Python之selenium库

本篇仅作为代码记录

要使用selenium必须装浏览器驱动，下载一个驱动包，解压放在python的script目录即可

#!/usr/bin/python
# -*- coding: UTF-8 -*-    
# Author: RuiMing Lin
# DateTime: 2021/01/26 15:06
# Description:
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
from selenium.webdriver import ActionChains
from selenium.common.exceptions import NoSuchElementException
import time

# 声明浏览器,运行后会打开浏览器，显示一个空白页
flag = False
# flag = True
if flag:
    browser = webdriver.Chrome()
    # browser = webdriver.Firefox()
    # browser = webdriver.Edge()
    # browser = webdriver.PhantomJS()
    # browser = webdriver.Safari()

# 通过get()访问页面
flag = False
# flag = True
if flag:
    browser = webdriver.Chrome()
    browser.get('https://www.taobao.com')
    print(browser.page_source)  # 输出源代码
    browser.close()

'''
查找节点：
find_element_by_id
find_element_by_name
find_element_by_xpath
find_element_by_link_text
find_element_by_partial_link_text
find_element_by_tag_name
find_element_by_class_name
find_element_by_css_selector
'''
flag = False
# flag = True
if flag:
    browser = webdriver.Chrome()
    browser.get('https://www.taobao.com')
    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"]')
    input_forth = browser.find_element(By.ID, 'q')
    print(input_first)
    print(input_second)
    print(input_third)
    print(input_forth)
    browser.close()

'''
多个节点
find_elements_by_id
find_elements_by_name
find_elements_by_xpath
find_elements_by_link_text
find_elements_by_partial_link_text
find_elements_by_tag_name
find_elements_by_class_name
find_elements_by_css_selector
'''
flag = False
# flag = True
if flag:
    browser = webdriver.Chrome()
    browser.get('https://www.taobao.com')
    lis = browser.find_elements_by_css_selector('.service-bd li')
    print(len(lis))
    browser.close()

# 节点交互
# send_keys()：输入文字
# clear()：清空文字
# click()：点击按钮
flag = False
# flag = True
if flag:
    browser = webdriver.Chrome()
    browser.get('https://www.taobao.com')
    input = browser.find_element_by_id('q')
    input.send_keys('iPhone')
    time.sleep(1)
    input.clear()
    input.send_keys('iPad')
    button = browser.find_element_by_class_name('btn-search')
    button.click()

# 动作链
flag = False
# flag = True
if flag:
    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()

# 执行JavaScript
flag = False
# flag = True
if flag:
    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")')

# 获得属性
flag = False
# flag = True
if flag:
    browser = webdriver.Chrome()
    url = 'https://www.zhihu.com/explore'
    browser.get(url)
    logo = browser.find_element_by_class_name('ZhihuLogoLink')
    print(logo)
    print(logo.get_attribute('href'))
    browser.close()

# 获得文本值
flag = False
# flag = True
if flag:
    browser = webdriver.Chrome()
    url = 'https://www.zhihu.com/explore'
    browser.get(url)
    input = browser.find_element_by_class_name('ExploreHomePage-ContentSection-header')
    input = input.find_element_by_tag_name('span')
    print(input.text)
    print(input.id)
    print(input.location)
    print(input.tag_name)
    print(input.size)
    browser.close()

# 切换frame
flag = False
# flag = True
if flag:
    browser = webdriver.Chrome()
    url = 'http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable'
    browser.get(url)
    browser.switch_to.frame('iframeResult')
    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)

# 延时等待 -- 隐式等待
flag = False
# flag = True
if flag:
    browser = webdriver.Chrome()
    browser.implicitly_wait(10)
    browser.get('https://www.zhihu.com/explore')
    input = browser.find_element_by_class_name('ExploreHomePage-ContentSection-header')
    print(input)

# 延时等待 -- 显式等待
'''
隐式等待的效果其实并没有那么好，因为我们只规定了一个固定时间，而页面的加载时间会受到网络条件的影响。
这里还有一种更合适的显式等待方法，它指定要查找的节点，然后指定一个最长等待时间。如果在规定时间内加载出来了这个节点，就返回查找的节点；如果到了规定时间依然没有加载出该节点，则抛出超时异常。
'''
flag = False
# flag = True
if flag:
    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)

# forward & backward
flag = False
# flag = True
if flag:
    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(1)
    browser.forward()
    browser.close()

# 添加cookies
flag = False
# flag = True
if flag:
    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())

# 选项卡管理
flag = False
# flag = True
if flag:
    browser = webdriver.Chrome()
    browser.get('https://www.baidu.com')
    browser.execute_script('window.open()') # 执行脚本，开启新的选项卡
    browser.switch_to_window(browser.window_handles[1]) # 切换选项卡
    browser.get('https://www.taobao.com')
    time.sleep(1)
    browser.switch_to_window(browser.window_handles[0])
    browser.get('https://python.org')

# 异常处理
flag = False
# flag = True
if flag:
    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()