Altair 使用 selenium chromedriver 自动保存图表

Altair automatic save chart using selenium chromedriver

由于 previous 已关闭,没有任何有用的解决方案,请再次询问。

我正在尝试循环生成一些图表并自动保存它们。

我正在 Windows,使用 Chrome。

我一直在关注 the documentation 如何在 svg 中保存图表。

我为我的 Chrome 版本下载了合适的 ChromeDriver。 gdf 是我的地理数据框,一切正常,我可以生成并手动保存图表。

此外,这个取自 chromium 文档的示例有效:

import time
from selenium import webdriver

driver = webdriver.Chrome('pathtochromedriver/chromedriver_win32/chromedriver.exe')
driver.get('http://www.google.com/');
time.sleep(5) # Let the user actually see something!
search_box = driver.find_element_by_name('q')
search_box.send_keys('ChromeDriver')
search_box.submit()
time.sleep(5) # Let the user actually see something!
driver.quit()

下面是我正在尝试的代码 运行:

#Chromedriver for headless run and chart automatic save
from selenium import webdriver
from selenium.webdriver.chrome.options import Options 

chrome_options = Options()  
chrome_options.add_argument("--headless") 
####### None of the following work! 
#driver = webdriver.Chrome(chrome_options=chrome_options, executable_path=r'pathtochromedriver/chromedriver_win32/chromedriver.exe')
#driver = webdriver.Chrome(executable_path=r'pathtochromedriver/chromedriver_win32/chromedriver.exe')
driver = webdriver.Chrome('pathtochromedriver/chromedriver_win32/chromedriver.exe')
#
#loop
for group in gdf['Group Name'].unique():
    map_1km_json = json.loads(gdf[gdf['Group Name']==group].to_json())
    map_1km_data = alt.Data(values=map_1km_json['features'])
    data_1km_geojson = alt.InlineData(values=map_1km, format=alt.DataFormat(property='features',type='json'))
    domain=[1,2]
    range_=['#b0d247','#007bd1']
    choro1_5 = alt.Chart(map_1km_data).mark_geoshape().encode(
        alt.Color('properties.Cat2:O', scale=alt.Scale(domain=domain, range=range_),title = "Havvandsstigning"),
        #alt.Color('properties.Cat2', type='quantitative', scale=alt.Scale(scheme='plasma'),title = "Havvandsstigning")
        tooltip = ['properties.dd_km1:N','properties.Cat2:N']
    ).properties(
    width=1100,
    height=800
    )
    (background + choro1_5).save("{}.svg".format(bank))
driver.quit()

运行 代码打开一个空的新 chrome 窗格 (在后台),看起来像这样,这暗示了 chromedriver 工作顺利:

但是代码returns出现如下错误:

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
~\Anaconda3\lib\site-packages\selenium\webdriver\common\service.py in start(self)
     75                                             stderr=self.log_file,
---> 76                                             stdin=PIPE)
     77         except TypeError:

~\Anaconda3\lib\subprocess.py in __init__(self, args, bufsize, executable, stdin, stdout, stderr, preexec_fn, close_fds, shell, cwd, env, universal_newlines, startupinfo, creationflags, restore_signals, start_new_session, pass_fds, encoding, errors, text)
    774                                 errread, errwrite,
--> 775                                 restore_signals, start_new_session)
    776         except:

~\Anaconda3\lib\subprocess.py in _execute_child(self, args, executable, preexec_fn, close_fds, pass_fds, cwd, env, startupinfo, creationflags, shell, p2cread, p2cwrite, c2pread, c2pwrite, errread, errwrite, unused_restore_signals, unused_start_new_session)
   1177                                          os.fspath(cwd) if cwd is not None else None,
-> 1178                                          startupinfo)
   1179             finally:

FileNotFoundError: [WinError 2] The system cannot find the file specified

During handling of the above exception, another exception occurred:

WebDriverException                        Traceback (most recent call last)
<ipython-input-27-6067387e4b2f> in <module>
     19     height=800
     20     )
---> 21     (background + choro1_5).save("{}.svg".format(bank))
     22 driver.quit()

~\Anaconda3\lib\site-packages\altair\vegalite\v3\api.py in save(self, fp, format, override_data_transformer, scale_factor, vegalite_version, vega_version, vegaembed_version, **kwargs)
    478         if override_data_transformer:
    479             with data_transformers.disable_max_rows():
--> 480                 result = save(**kwds)
    481         else:
    482             result = save(**kwds)

~\Anaconda3\lib\site-packages\altair\utils\save.py in save(chart, fp, vega_version, vegaembed_version, format, mode, vegalite_version, embed_options, json_kwds, webdriver, scale_factor, **kwargs)
    102                                         vegaembed_version=vegaembed_version,
    103                                         webdriver=webdriver,
--> 104                                         scale_factor=scale_factor, **kwargs)
    105         if format == 'png':
    106             write_file_or_filename(fp, mimebundle['image/png'], mode='wb')

~\Anaconda3\lib\site-packages\altair\utils\mimebundle.py in spec_to_mimebundle(spec, format, mode, vega_version, vegaembed_version, vegalite_version, **kwargs)
     54                               vega_version=vega_version,
     55                               vegaembed_version=vegaembed_version,
---> 56                               vegalite_version=vegalite_version, **kwargs)
     57         if format == 'png':
     58             render = base64.b64decode(render.split(',', 1)[1].encode())

~\Anaconda3\lib\site-packages\altair\utils\headless.py in compile_spec(spec, format, mode, vega_version, vegaembed_version, vegalite_version, scale_factor, driver_timeout, webdriver)
    152             webdriver_options.add_argument('--no-sandbox')
    153 
--> 154     driver = webdriver_class(options=webdriver_options)
    155 
    156     try:

~\Anaconda3\lib\site-packages\selenium\webdriver\chrome\webdriver.py in __init__(self, executable_path, port, options, service_args, desired_capabilities, service_log_path, chrome_options, keep_alive)
     71             service_args=service_args,
     72             log_path=service_log_path)
---> 73         self.service.start()
     74 
     75         try:

~\Anaconda3\lib\site-packages\selenium\webdriver\common\service.py in start(self)
     81                 raise WebDriverException(
     82                     "'%s' executable needs to be in PATH. %s" % (
---> 83                         os.path.basename(self.path), self.start_error_message)
     84                 )
     85             elif err.errno == errno.EACCES:

WebDriverException: Message: 'chromedriver' executable needs to be in PATH. Please see https://sites.google.com/a/chromium.org/chromedriver/home

看看 Altair Saver 项目。 它使用 Chrome 驱动程序和 Selenium。 通过 pip 或 conda 安装。它可以保存到 svg:

from altair_saver import save

save((background + choro1_5), "{}.svg".format(bank))

您的代码不起作用的原因是您没有将驱动程序实例传递给 Altair,因此 Altair 正在创建默认驱动程序实例并在默认位置寻找 chromedriver。

Altair 目前不支持将自定义驱动程序实例传递给 save() 方法,因此无法按照您上面尝试的方式保存图形,除非可以在默认位置提供 chromedriver。

不过,我们正在使用 altair_saver 软件包对此进行改进。使用它,您可以将自定义驱动程序实例传递给保存方法:

from altair_saver import save

# ...

chart = background + choro1_5
filename = f"{bank}.svg"
save(chart, filename, method='selenium', webdriver=driver)

在未来的 Altair 版本中,这个更灵活的保护程序扩展将取代 Altair 当前的内置 chart.save() 方法。

@jakevdp 解决方案完美运行。以下是有关如何在 Windows 机器

上使用 selenium 和 chrome 驱动程序启用 .png 和 .svg 的完整步骤

安装altair_saver

pip install altair_saver

检查安装在 windows 系统中的 chrome 版本(Chrome 浏览器 > 帮助 > 版本)。比如版本是99.0.4844.xx,安装匹配的chromedriver如下

pip install chromedriver-binary=="99.0.4844.74"

chromium.org 下载 chrome 驱动程序并将其添加到环境变量 PATH 或者假设驱动程序的位置是 PATH_TO_CHROME_DRIVER_EXE

你的Python代码应该如下保存为png

from altair_saver import save
import selenium.webdriver
driver = selenium.webdriver.Chrome('PATH_TO_CHROME_DRIVER_EXE')
save(chart, "chart.png", method='selenium', webdriver=driver) 

注意:altair_saver在各种操作系统的顶层installation部分记录了其中一些细节,供您参考。