如何使用Python获取网站的屏幕截图/图像？

Question

我想要实现的是从python中的任何网站获取网站截图.

环境:Linux

Answer 1

这是一个使用webkit的简单解决方案: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 2

这是我的解决方案,从各种来源获取帮助.它需要完整的网页屏幕捕获并裁剪它(可选)并从裁剪后的图像中生成缩略图.以下是要求:

要求:

1. 安装NodeJS
2. 使用Node的包管理器安装phantomjs: npm -g install phantomjs
3. 安装selenium(在你的virtualenv中,如果你正在使用它)
4. 安装imageMagick
5. 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,
    )

这些是生成的图像:

• 完整的网页屏幕
• 从捕获的屏幕裁剪图像
• 裁剪图像的缩略图

Answer 3

11年后...

Python3.6使用和截取网站屏幕截图Google PageSpeedApi Insights v5：

import base64
import requests
import traceback
import urllib.parse as ul

# It's possible to make requests without the api key, but the number of requests is very limited  

url = "https://duckgo.com"
urle = ul.quote_plus(url)
image_path = "duckgo.jpg"

key = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
strategy = "desktop" # "mobile"
u = f"https://www.googleapis.com/pagespeedonline/v5/runPagespeed?key={key}&strategy={strategy}&url={urle}"

try:
    j = requests.get(u).json()
    ss_encoded = j['lighthouseResult']['audits']['final-screenshot']['details']['data'].replace("data:image/jpeg;base64,", "")
    ss_decoded = base64.b64decode(ss_encoded)
    with open(image_path, 'wb+') as f:
        f.write(ss_decoded) 
except:
    print(traceback.format_exc())
    exit(1)

笔记：

• 现场演示
• 优点：免费
• 缺点：分辨率低
• 获取API密钥
• 文档
• 限制：
  • 每天查询 = 25,000
  • 每 100 秒的查询数 = 400

Answer 4

在Mac上,有webkit2png,在Linux + KDE上,你可以使用khtml2png.我尝试了前者并且效果很好,并且听说后者正在使用.

我最近遇到了QtWebKit,它声称是跨平台的(Qt将WebKit推入他们的库中,我猜).但我从未尝试过,所以我不能告诉你更多.

QtWebKit链接显示了如何从Python访问.您应该至少可以使用子进程对其他进程执行相同的操作.

Answer 5

可以使用硒

from selenium import webdriver

DRIVER = 'chromedriver'
driver = webdriver.Chrome(DRIVER)
driver.get('https://www.spotify.com')
screenshot = driver.save_screenshot('my_screenshot.png')
driver.quit()

https://sites.google.com/a/chromium.org/chromedriver/getting-started

Answer 6

使用Rendertron是一种选择。在幕后，这是一个无头的 Chrome，暴露了以下端点：

• /render/:url：访问此路线，例如，requests.get如果您对 DOM 感兴趣。
• /screenshot/:url：如果您对屏幕截图感兴趣，请访问此路线。

您可以使用 npm 安装 rendertron，rendertron在一个终端中运行，访问http://localhost:3000/screenshot/:url并保存文件，但是render-tron.appspot.com上提供了一个演示，可以在不安装 npm 包的情况下在本地运行此 Python3 代码段：

import requests

BASE = 'https://render-tron.appspot.com/screenshot/'
url = 'https://google.com'
path = 'target.jpg'
response = requests.get(BASE + url, stream=True)
# save file, see /sf/answers/919651141/
if response.status_code == 200:
    with open(path, 'wb') as file:
        for chunk in response:
            file.write(chunk)

Answer 7

我无法对ars的回答发表评论,但实际上我使用QtWebkit运行了Roland Tapken的代码并且运行良好.

只是想确认Roland在他的博客上发布的内容在Ubuntu上运行得很好.我们的生产版本最终没有使用他写的任何内容,但我们使用PyQt/QtWebKit绑定取得了很大的成功.

Answer 8

这是一个老问题，大多数答案都有点过时了。目前，我会做两件事中的一件。

1. 创建一个截屏程序

我会使用Pyppeteer来截取网站的屏幕截图。它在Puppeteer包上运行。Puppeteer 会启动无头 Chrome 浏览器，因此屏幕截图看起来就像在普通浏览器中一样。

这取自 pyppeteer 文档：

import asyncio
from pyppeteer import launch

async def main():
    browser = await launch()
    page = await browser.newPage()
    await page.goto('https://example.com')
    await page.screenshot({'path': 'example.png'})
    await browser.close()

asyncio.get_event_loop().run_until_complete(main())

2.使用截图API

您还可以使用截图 API，例如此API 。好处是您不必自己设置所有内容，而只需调用 API 端点即可。

这取自截图 API 的文档：

import urllib.parse
import urllib.request
import ssl

ssl._create_default_https_context = ssl._create_unverified_context

# The parameters.
token = "YOUR_API_TOKEN"
url = urllib.parse.quote_plus("https://example.com")
width = 1920
height = 1080
output = "image"

# Create the query URL.
query = "https://screenshotapi.net/api/v1/screenshot"
query += "?token=%s&url=%s&width=%d&height=%d&output=%s" % (token, url, width, height, output)

# Call the API.
urllib.request.urlretrieve(query, "./example.png")