python + selenium==2.48.0 + PhantomJS 网页截图

文章目录

• 1. 前置条件
• 2. 上脚本
• 3. 上结果

1. 前置条件

• win10, python 3.6
• 下载PhantomJS, 下载地址
• 下载解压完成后, 放入一个你喜欢的目录(意思就是放哪儿都行), 但要记得你放哪儿了, 一会儿要用
• 我的就放这儿了

  

2. 上脚本

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
'''
@File    :   screen_shot.py
@Time    :   2020/01/01 09:28:03
@Author  :   zhugelaoliu
@Version :   1.0
@Desc    :   网页截图
'''
import os
from selenium import webdriver
# 此处 selenium==2.48.0 版本的, 最新版本不支持PhantomJS
import arrow
from PIL import Image


class ScreenShot():
    def __init__(self, url, picname, **kwargs):
        self.url = url
        self.picname = picname + '.png'
        self.base_dir = os.path.dirname(
            os.path.dirname(os.path.dirname(__file__)))
        # 前置条件中提到的要用到的PhantomJS地址
        self.driver = webdriver.PhantomJS(
            executable_path=r'D:/Anaconda3/envs/py36/Scripts/phantomjs-2.1.1-windows/bin/phantomjs.exe')
        # 以下为另一种解决方案(未使用)
        # self.chrome_options = webdriver.ChromeOptions()
        # self.chrome_options.add_argument("--headless")
        # self.chrome_options.add_argument('--disable-gpu')
        # self.driver = webdriver.Chrome(chrome_options=self.chrome_options,
        #     executable_path=r'D:/Anaconda3/envs/py36/Scripts/chromedriver_win32/chromedriver.exe')
        # end
        self.now = arrow.now('local')
        self.month = self.now.format('YYYYMM')
        self.today = self.now.format('YYYYMMDD')
        self.new_picname = '_'.join([self.today, self.picname])
        self.screen_shot_dir = os.path.join(
            self.base_dir, f'report_images/{self.month}/{self.today}')
        if not os.path.exists(self.screen_shot_dir):
            os.makedirs(self.screen_shot_dir)
        self.screen_shot_image = os.path.join(
            self.screen_shot_dir, self.new_picname)

    @property
    def getImage(self):
        '''
        截取全屏,并保存在images文件夹
        :return: 无
        '''
        self.driver.get(self.url)
        self.driver.maximize_window()
        self.driver.save_screenshot(self.screen_shot_image)
        self.driver.close()
        return self.screen_shot_image

    def getElementImage(self, element):
        """
        截图,指定元素图片
        :param element: 元素对象
        :return: 无
        """
        print(f'正在打开 {self.url} ---> ', end='')
        self.driver.get(self.url)
        self.driver.maximize_window()
        element_obj = self.driver.find_element_by_class_name(element)
        # 备用的查找元素方式
        # element_obj = self.driver.find_element_by_id(element)
        print(f'ok, 正在截屏 ---> ', end='')
        self.driver.save_screenshot(self.screen_shot_image)
        left = element_obj.location['x']
        top = element_obj.location['y']
        elementWidth = left + element_obj.size['width']
        elementHeight = top + element_obj.size['height']
        picture = Image.open(self.screen_shot_image)
        picture = picture.crop((left, top, elementWidth, elementHeight))
        picture.save(self.screen_shot_image)
        self.driver.close()
        print(f'Done',)
        return self.screen_shot_image


def main():
    url = 'https://www.csdn.net/'
    picname = 'csdn'
    obj = ScreenShot(url, picname)
    image = obj.getElementImage('clearfix')

if __name__ == "__main__":
    main()
           

3. 上结果