Python爬蟲之Selenium庫的使用方法

# 基本使用
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
browser = webdriver.Chrome()
try:
  browser.get('https://www.baidu.com')
  input = browser.find_element_by_id('kw')
  input.send_keys('Python')
  input.send_keys(Keys.ENTER)
  wait = WebDriverWait(browser, 10)
  wait.until(EC.presence_of_element_located((By.ID, 'content_left')))
  print(browser.current_url)
  print(browser.get_cookies())
  print(browser.page_source)
finally:
  browser.close()

# 聲明瀏覽器對象
from selenium import webdriver
browser = webdriver.Chrome()
browser = webdriver.Firefox()
browser = webdriver.Edge()
browser = webdriver.PhantomJS()
browser = webdriver.Safari()

# 訪問頁面
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
print(browser.page_source)
browser.close()

# 查找元素
# 單個元素
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
# 下面三個效果是一樣的
input_first = browser.find_element_by_id('q')
input_second = browser.find_element_by_css_selector('#q')
input_third = browser.find_element_by_xpath('//*[@id="q"]')
print(input_first)
print(input_second)
print(input_third)
browser.close()

from selenium import webdriver
from selenium.webdriver.common.by import By
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
input_first = browser.find_element(By.ID, 'q')
print(input_first)
browser.close()

# 多個元素
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
lis = browser.find_elements_by_css_selector('.service-bd li')
print(lis)
browser.close()

from selenium import webdriver
from selenium.webdriver.common.by import By
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
lis = browser.find_elements(By.CSS_SELECTOR, '.service-bd li')
print(lis)
browser.close()

# 元素交互操作
# 對獲取的元素調用交互方法
from selenium import webdriver
import time
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
input = browser.find_element_by_id('q')
input.send_keys('筆記本電腦')
time.sleep(5)
input.clear()
input.send_keys('iPad')
button = browser.find_element_by_class_name('btn-search')
# button.click()

# 交互動作
# 將動作附加到動作鏈中串行執行
from selenium import webdriver
from selenium.webdriver import ActionChains
browser = webdriver.Chrome()
url = "http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable"
browser.get(url)
browser.switch_to.frame('iframeResult')
source = browser.find_element_by_css_selector('#draggable')
target = browser.find_element_by_css_selector('#droppable')
actions = ActionChains(browser)
actions.drag_and_drop(source, target)
actions.perform()

# 執行JavaScript
from selenium import webdriver
browser = webdriver.Chrome()
browser.get("https://www.zhihu.com/explore")
browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')
browser.execute_script('alert("To Bottom")')

# 獲取元素信息
# 獲取屬性
from selenium import webdriver
from selenium.webdriver import ActionChains
browser = webdriver.Chrome()
browser.get("https://www.zhihu.com/explore")
logo = browser.find_element_by_id('zh-top-link-logo')
print(logo)
print(logo.get_attribute('class'))

# 獲取文本值
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.zhihu.com/explore')
input = browser.find_element_by_class_name('zu-top-add-question')
print(input.text)

# 獲取ID、位置、標簽名、大小
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.zhihu.com/explore')
input = browser.find_element_by_class_name('zu-top-add-question')
print(input.id)
print(input.location)
print(input.tag_name)
print(input.size)

# Frame
import time
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
browser = webdriver.Chrome()
browser.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')
browser.switch_to.frame('iframeResult')
source = browser.find_element_by_css_selector('#draggable')
print(source)
try:
  logo = browser.find_element_by_class_name('logo')
except NoSuchElementException:
  print('NO LOGO')
browser.switch_to.parent_frame()
logo = browser.find_element_by_class_name('logo')
print(logo)
print(logo.text)

# 等待
# 隱式等待
# 當使用瞭隱式等待執行測試的時候，如果WebDriver沒有在DOM中找到元素，將繼續等待，超出設定時間後拋出找不到元素的異常，
# 換句話說，當查找元素或元素並沒有立即出現的時候，隱式等待將等待一段時間再查找DOM，默認的時間是0
from selenium import webdriver
browser = webdriver.Chrome()
browser.implicitly_wait(10)
browser.get('https://www.zhihu.com/explore')
input = browser.find_element_by_class_name('zu-top-add-question')
print(input)

# 顯示等待
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
browser = webdriver.Chrome()
browser.get('https://www.taobao.com/')
wait = WebDriverWait(browser, 10)
input = wait.until(EC.presence_of_element_located((By.ID, 'q')))
button = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, '.btn-search')))
print(input, button)

# 前進後退
import time
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.get('https://www.taobao.com')
browser.get('https://www.python.org')
browser.back()
time.sleep(5)
browser.forward()
browser.close()

# Cookies
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.zhihu.com/explore')
print(browser.get_cookies())
browser.add_cookie({'name':'name', 'domain':'www.zhihu.com', 'value':'germey'})
print(browser.get_cookies())
browser.delete_all_cookies()
print(browser.get_cookies())

# 選項卡管理
import time
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.execute_script('window.open()')
print(browser.window_handles)
browser.switch_to_window(browser.window_handles[1])
browser.get('https://www.taobao.com')
time.sleep(5)
browser.switch_to_window(browser.window_handles[0])
browser.get('https://python.org')

# 異常處理
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.find_element_by_id('hello')

from selenium import webdriver
from selenium.common.exceptions import TimeoutException, NoSuchElementException
browser = webdriver.Chrome()
try:
  browser.get('https://www.baidu.com')
except TimeoutException:
  print('Time Out')
try:
  browser.find_element_by_id('hello')
except NoSuchElementException:
  print('No Element')
finally:
  browser.close()