votes (names, UF, and vote) from the Parliamentarian row. It has this XPath: // * [@ id="listing"] / table. And the class="table-2"
Does anyone know the correct form of the commands? Or any tutorial?