• 图片懒加载
  • selenium
  • phantomJs
  • 谷歌无头浏览器

动态数据加载处理

一.图片懒加载

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
from lxml import etree

if __name__ == "__main__":
     url = 'http://sc.chinaz.com/tupian/gudianmeinvtupian.html'
     headers = {
         'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
     }
     #获取页面文本数据
     response = requests.get(url=url,headers=headers)
     response.encoding = 'utf-8'
     page_text = response.text
     #解析页面数据（获取页面中的图片链接）
     #创建etree对象
     tree = etree.HTML(page_text)
     div_list = tree.xpath('//div[@id="container"]/div')
     #解析获取图片地址和图片的名称
     for div in div_list:
         image_url = div.xpath('.//img/@src')
         image_name = div.xpath('.//img/@alt')
         print(image_url) #打印图片链接
         print(image_name)#打印图片名称
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
from lxml import etree

if __name__ == "__main__":
     url = 'http://sc.chinaz.com/tupian/gudianmeinvtupian.html'
     headers = {
         'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
     }
     #获取页面文本数据
     response = requests.get(url=url,headers=headers)
     response.encoding = 'utf-8'
     page_text = response.text
     #解析页面数据（获取页面中的图片链接）
     #创建etree对象
     tree = etree.HTML(page_text)
     div_list = tree.xpath('//div[@id="container"]/div')
     #解析获取图片地址和图片的名称
     for div in div_list:
         image_url = div.xpath('.//img/@src'2) #src2伪属性
         image_name = div.xpath('.//img/@alt')
         print(image_url) #打印图片链接
         print(image_name)#打印图片名称

二.selenium

http://chromedriver.storage.googleapis.com/index.htmlhttp://blog.csdn.net/huilan_same/article/details/51896672中提供的版本映射表进行对应

               效果展示：

代码介绍：

 

 

三.phantomJs

from selenium import webdriver
import time

# phantomjs路径
path = r'PhantomJS驱动路径'
browser = webdriver.PhantomJS(path)

# 打开百度
url = 'http://www.baidu.com/'
browser.get(url)

time.sleep(3)

browser.save_screenshot(r'phantomjs\baidu.png')

# 查找input输入框
my_input = browser.find_element_by_id('kw')
# 往框里面写文字
my_input.send_keys('美女')
time.sleep(3)
#截屏
browser.save_screenshot(r'phantomjs\meinv.png')

# 查找搜索按钮
button = browser.find_elements_by_class_name('s_btn')[0]
button.click()

time.sleep(3)

browser.save_screenshot(r'phantomjs\show.png')

time.sleep(3)

browser.quit()
from selenium import webdriver
from time import sleep
import time

if __name__ == '__main__':
    url = 'https://movie.douban.com/typerank?type_name=%E6%81%90%E6%80%96&type=20&interval_id=100:90&action='
    # 发起请求前，可以让url表示的页面动态加载出更多的数据
    path = r'C:\Users\Administrator\Desktop\爬虫授课\day05\ziliao\phantomjs-2.1.1-windows\bin\phantomjs.exe'
    # 创建无界面的浏览器对象
    bro = webdriver.PhantomJS(path)
    # 发起url请求
    bro.get(url)
    time.sleep(3)
    # 截图
    bro.save_screenshot('1.png')

    # 执行js代码（让滚动条向下偏移n个像素（作用：动态加载了更多的电影信息））
    js = 'window.scrollTo(0,document.body.scrollHeight)'
    bro.execute_script(js)  # 该函数可以执行一组字符串形式的js代码
    time.sleep(2)

    bro.execute_script(js)  # 该函数可以执行一组字符串形式的js代码
    time.sleep(2)
    bro.save_screenshot('2.png') 
    time.sleep(2) 
    # 使用爬虫程序爬去当前url中的内容 
    html_source = bro.page_source # 该属性可以获取当前浏览器的当前页的源码（html） 
    with open('./source.html', 'w', encoding='utf-8') as fp: 
        fp.write(html_source) 
    bro.quit()

四.谷歌无头浏览器

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import time
 
# 创建一个参数对象，用来控制chrome以无界面模式打开
chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
# 驱动路径
path = r'C:\Users\ZBLi\Desktop\1801\day05\ziliao\chromedriver.exe'
 
# 创建浏览器对象
browser = webdriver.Chrome(executable_path=path, chrome_options=chrome_options)
 
# 上网
url = 'http://www.baidu.com/'
browser.get(url)
time.sleep(3)
 
browser.save_screenshot('baidu.png')
 
browser.quit()