Python爬虫selenium模块

pip install selenium

pip install "selenium < 3"

from selenium import webdriver
from bs4 import BeautifulSoup
import time
# 显示等待页面加载
def getPage1():
    url = "http://www.pythonscraping.com/pages/javascript/ajaxDemo.html"
    driver = webdriver.PhantomJS()
    driver.get(url)
    time.sleep(1)  # 设置等待时间
    # 获取内容
    content = driver.find_element_by_id("content")
    print(content.text)
    # 通过bs解析
    html = driver.page_source  # 源代码字符串
    soup = BeautifulSoup(html, "html.parser")
    tag = soup.find(id="content")
    print(tag)
    driver.close()
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
# 隐式等待页面加载
def getPage2():
    url = "http://www.pythonscraping.com/pages/javascript/ajaxDemo.html"
    driver = webdriver.PhantomJS(executable_path="phantomjs")
    driver.get(url)
    # 等待页面加载完毕，获取明显元素作为标志
    try:
        element = WebDriverWait(driver, 10).until(
            EC.presence_of_element_located((By.ID, "loadedButton"))
        )
    finally:
        # 获取内容
        content = driver.find_element_by_id("content")
        print(content.text)
        driver.close()
getPage2()

# -*- coding:utf-8 -*-
from selenium import webdriver
import time
def clickBaidu():
    # 为了看到效果，使用chrome浏览器
    driver = webdriver.Chrome()
    time.sleep(5)
    baidu = "http:www.baidu.com"
    driver.get(baidu)
    time.sleep(5)
    driver.find_element_by_id("kw").send_keys("百度")
    time.sleep(5)
    driver.find_element_by_id("su").click()
    time.sleep(5)
    # 截屏
    driver.get_screenshot_as_file("baidu_shot.png")
    time.sleep(5)
    driver.close()
clickBaidu()
# 说明，time.sleep() 是为了看到浏览器整个自动过程，实际使用可以去掉

element.click()
element.click_and_hold()
element.release()
element.double_click()