前言:
最近,项目中遇到了一个关于实现通过给定URL,实现对网页屏幕进行截图的一个功能,前面代码中已经用python的第三方库实现了截图功能,但在上线以后出现了一些bug,所以就改bug的任务就落在了我的头上,这方面前面没有接触过,正好利用这个机会学习一下python中各种截图方法,下面就是我要介绍的一些常用截图功能的基本使用,希望可以帮到你,也可以提出文中不足的地方。
PIL和Pillow
PIL:Python Imaging Library,已经是Python平台事实上的图像处理标准库了。PIL功能非常强大,但API却非常简单易用,不过只支持到Python 2.7
Pillow:是PIL的一个派生分支,但如今已经发展成为比PIL本身更具活力的图像处理库。目前最新版本是3.0.0
1、安装
在Debian/Ubuntu Linux下直接通过apt安装:
$ sudo apt-get install python-imaging
Mac和其他版本的Linux可以直接使用easy_install或pip安装,安装前需要把编译环境装好:
$ sudo easy_install PIL
Windows平台就去PIL官方网站下载exe安装包或pip
$ pip install pillow
2、实现屏幕截图
from PIL import ImageGrab im = ImageGrab.grab() im.save("1.png") #定义保存的路径和保存的图片格式
PyQt4
PyQt是一个创建GUI应用程序的工具包。它是Python编程语言和Qt库的成功融合。Qt库是目前最强大的库之一。PyQt是由Phil Thompson 开发。PyQt是Qt库的Python版本。PyQt3支持Qt1到Qt3。 PyQt4支持Qt4。它的首次发布也是在1998年,但是当时它叫 PyKDE,因为开始的时候SIP和PyQt没有分开。PyQt是用SIP写的。PyQt 提供 GPL版和商业版。
1、安装
windows下:
32位: http://sourceforge.net/projects/pyqt/files/PyQt4/PyQt-4.11.4/PyQt4-4.11.4-gpl-Py2.7-Qt4.8.7-x32.exe 64位: http://sourceforge.net/projects/pyqt/files/PyQt4/PyQt-4.11.4/PyQt4-4.11.4-gpl-Py2.7-Qt4.8.7-x64.exe
linux下:
https://www.riverbankcomputing.com/software/pyqt/download
2、实现网页截图
有些图片较多,或是页面较长的网站,截出来的图,会出现图片未加载完毕或页面截取不完整等情况,找了很多资料也没解决,如果那个小伙伴会的话,可以教一下我
#!/usr/bin/env python # -*- coding:utf-8 -*- import sys,time import os.path from PyQt4 import QtGui, QtCore, QtWebKit class PageShotter(QtGui.QWidget): def __init__(self, url, parent=None): QtGui.QWidget.__init__(self, parent) self.url = url def shot(self): webView = QtWebKit.QWebView(self) webView.load(QtCore.QUrl(self.url)) self.webPage = webView.page() self.connect(webView, QtCore.SIGNAL("loadFinished(bool)"), self.savePage) def savePage(self, finished): if finished: print "开始截图!" size = self.webPage.mainFrame().contentsSize() print "页面宽:%d,页面高:%d" % (size.width(), size.height()) self.webPage.setViewportSize(QtCore.QSize(size.width() + 16, size.height())) img = QtGui.QImage(size, QtGui.QImage.Format_ARGB32) painter = QtGui.QPainter(img) self.webPage.mainFrame().render(painter) painter.end() fileName = "shot.png" if img.save(fileName): filePath = os.path.join(os.path.dirname(__file__), fileName) print "截图完毕:%s" % filePath else: print "截图失败" else: print "网页加载失败!" self.close() if __name__ == "__main__": app = QtGui.QApplication(sys.argv) shotter = PageShotter("https://www.jd.com/") shotter.shot() sys.exit(app.exec_())
加强版
#!/usr/bin/python # coding:utf-8 import sys import os.path import requests import urlparse import time sys.path.append('../') from PyQt4 import QtGui, QtCore, QtWebKit from PyQt4.QtNetwork import QNetworkRequest class WebStatus(object): def __init__(self, timeout, tries): ''' 类说明:获取网页的状态码。如200表示“网页正常,可访问” 参数:timeout(s) 请求等待时间;tries 请求次数; ''' self.__timeout = timeout self.__tries = tries self.__headers = { "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8", "Accept-Language": "en-US,en;q=0.5", "Accept-Encoding": "gzip, deflate", "User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Firefox/45.0" } def clear_url(self, url): if not url: return None if ',' in url: url = url.split(',')[0] url = url.strip() if url.startswith('http://') or url.startswith('https://'): pass else: url = 'http://' + url try: parse = urlparse.urlparse(url) url_new = parse.scheme + '://' + parse.netloc except: url_new = url if url_new.endswith('.'): url_new = url_new.rstrip('.') return url_new def isAccessible(self, url): ''' 说明:获取网页状态码,判断该网页是否可正常访问的,200表示网页可正常访问的。 参数:url 网址; 返回: True:状态码200,网页正常可访问; False:网页状态码非200,或者请求异常。 ''' url = self.clear_url(url) tries = self.__tries status = False r = None while tries > 0: try: r = requests.get(url=url, headers=self.__headers, timeout=self.__timeout) except: tries -= 1 status = False else: if r.status_code == 200: status = url break finally: if r: r.close() r = None return status def __del__(self): pass class PageShotter(QtGui.QWidget): def __init__(self, url, parent=None,pic_path = './pic_path'): path = os.path.exists(pic_path) if not path: os.mkdir(pic_path) self.request = QNetworkRequest() QtGui.QWidget.__init__(self, parent) self.url = url self.dir_path = os.path.join(pic_path,str(time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))) + '_' + urlparse.urlparse(self.url).netloc + '.png') def shot(self): webView = QtWebKit.QWebView(self) self.request.setRawHeader("User-Agent", "Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Firefox/45.0") webView.load(QtCore.QUrl(self.url)) self.webPage = webView.page() self.connect(webView, QtCore.SIGNAL("loadFinished(bool)"), self.savePage) return self.dir_path def savePage(self, finished): if finished: size = self.webPage.mainFrame().contentsSize() self.webPage.setViewportSize(QtCore.QSize(size.width() + 16, size.height())) img = QtGui.QImage(size, QtGui.QImage.Format_ARGB32) painter = QtGui.QPainter(img) self.webPage.mainFrame().render(painter) painter.end() if img.save(self.dir_path): filePath = os.path.join(os.path.dirname(__file__),self.dir_path) #print "截图完毕:%s" % filePath else: print "截图失败" else: print "网页加载失败!" self.close() if __name__ == "__main__": obj1 = WebStatus(10, 2) status = obj1.isAccessible("https://www.jd.com") if status: app = QtGui.QApplication(sys.argv) shotter = PageShotter(status,pic_path = './dirpath_test') obj = shotter.shot() print obj sys.exit(app.exec_()) else: print 'Invalid URL'
selenium +phantomjs
安装请参考 http://www.cnblogs.com/luxiaojun/p/6144748.html
from selenium import webdriver from selenium.webdriver.common.desired_capabilities import DesiredCapabilities dcap = dict(DesiredCapabilities.PHANTOMJS) #设置userAgent dcap["phantomjs.page.settings.userAgent"] = ("Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:25.0) Gecko/20100101 Firefox/25.0 ") obj = webdriver.PhantomJS(executable_path='C:\Python27\Scripts\phantomjs.exe',desired_capabilities=dcap) #加载网址 obj.get('http://wap.95533pc.com')#打开网址 obj.save_screenshot("1.png") #截图保存 obj.quit()
另外还有利用subprocess中的popen方法指令linux命令进行截图的方法,如 cutycapt,会在以后的文章中继续写到,同样也可以参考以下文章:
http://www.111cn.net/sys/linux/81361.htm