如何用Python截取网站的截图/图像？

Question

我想要实现的是用Python从任何网站获取一个网页截图。

环境：Linux

Answer 1

这是我通过各种渠道找到的解决方案。它可以完整地捕捉网页的屏幕，并且可以选择性地裁剪这个屏幕，还能从裁剪后的图片生成缩略图。以下是需要的步骤：

需求：

安装 NodeJS
使用 Node 的包管理器安装 phantomjs：npm -g install phantomjs
安装 selenium（如果你在使用虚拟环境的话）
安装 imageMagick
将 phantomjs 添加到系统路径（在 Windows 上）

import os
from subprocess import Popen, PIPE
from selenium import webdriver

abspath = lambda *p: os.path.abspath(os.path.join(*p))
ROOT = abspath(os.path.dirname(__file__))


def execute_command(command):
    result = Popen(command, shell=True, stdout=PIPE).stdout.read()
    if len(result) > 0 and not result.isspace():
        raise Exception(result)


def do_screen_capturing(url, screen_path, width, height):
    print "Capturing screen.."
    driver = webdriver.PhantomJS()
    # it save service log file in same directory
    # if you want to have log file stored else where
    # initialize the webdriver.PhantomJS() as
    # driver = webdriver.PhantomJS(service_log_path='/var/log/phantomjs/ghostdriver.log')
    driver.set_script_timeout(30)
    if width and height:
        driver.set_window_size(width, height)
    driver.get(url)
    driver.save_screenshot(screen_path)


def do_crop(params):
    print "Croping captured image.."
    command = [
        'convert',
        params['screen_path'],
        '-crop', '%sx%s+0+0' % (params['width'], params['height']),
        params['crop_path']
    ]
    execute_command(' '.join(command))


def do_thumbnail(params):
    print "Generating thumbnail from croped captured image.."
    command = [
        'convert',
        params['crop_path'],
        '-filter', 'Lanczos',
        '-thumbnail', '%sx%s' % (params['width'], params['height']),
        params['thumbnail_path']
    ]
    execute_command(' '.join(command))


def get_screen_shot(**kwargs):
    url = kwargs['url']
    width = int(kwargs.get('width', 1024)) # screen width to capture
    height = int(kwargs.get('height', 768)) # screen height to capture
    filename = kwargs.get('filename', 'screen.png') # file name e.g. screen.png
    path = kwargs.get('path', ROOT) # directory path to store screen

    crop = kwargs.get('crop', False) # crop the captured screen
    crop_width = int(kwargs.get('crop_width', width)) # the width of crop screen
    crop_height = int(kwargs.get('crop_height', height)) # the height of crop screen
    crop_replace = kwargs.get('crop_replace', False) # does crop image replace original screen capture?

    thumbnail = kwargs.get('thumbnail', False) # generate thumbnail from screen, requires crop=True
    thumbnail_width = int(kwargs.get('thumbnail_width', width)) # the width of thumbnail
    thumbnail_height = int(kwargs.get('thumbnail_height', height)) # the height of thumbnail
    thumbnail_replace = kwargs.get('thumbnail_replace', False) # does thumbnail image replace crop image?

    screen_path = abspath(path, filename)
    crop_path = thumbnail_path = screen_path

    if thumbnail and not crop:
        raise Exception, 'Thumnail generation requires crop image, set crop=True'

    do_screen_capturing(url, screen_path, width, height)

    if crop:
        if not crop_replace:
            crop_path = abspath(path, 'crop_'+filename)
        params = {
            'width': crop_width, 'height': crop_height,
            'crop_path': crop_path, 'screen_path': screen_path}
        do_crop(params)

        if thumbnail:
            if not thumbnail_replace:
                thumbnail_path = abspath(path, 'thumbnail_'+filename)
            params = {
                'width': thumbnail_width, 'height': thumbnail_height,
                'thumbnail_path': thumbnail_path, 'crop_path': crop_path}
            do_thumbnail(params)
    return screen_path, crop_path, thumbnail_path


if __name__ == '__main__':
    '''
        Requirements:
        Install NodeJS
        Using Node's package manager install phantomjs: npm -g install phantomjs
        install selenium (in your virtualenv, if you are using that)
        install imageMagick
        add phantomjs to system path (on windows)
    '''

    url = 'http://stackoverflow.com/questions/1197172/how-can-i-take-a-screenshot-image-of-a-website-using-python'
    screen_path, crop_path, thumbnail_path = get_screen_shot(
        url=url, filename='sof.png',
        crop=True, crop_replace=False,
        thumbnail=True, thumbnail_replace=False,
        thumbnail_width=200, thumbnail_height=150,
    )

这些是生成的图片：

Answer 2

这里有一个简单的解决方案，使用了webkit技术：http://webscraping.com/blog/Webpage-screenshots-with-webkit/

import sys
import time
from PyQt4.QtCore import *
from PyQt4.QtGui import *
from PyQt4.QtWebKit import *

class Screenshot(QWebView):
    def __init__(self):
        self.app = QApplication(sys.argv)
        QWebView.__init__(self)
        self._loaded = False
        self.loadFinished.connect(self._loadFinished)

    def capture(self, url, output_file):
        self.load(QUrl(url))
        self.wait_load()
        # set to webpage size
        frame = self.page().mainFrame()
        self.page().setViewportSize(frame.contentsSize())
        # render image
        image = QImage(self.page().viewportSize(), QImage.Format_ARGB32)
        painter = QPainter(image)
        frame.render(painter)
        painter.end()
        print 'saving', output_file
        image.save(output_file)

    def wait_load(self, delay=0):
        # process app events until page loaded
        while not self._loaded:
            self.app.processEvents()
            time.sleep(delay)
        self._loaded = False

    def _loadFinished(self, result):
        self._loaded = True

s = Screenshot()
s.capture('http://webscraping.com', 'website.png')
s.capture('http://webscraping.com/blog', 'blog.png')

Answer 3

在Mac上，有一个叫做 webkit2png 的工具，而在Linux加KDE系统上，你可以使用 khtml2png。我试过前者，效果不错，听说后者也有人在用。

最近我发现了一个叫 QtWebKit 的东西，它声称可以跨平台使用（我猜是因为Qt把WebKit整合进了他们的库里）。不过我没试过，所以也不能告诉你太多。

QtWebKit的链接展示了如何用Python来访问它。你至少可以用subprocess来实现其他工具的相似功能。

如何用Python截取网站的截图/图像？

14 个回答

撰写回答