¿Cómo puedo tomar una captura de pantalla / imagen de un sitio web usando Python?

Aquí hay una solución simple usando webkit: 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')

Aquí está mi solución al obtener ayuda de varias fuentes. Toma la captura de pantalla de la página web completa y la recorta (opcional) y genera miniaturas de la imagen recortada también. Los siguientes son los requisitos:

Requisitos:

1. Instalar NodeJS
2. Usando el gestor de paquetes de Node instalar phantomjs: npm -g install phantomjs
3. Instale selenium (en su virtualenv, si está usando eso)
4. Instalar ImageMagick
5. Añadir phantomjs a la ruta del sistema (on windows)

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,
    )

Estas son las imágenes generadas:

• Pantalla completa de la página web
• Imagen recortada de la pantalla capturada
• Miniatura de una imagen recortada

No puedo comentar la respuesta de ars, pero en realidad tengo El código de Roland Tapken corriendo usando QtWebKit y funciona bastante bien.

Solo quería confirmar que lo que Roland publica en su blog funciona muy bien en Ubuntu. Nuestra versión de producción terminó sin usar nada de lo que escribió, pero estamos usando los enlaces PyQt/QtWebKit con mucho éxito.

Puede hacer usando Selenio

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

No mencionas en qué entorno estás ejecutando, lo que hace una gran diferencia porque no hay un navegador web Python puro que sea capaz de renderizar HTML.

Pero si estás usando un Mac, he usado webkit2png con gran éxito. Si no, como otros han señalado, hay muchas opciones.

Prueba esto..

#!/usr/bin/env python

import gtk.gdk

import time

import random

while 1 :
    # generate a random time between 120 and 300 sec
    random_time = random.randrange(120,300)

    # wait between 120 and 300 seconds (or between 2 and 5 minutes)
    print "Next picture in: %.2f minutes" % (float(random_time) / 60)

    time.sleep(random_time)

    w = gtk.gdk.get_default_root_window()
    sz = w.get_size()

    print "The size of the window is %d x %d" % sz

    pb = gtk.gdk.Pixbuf(gtk.gdk.COLORSPACE_RGB,False,8,sz[0],sz[1])
    pb = pb.get_from_drawable(w,w.get_colormap(),0,0,0,0,sz[0],sz[1])

    ts = time.time()
    filename = "screenshot"
    filename += str(ts)
    filename += ".png"

    if (pb != None):
        pb.save(filename,"png")
        print "Screenshot saved to "+filename
    else:
        print "Unable to get the screenshot."