在Python中拍摄URL屏幕截图的更好方法
问题描述
问题说明
当前正在处理一个项目,该项目需要我浏览URL并拍摄网页的屏幕截图。
在查看各种资源后,我找到了3种方法。我将介绍我目前使用的所有3种方法。
方法1:PhantomJS
from selenium import webdriver
import time
import sys
print 'Without Headless'
_start = time.time()
br = webdriver.PhantomJS()
br.get('http://' + sys.argv[1])
br.save_screenshot('screenshot-phantom.png')
br.quit
_end = time.time()
print 'Total time for non-headless {}'.format(_end - _start)
方法2:无头浏览器
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
print 'Headless'
_start = time.time()
options = Options()
options.add_argument("--headless") # Runs Chrome in headless mode.
options.add_argument('--no-sandbox') # # Bypass OS security model
options.add_argument('start-maximized')
options.add_argument('disable-infobars')
options.add_argument("--disable-extensions")
driver = webdriver.Chrome(chrome_options=options, executable_path='/usr/bin/chromedriver')
driver.get('http://' + sys.argv[1])
driver.save_screenshot('screenshot-headless.png')
driver.quit()
_end = time.time()
print 'Total time for headless {}'.format(_end - _start)
方法3:pyQt
import argparse
import sys
import logging
import sys
import time
import os
import urlparse
from selenium import webdriver
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):
_logger.info('Received url {}'.format(url))
_start = time.time()
try:
#Check for http/https
if url[0:3] == 'http' or url[0:4] == 'https':
self.url = url
else:
url = 'http://' + url
self.load(QUrl(url))
self.wait_load(url)
# 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()
_logger.info('Saving screenshot {} for {}'.format(output_file,url))
image.save(os.path.join(os.path.dirname(os.path.realpath(__file__)),'data',output_file))
except Exception as e:
_logger.error('Error in capturing screenshot {} - {}'.format(url,e))
_end = time.time()
_logger.info('Time took for processing url {} - {}'.format(url,_end - _start))
def wait_load(self,url,delay=1,retry_count=60):
# process app events until page loaded
while not self._loaded and retry_count:
_logger.info('wait_load for url {} retry_count {}'.format(url,retry_count))
self.app.processEvents()
time.sleep(delay)
retry_count -=1
_logger.info('wait_load for url {} expired'.format(url))
self._loaded = False
def _loadFinished(self, result):
self._loaded = True
面临的问题:
这3种方法在使用过程中,都会因为这样或那样的错误而卡住,这里就问了这样一个问题Error Question on Stackoverflow。 所以在这3种方法中,用Python截取网页截图是非常有效的,而且适用于大规模部署。
解决方案
取自https://gist.github.com/fabtho/13e4a2e7cfbfde671b8fa81bbe9359fb,用Python3重写
此方法在技术上可行,但效果不佳,因为许多网站都会在每个截图中显示接受Cookie的弹出窗口,因此根据您使用的网站,您可能希望在开始截图过程之前先使用Selenium删除这些弹出窗口。
from PIL import Image
from io import BytesIO
verbose = 1
browser = webdriver.Chrome(executable_path='C:/yourpath/chromedriver.exe')
browser.get('http://stackoverflow.com/questions/37906704/taking-a-whole-page-screenshot-with-selenium-marionette-in-python')
# from here http://stackoverflow.com/questions/1145850/how-to-get-height-of-entire-document-with-javascript
js = 'return Math.max( document.body.scrollHeight, document.body.offsetHeight, document.documentElement.clientHeight, document.documentElement.scrollHeight, document.documentElement.offsetHeight);'
scrollheight = browser.execute_script(js)
if verbose > 0:
print(scrollheight)
slices = []
offset = 0
while offset < scrollheight:
if verbose > 0:
print(offset)
browser.execute_script("window.scrollTo(0, %s);" % offset)
img = Image.open(BytesIO(browser.get_screenshot_as_png()))
offset += img.size[1]
slices.append(img)
if verbose > 0:
browser.get_screenshot_as_file('%s/screen_%s.png' % ('/tmp', offset))
print(scrollheight)
screenshot = Image.new('RGB', (slices[0].size[0], offset))
offset = 0
for img in slices:
screenshot.paste(img, (0, offset))
offset += img.size[1]
screenshot.save('screenshot.png')
browser.quit()```
相关文章