Python实现网页截图

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 = 0self.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, 1370desktop = 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；

'''
遇到问题没人解答？小编创建了一个Python学习交流QQ群：778463939
寻找有志同道合的小伙伴，互帮互助,群里还有不错的视频学习教程和PDF电子书！
'''
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 = 1self.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 -= 1def run_js(self):script = """var scroll = function (dHeight) {var t = document.documentElement.scrollTopvar h = document.documentElement.scrollHeightdHeight = dHeight || 0var current = t + dHeightif (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。

'''
遇到问题没人解答？小编创建了一个Python学习交流QQ群：778463939
寻找有志同道合的小伙伴，互帮互助,群里还有不错的视频学习教程和PDF电子书！
'''
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 = pageself.over_flow_size = over_flow_sizeself.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 = 0total_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.sizeif width > max_width:max_width = widthtotal_height += heightreturn max_width, total_heightdef 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 = 0for img in self.im_list:width, height = img.sizenew_img.paste(img, (x, y))y += heightnew_img.save(self.save_path)print('截图成功:', self.save_path)else:obj = self.im_list[0]width, height = obj.sizeleft, top, right, bottom = 0, 0, width, heightbox = (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.sizeleft, top, right, bottom = 0, height - self.over_flow_size, width, heightbox = (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 -*-
#遇到问题没人解答？小编创建了一个Python学习交流QQ群：778463939
#寻找有志同道合的小伙伴，互帮互助,群里还有不错的视频学习教程和PDF电子书！import sys
from PyQt5.QtCore import *
from PyQt5.QtWidgets import *
from PyQt5.QtWebEngineWidgets import *
from PIL import Image
from pathlib import Pathclass ScreenShotMerge():def __init__(self, page, over_flow_size):self.im_list = []self.page = pageself.over_flow_size = over_flow_sizeself.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 = 0total_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.sizeif width > max_width:max_width = widthtotal_height += heightreturn max_width, total_heightdef 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 = 0for img in self.im_list:width, height = img.sizenew_img.paste(img, (x, y))y += heightnew_img.save(self.save_path)print('截图成功:', self.save_path)else:obj = self.im_list[0]width, height = obj.sizeleft, top, right, bottom = 0, 0, width, heightbox = (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.sizeleft, top, right, bottom = 0, height - self.over_flow_size, width, heightbox = (left, top, right, bottom)region = obj.crop(box)return regionclass MainWindow(QMainWindow):def __init__(self, parent=None):super(MainWindow, self).__init__(parent)self.setWindowTitle('易哈佛')self.temp_height = 0self.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, 1370desktop = 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 = 1self.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 -= 1def run_js(self):script = """var scroll = function (dHeight) {var t = document.documentElement.scrollTopvar h = document.documentElement.scrollHeightdHeight = dHeight || 0var current = t + dHeightif (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_())

Python实现网页截图相关推荐

Python实现网页截图，附带完整代码
Python实现网页截图,附带完整代码在现代化的互联网时代,我们经常需要对网页进行截图以便于保存.共享以及其他种种用途.Python是一种功能强大的编程语言,可以帮助我们轻松地实现网页截图功能.本文 ...
python抓取网页数据并截图_python实现自动网页截图并裁剪图片
本文实例为大家分享了python自动网页截图并裁剪图片的具体代码,供大家参考,具体内容如下代码: # coding=utf-8 import time from selenium import we ...
linux下使用python截图_linux多线程网页截图-python
上一篇中( linux多线程网页截图-shell ),使用shell多进程对大量的网站截图,大大减少了截图的时间.但慢慢的也发现了这种方式的弊端:每个进程分配的网站数量是相等的,有些进程截图较快,有些 ...
python实现网页长截图
python实现网页长截图实现思路使用工具和第三方库参考内容网址具体代码案例实现思路获取到所需内容截图.移动.截图.移动- 拼接使用工具和第三方库 Python.Pycharm PIL ...
Python将网页转化为PDF(python网页自动长截图)
初次实践:python网页自动截图步骤如下: (1) 安装python selenium 库,推荐使用pip快速安装最新版本 pip install selenium (2) 检查Chrome浏览器 ...
网页截图并自动放入word文档【python】
这里写自定义目录标题使用场景准备环境实现逻辑引入包截图模块访问mysql数据库,获取标题和网址截图并保存为word 使用场景从mysql数据库中读取需求标题和对应网页传参,提供网页截图 ...
python获取网页元素坐标_html网页元素在屏幕上的坐标获取
今天在用python调用IE获取html网页元素在屏幕上的坐标,当然为了截图啦,(*^__^*) 嘻嘻-- xtop=ie.document.forms[i].elements[j].getBound ...
实用小技巧---如何给全部网页截图
相信大家在平时学习和工作的时候,都少不了要对网页截图.可是,如果使用一般传统的截图方法:QQ截图或者微信截图,很难做到对一个网页的全部页面截图.如下图: 因为这些截图方法,只能对电脑屏幕现在展示出来的 ...
phantomjs实现免费在线网页截图工具-toolfk程序员在线工具网
本文要推荐的[ToolFk]是一款程序员经常使用的线上免费测试工具箱,ToolFk 特色是专注于程序员日常的开发工具,不用安装任何软件,只要把内容贴上按一个执行按钮,就能获取到想要的内容结果.Tool ...

Python实现网页截图

Python实现网页截图相关推荐

最新文章

热门文章