selenium

selenium是一个浏览器驱动模块，支持多种浏览器，主要用于自动化测试。

爬虫中主要用来解决JavaScript渲染的问题。

效果示例：

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("http://www.baidu.com")
    input = browser.find_element_by_id("kw")    # 通过ID找到输入框
    input.send_keys("Python")   # 向输入框输入字符
    input.send_keys(Keys.ENTER)     # 按ENTER键，这个和找到那个搜索元素，然后执行点击操作一样的
    wait = WebDriverWait(browser,10)    # 创建一个wait
    wait.until(EC.presence_of_element_located((By.ID,"content_left")))
    print(browser.current_url)    # 当前页面的url
    print(browser.get_cookies())
    print(browser.page_source)    # 当前页面的源代码
finally:
    browser.close()

查找元素

单个元素：如果想查多个元素就只要在element后面加个s就可以了

from selenium import webdriver

browser = webdriver.Chrome()
browser.get("https://www.taobao.com")
input = browser.find_element_by_id("q")
print(input)
browser.close()

# 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

# 另一种通用方法
from selenium import webdriver

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

元素交互操作：

对获取的元素调用交互方法

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("iPhone")
time.sleep(1)
input.clear()
input.send_keys("iPad")
button = browser.find_element_by_class_name("btn-search")
button.click()

交互动作：

将动作附加到动作链中串行执行

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()

执行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")')

获取元素信息

获取属性

from selenium import webdriver
from selenium.webdriver import ActionChains

browser = webdriver.Chrome()
url = "https://www.zhihu.com/explore"
browser.get(url)
logo = browser.find_element_by_id("zh-top-link-logo")
print(logo)
print(logo.get_attribute("class"))

获取文本值

from selenium import webdriver
browser = webdriver.Chrome()
url = "https://www.zhihu.com/explore"
browser.get(url)
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()
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")
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

隐式等待

选项卡管理

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(1)
browser.switch_to.window(browser.window_handles[0])
browser.get("https://python.org")

参考：https://blog.csdn.net/ccggaag/article/details/76652274