Python实现网页截图(PyQT5)过程解析


Posted in Python onAugust 12, 2019

方案说明

功能要求:实现网页加载后将页面截取成长图片

涉及模块:PyQT5 PIL

逻辑说明:

1:完成窗口设置,利用PyQT5 QWebEngineView加载网页地址,待网页加载完成后,调用check_pag;

class MainWindow(QMainWindow):
  def __init__(self, parent=None):
    super(MainWindow, self).__init__(parent)
    self.setWindowTitle('易哈佛')
    self.temp_height = 0
    self.setWindowFlag(Qt.WindowMinMaxButtonsHint, False) # 禁用最大化,最小化
    # self.setWindowFlag(Qt.WindowStaysOnTopHint, True) # 窗口顶置
    self.setWindowFlag(Qt.FramelessWindowHint, True) # 窗口无边框
  def urlScreenShot(self, url):
    self.browser = QWebEngineView()
    self.browser.load(QUrl(url))
    geometry = self.chose_screen()
    self.setGeometry(geometry)
    self.browser.loadFinished.connect(self.check_page)
    self.setCentralWidget(self.browser)
  def get_page_size(self):
    size = self.browser.page().contentsSize()
    self.set_height = size.height()
    self.set_width = size.width()
    return size.width(), size.height()
  def chose_screen(self):
    width, height = 750, 1370
    desktop = QApplication.desktop()
    screen_count = desktop.screenCount()
    for i in range(0, screen_count):
      rect = desktop.availableGeometry(i)
      s_width, s_height = rect.width(), rect.height()
      if s_width > width and s_height > height:
        return QRect(rect.left(), rect.top(), width, height)
    return QRect(0, 0, width, height)
if __name__ == '__main__':
  app = QApplication(sys.argv)
  win = MainWindow()
  win.show()
  app.exit(app.exec_())

2:收集页面高度,并计算分次截屏的次数和余量高度;实例化图片合并工具,设置定时器,超时信号发出后,执行exe_command;

def check_page(self):
    p_width, p_height = self.get_page_size()
    self.page, self.over_flow_size = divmod(p_height, self.height())
    if self.page == 0:
      self.page = 1
    self.ssm = ScreenShotMerge(self.page, self.over_flow_size)
    self.timer = QTimer(self)
    self.timer.timeout.connect(self.exe_command)
    self.timer.setInterval(400)
    self.timer.start()

3:exe_command用来控制截图次数,并在每次截图完成后控制网页向下滑屏幕的高度;所有的页面都已截取时,完成图片合并。

def exe_command(self):
    if self.page > 0:
      self.screen_shot()
      self.run_js()
    elif self.page < 0:
      self.timer.stop()
      self.ssm.image_merge()
      self.close()
    elif self.over_flow_size > 0:
      self.screen_shot()
    self.page -= 1    
  def run_js(self):
    script = """
      var scroll = function (dHeight) {
      var t = document.documentElement.scrollTop
      var h = document.documentElement.scrollHeight
      dHeight = dHeight || 0
      var current = t + dHeight
      if (current > h) {
        window.scrollTo(0, document.documentElement.clientHeight)
       } else {
        window.scrollTo(0, current)
       }
      }
    """
    command = script + '\n scroll({})'.format(self.height())
    self.browser.page().runJavaScript(command)

4:screen_shot在每次截图完成后将图片保存,并将图片对象由图片合并根据保存到列表中。

def screen_shot(self):
    screen = QApplication.primaryScreen()
    winid = self.browser.winId()
    pix = screen.grabWindow(int(winid))
    name = '{}/temp.png'.format(self.ssm.root_path)
    pix.save(name)
    self.ssm.add_im(name)

5:截图合并工具,在每次截图完成后将图片对象保存,完成余量截图的重绘和截图的合并。

class ScreenShotMerge():
  def __init__(self, page, over_flow_size):
    self.im_list = []
    self.page = page
    self.over_flow_size = over_flow_size
    self.get_path()

  def get_path(self):
    self.root_path = Path(__file__).parent.joinpath('temp')
    if not self.root_path.exists():
      self.root_path.mkdir(parents=True)
    self.save_path = self.root_path.joinpath('merge.png')

  def add_im(self, path):
    if len(self.im_list) == self.page:
      im = self.reedit_image(path)
    else:
      im = Image.open(path)
    im.save('{}/{}.png'.format(self.root_path, len(self.im_list) + 1))
    self.im_list.append(im)

  def get_new_size(self):
    max_width = 0
    total_height = 0
    # 计算合成后图片的宽度(以最宽的为准)和高度
    for img in self.im_list:
      width, height = img.size
      if width > max_width:
        max_width = width
      total_height += height
    return max_width, total_height

  def image_merge(self, ):
    if len(self.im_list) > 1:
      max_width, total_height = self.get_new_size()
      # 产生一张空白图
      new_img = Image.new('RGB', (max_width - 15, total_height), 255)
      x = y = 0
      for img in self.im_list:
        width, height = img.size
        new_img.paste(img, (x, y))
        y += height
      new_img.save(self.save_path)
      print('截图成功:', self.save_path)
    else:
      obj = self.im_list[0]
      width, height = obj.size
      left, top, right, bottom = 0, 0, width, height
      box = (left, top, right, bottom)
      region = obj.crop(box)
      new_img = Image.new('RGB', (width, height), 255)
      new_img.paste(region, box)
      new_img.save(self.save_path)
      print('截图成功:', self.save_path)

  def reedit_image(self, path):
    obj = Image.open(path)
    width, height = obj.size
    left, top, right, bottom = 0, height - self.over_flow_size, width, height
    box = (left, top, right, bottom)
    region = obj.crop(box)
    return region

截图功能完整代码

#!/usr/bin/env python
# -*- coding:UTF-8 -*-
# Author:Leslie-x
import sys
from PyQt5.QtCore import *
from PyQt5.QtWidgets import *
from PyQt5.QtWebEngineWidgets import *
from PIL import Image
from pathlib import Path
class ScreenShotMerge():
  def __init__(self, page, over_flow_size):
    self.im_list = []
    self.page = page
    self.over_flow_size = over_flow_size
    self.get_path()
  def get_path(self):
    self.root_path = Path(__file__).parent.joinpath('temp')
    if not self.root_path.exists():
      self.root_path.mkdir(parents=True)
    self.save_path = self.root_path.joinpath('merge.png')
  def add_im(self, path):
    if len(self.im_list) == self.page:
      im = self.reedit_image(path)
    else:
      im = Image.open(path)
    im.save('{}/{}.png'.format(self.root_path, len(self.im_list) + 1))
    self.im_list.append(im)
  def get_new_size(self):
    max_width = 0
    total_height = 0
    # 计算合成后图片的宽度(以最宽的为准)和高度
    for img in self.im_list:
      width, height = img.size
      if width > max_width:
        max_width = width
      total_height += height
    return max_width, total_height
  def image_merge(self, ):
    if len(self.im_list) > 1:
      max_width, total_height = self.get_new_size()
      # 产生一张空白图
      new_img = Image.new('RGB', (max_width - 15, total_height), 255)
      x = y = 0
      for img in self.im_list:
        width, height = img.size
        new_img.paste(img, (x, y))
        y += height
      new_img.save(self.save_path)
      print('截图成功:', self.save_path)
    else:
      obj = self.im_list[0]
      width, height = obj.size
      left, top, right, bottom = 0, 0, width, height
      box = (left, top, right, bottom)
      region = obj.crop(box)
      new_img = Image.new('RGB', (width, height), 255)
      new_img.paste(region, box)
      new_img.save(self.save_path)
      print('截图成功:', self.save_path)
  def reedit_image(self, path):
    obj = Image.open(path)
    width, height = obj.size
    left, top, right, bottom = 0, height - self.over_flow_size, width, height
    box = (left, top, right, bottom)
    region = obj.crop(box)
    return region
class MainWindow(QMainWindow):
  def __init__(self, parent=None):
    super(MainWindow, self).__init__(parent)
    self.setWindowTitle('易哈佛')
    self.temp_height = 0
    self.setWindowFlag(Qt.WindowMinMaxButtonsHint, False) # 禁用最大化,最小化
    # self.setWindowFlag(Qt.WindowStaysOnTopHint, True) # 窗口顶置
    self.setWindowFlag(Qt.FramelessWindowHint, True) # 窗口无边框
  def urlScreenShot(self, url):
    self.browser = QWebEngineView()
    self.browser.load(QUrl(url))
    geometry = self.chose_screen()
    self.setGeometry(geometry)
    self.browser.loadFinished.connect(self.check_page)
    self.setCentralWidget(self.browser)
  def get_page_size(self):
    size = self.browser.page().contentsSize()
    self.set_height = size.height()
    self.set_width = size.width()
    return size.width(), size.height()
  def chose_screen(self):
    width, height = 750, 1370
    desktop = QApplication.desktop()
    screen_count = desktop.screenCount()
    for i in range(0, screen_count):
      rect = desktop.availableGeometry(i)
      s_width, s_height = rect.width(), rect.height()
      if s_width > width and s_height > height:
        return QRect(rect.left(), rect.top(), width, height)
    return QRect(0, 0, width, height)
  def check_page(self):
    p_width, p_height = self.get_page_size()
    self.page, self.over_flow_size = divmod(p_height, self.height())
    if self.page == 0:
      self.page = 1
    self.ssm = ScreenShotMerge(self.page, self.over_flow_size)
    self.timer = QTimer(self)
    self.timer.timeout.connect(self.exe_command)
    self.timer.setInterval(400)
    self.timer.start()
  def exe_command(self):
    if self.page > 0:
      self.screen_shot()
      self.run_js()

    elif self.page < 0:
      self.timer.stop()
      self.ssm.image_merge()
      self.close()

    elif self.over_flow_size > 0:
      self.screen_shot()
    self.page -= 1

  def run_js(self):
    script = """
      var scroll = function (dHeight) {
      var t = document.documentElement.scrollTop
      var h = document.documentElement.scrollHeight
      dHeight = dHeight || 0
      var current = t + dHeight
      if (current > h) {
        window.scrollTo(0, document.documentElement.clientHeight)
       } else {
        window.scrollTo(0, current)
       }
      }
    """
    command = script + '\n scroll({})'.format(self.height())
    self.browser.page().runJavaScript(command)

  def screen_shot(self):
    screen = QApplication.primaryScreen()
    winid = self.browser.winId()
    pix = screen.grabWindow(int(winid))
    name = '{}/temp.png'.format(self.ssm.root_path)
    pix.save(name)
    self.ssm.add_im(name)

if __name__ == '__main__':
  url = 'http://blog.sina.com.cn/lm/rank/focusbang//'
  app = QApplication(sys.argv)
  win = MainWindow()
  win.urlScreenShot(url)
  win.show()
  app.exit(app.exec_())

以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持三水点靠木。

Python 相关文章推荐
使用Python脚本生成随机IP的简单方法
Jul 30 Python
Python使用wxPython实现计算器
Jan 30 Python
Python模拟随机游走图形效果示例
Feb 06 Python
机器学习之KNN算法原理及Python实现方法详解
Jul 09 Python
Django 对象关系映射(ORM)源码详解
Aug 06 Python
python中return的返回和执行实例
Dec 24 Python
python实现高斯投影正反算方式
Jan 17 Python
关于python 跨域处理方式详解
Mar 28 Python
Python使用monkey.patch_all()解决协程阻塞问题
Apr 15 Python
彻底解决Python包下载慢问题
Nov 15 Python
flask项目集成swagger的方法
Dec 09 Python
python 字典和列表嵌套用法详解
Jun 29 Python
python实现知乎高颜值图片爬取
Aug 12 #Python
python3 enum模块的应用实例详解
Aug 12 #Python
Python一键查找iOS项目中未使用的图片、音频、视频资源
Aug 12 #Python
django+echart数据动态显示的例子
Aug 12 #Python
Flask框架学习笔记之使用Flask实现表单开发详解
Aug 12 #Python
Flask框架学习笔记之表单基础介绍与表单提交方式
Aug 12 #Python
python内存管理机制原理详解
Aug 12 #Python
You might like
制作美丽的拉花
2021/03/03 冲泡冲煮
php中支持多种编码的中文字符串截取函数!
2007/03/20 PHP
11个PHPer必须要了解的编程规范
2014/09/22 PHP
php新浪微博登录接口用法实例
2014/12/23 PHP
ThinkPHP路由详解
2015/07/27 PHP
php变量与字符串的增删改查操作示例
2020/05/07 PHP
JavaScript中的一些定位属性[图解]
2010/07/14 Javascript
javascript string字符串优化问题
2011/07/31 Javascript
圣诞节Merry Christmas给博客添加浪漫的下雪效果基于jquery实现
2012/12/27 Javascript
javaScript实现浮点数转十六进制字符
2013/10/29 Javascript
JS模拟键盘打字效果的方法
2015/08/05 Javascript
JQuery标签页效果的两个实例讲解(4)
2015/09/17 Javascript
JavaScript+html5 canvas实现图片破碎重组动画特效
2016/02/22 Javascript
分享js粘帖屏幕截图到web页面插件screenshot-paste
2020/08/21 Javascript
jQuery实现鼠标经过时高亮,同时其他同级元素变暗的效果
2016/09/18 Javascript
jQuery实现的简单动态添加、删除表格功能示例
2017/09/21 jQuery
element-ui 表格数据时间格式化的方法
2018/08/24 Javascript
在Vue项目中引入JQuery-ui插件的讲解
2019/01/27 jQuery
Javascript组合继承方法代码实例解析
2020/04/02 Javascript
小程序实现背景音乐播放和暂停
2020/06/19 Javascript
[54:19]完美世界DOTA2联赛PWL S2 Magma vs PXG 第二场 11.28
2020/12/01 DOTA
Python linecache.getline()读取文件中特定一行的脚本
2008/09/06 Python
跟老齐学Python之编写类之三子类
2014/10/11 Python
Python用GET方法上传文件
2015/03/10 Python
Python的Django框架中自定义模版标签的示例
2015/07/20 Python
Python实现在某个数组中查找一个值的算法示例
2018/06/27 Python
python简单验证码识别的实现方法
2019/05/10 Python
关于tensorflow的几种参数初始化方法小结
2020/01/04 Python
Python3 pickle对象串行化代码实例解析
2020/03/23 Python
python中time tzset()函数实例用法
2021/02/18 Python
石油工程专业毕业生求职信
2014/04/13 职场文书
商场开业庆典策划方案
2014/06/02 职场文书
小学兴趣小组活动总结
2014/07/07 职场文书
《检阅》教学反思
2016/02/22 职场文书
2019销售早会主持词
2019/06/27 职场文书
如何使用Maxwell实时同步mysql数据
2021/04/08 MySQL