Python爬虫：selenium模块基本使用

from selenium import webdriver
from selenium.common.exceptions import TimeoutException, NoSuchElementException
import time
# 声明浏览器对象
driver = webdriver.Chrome()
# 可用的浏览器对象：
# Firefox，Chrome，Ie，Edge，Opera，Safari，BlackBerry，PhantomJS，Android
# 访问页面
def foo1():
    driver.get("http://www.baidu.com")
    print(driver.page_source)
    # 查找元素
    try:
        p=driver.find_element_by_class_name("p")
    except NoSuchElementException as e:
        print(e)
    """
    # 单个元素
    find_element_by_id
    find_element_by_name
    find_element_by_xpath
    find_element_by_tag_name
    find_element_by_link_text
    find_element_by_class_name
    find_element_by_css_selector
    find_element_by_partial_link_text
    # 多个元素
    find_elements_by_id
    find_elements_by_name
    find_elements_by_xpath
    find_elements_by_tag_name
    find_elements_by_link_text
    find_elements_by_class_name
    find_elements_by_css_selector
    find_elements_by_partial_link_text
    """
    # 通用查找方式
    from selenium.webdriver.common.by import By
    driver.find_element(By.ID, "kw")
    """
    ID = "id"
    XPATH = "xpath"
    LINK_TEXT = "link text"
    PARTIAL_LINK_TEXT = "partial link text"
    NAME = "name"
    TAG_NAME = "tag name"
    CLASS_NAME = "class name"
    CSS_SELECTOR = "css selector"
    """
# 元素交互
def foo2():
    import time
    driver.get("http://www.baidu.com")
    input = driver.find_element_by_id("kw")
    input.send_keys("淘宝")
    time.sleep(2)
    input.clear()
    input.send_keys("京东")
    button = driver.find_element_by_id("su")
    time.sleep(2)
    button.click()
# 交互动作
# 将动作附加到动作链中串行执行
def foo3():
    driver.get("http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable")
    # 切换到子frame
    driver.switch_to.frame("iframeResult")
    draggable = driver.find_element_by_id("draggable")
    droppable = driver.find_element_by_id("droppable")
    actions = webdriver.ActionChains(driver)
    actions.drag_and_drop(draggable, droppable)
    actions.perform()
    # 切换回父frame
    driver.switch_to.parent_frame()
# 执行javascript
def foo4():
    driver.execute_script('alert("hello")')
# 获取文本和属性
def foo5():
    driver.get("https://www.zhihu.com/topics")
    # 隐式等待
    driver.implicitly_wait(10)
    # 显示等待
    from selenium.webdriver.support import expected_conditions as EC
    from selenium.webdriver.support.ui import WebDriverWait
    from selenium.webdriver.common.by import By
    wait = WebDriverWait(driver, 10)
    logo = wait.until(EC.presence_of_element_located((By.ID, "zh-top-link-logo")))
    print(logo.text)
    # 获取属性, id， 标签名， 位置， 大小
    print(logo.get_attribute("class"))
    print(logo.id)
    print(logo.location)
    print(logo.tag_name)
    print(logo.size)
# 前进后退
def foo6():
    import time
    driver.get("http://www.taobao.com")
    driver.get("http://www.jd.com")
    driver.get("http://www.qq.com")
    time.sleep(2)
    driver.back()
    time.sleep(2)
    driver.forward()
    time.sleep(3)
# cookie
def foo7():
    driver.get("https://www.zhihu.com/explore")
    print(driver.get_cookies())
    driver.add_cookie({"name": "mouday", "value": "mouday.com"})
    print(driver.get_cookies())
    driver.delete_all_cookies()
    print(driver.get_cookies())
# 选项卡管理
def foo8():
    driver.get("https://www.qq.com/")
    # 开启
    driver.execute_script("window.open()")
    print(driver.window_handles)
    # 切换
    driver.switch_to_window(driver.window_handles[1])
    driver.get("https://www.taobao.com/")
    time.sleep(2)
    # 切换
    driver.switch_to_window(driver.window_handles[0])
    driver.get("https://www.jd.com/")
    time.sleep(2)
# 异常处理
def foo9():
    try:
        driver.get("https://www.google.com")
    except TimeoutException as e:
        print(e.msg)
    try:
        p = driver.find_element_by_class_name("p")
    except NoSuchElementException as e:
        print(e)
# 关闭退出浏览器
driver.close()
driver.quit()
# 如果不退出浏览器，会报错：
# ImportError: sys.meta_path is None, Python is likely shutting down