Firstly, I have been trying to get the dropdown from this web page: http://solutions.3m.com/wps/portal/3M/en_US/Interconnect/Home/Products/ProductCatalog/Catalog/?PC_Z7_RJH9U5230O73D0ISNF9B3C3SI1000000_nid=RFCNF5FK7WitWK7G49LP38glNZJXPCDXLDbl
This is the code I have:
import urllib2
from bs4 import BeautifulSoup
import re
from pprint import pprint
import sys
from selenium import common
from selenium import webdriver
import selenium.webdriver.support.ui as ui
from boto.s3.key import Key
import requests
url = 'http://solutions.3m.com/wps/portal/3M/en_US/Interconnect/Home/Products/ProductCatalog/Catalog/?PC_Z7_RJH9U5230O73D0ISNF9B3C3SI1000000_nid=RFCNF5FK7WitWK7G49LP38glNZJXPCDXLDbl'
element_xpath = '//*[@id="Component1"]'
driver = webdriver.PhantomJS()
driver.get(url)
element = driver.find_element_by_xpath(element_xpath)
element_xpath = '/option[@value="02"]'
all_options = element.find_elements_by_tag_name("option")
for option in all_options:
print("Value is: %s" % option.get_attribute("value"))
option.click()
source = driver.page_source.encode('utf-8', 'ignore')
driver.quit()
source = str(source)
soup = BeautifulSoup(source, 'html.parser')
print soup
What prints out is this:
Traceback (most recent call last):
File "../../../../test.py", line 58, in <module>
Value is: XX
main()
File "../../../../test.py", line 46, in main
option.click()
File "/home/eric/dev/octocrawler-env/local/lib/python2.7/site-packages/selenium-2.33.0-py2.7.egg/selenium/webdriver/remote/webelement.py", line 54, in click
self._execute(Command.CLICK_ELEMENT)
File "/home/eric/dev/octocrawler-env/local/lib/python2.7/site-packages/selenium-2.33.0-py2.7.egg/selenium/webdriver/remote/webelement.py", line 228, in _execute
return self._parent.execute(command, params)
File "/home/eric/dev/octocrawler-env/local/lib/python2.7/site-packages/selenium-2.33.0-py2.7.egg/selenium/webdriver/remote/webdriver.py", line 165, in execute
self.error_handler.check_response(response)
File "/home/eric/dev/octocrawler-env/local/lib/python2.7/site-packages/selenium-2.33.0-py2.7.egg/selenium/webdriver/remote/errorhandler.py", line 158, in check_response
raise exception_class(message, screen, stacktrace)
selenium.common.exceptions.ElementNotVisibleException: Message: u'{"errorMessage":"Element is not currently visible and may not be manipulated","request":{"headers":{"Accept":"application/json","Accept-Encoding":"identity","Connection":"close","Content-Length":"81","Content-Type":"application/json;charset=UTF-8","Host":"127.0.0.1:51413","User-Agent":"Python-urllib/2.7"},"httpVersion":"1.1","method":"POST","post":"{\\"sessionId\\": \\"30e4fd50-f0e4-11e3-8685-6983e831d856\\", \\"id\\": \\":wdc:1402434863875\\"}","url":"/click","urlParsed":{"anchor":"","query":"","file":"click","directory":"/","path":"/click","relative":"/click","port":"","host":"","password":"","user":"","userInfo":"","authority":"","protocol":"","source":"/click","queryKey":{},"chunks":["click"]},"urlOriginal":"/session/30e4fd50-f0e4-11e3-8685-6983e831d856/element/%3Awdc%3A1402434863875/click"}}' ; Screenshot: available via screen
And the weirdest most infuriating bit of it all is that sometimes it actually all works out. I have no clue what's going on here.