JavaScript__DoPostback的web刮擦在td中包含herf

Question

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC

chromeOptions = webdriver.ChromeOptions()
chromeOptions.add_experimental_option('useAutomationExtension', False)
driver = webdriver.Chrome(executable_path='C:/Users/ptiwar34/Documents/chromedriver.exe', chrome_options=chromeOptions, desired_capabilities=chromeOptions.to_capabilities())
driver.get('https://www.unspsc.org/search-code/default.aspx?CSS=51%&Type=desc&SS%27=')
WebDriverWait(driver, 20).until(EC.staleness_of(driver.find_element_by_xpath("//td/a[text()='2']")))
driver.find_element_by_xpath("//td/a[text()='2']").click()

numLinks = len(WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.XPATH, "//td/a[text()='2']"))))
print(numLinks)
for i in range(numLinks):
    print("Perform your scraping here on page {}".format(str(i+1)))
    WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH, "//td/a[text()='2']/span//following::span[1]"))).click()
driver.quit()

    <td><span>1</span></td>
    <td><a 
     href="javascript:__doPostBack 
(&#39;dnn$ctr1535$UNSPSCSearch$gvDetailsSearchView&#39;,&#39;Page$2&#39;)" 
style="color:#333333;">2</a>
     </td>

这将引发错误：

raise TimeoutException(message, screen, stacktrace)
TimeoutException

Answer 1

若要刮取网站https://www.unspsc.org/search-code/default.aspx？css=51%&type=desc&ss%27=，使用Selenium可以使用以下定位器策略：

>

代码块：

  from selenium import webdriver
  from selenium.webdriver.support.ui import WebDriverWait
  from selenium.webdriver.common.by import By
  from selenium.webdriver.support import expected_conditions as EC

  chrome_options = webdriver.ChromeOptions() 
  chrome_options.add_argument("start-maximized")
  driver = webdriver.Chrome(options=chrome_options, executable_path=r'C:\WebDrivers\chromedriver.exe')
  driver.get("https://www.unspsc.org/search-code/default.aspx?CSS=51%&Type=desc&SS%27=%27")
  while True:
      try:
          WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH, "//table[contains(@id, 'UNSPSCSearch_gvDetailsSearchView')]//tr[last()]//table//span//following::a[1]"))).click()
          print("Clicked for next page")
      except TimeoutException:
          print("No more pages")
          break
  driver.quit()

控制台输出：

  Clicked for next page
  Clicked for next page
  Clicked for next page
  .
  .
  .