Question

我正在尝试从Google chrome获取图像并将其保存在文件夹中。不知何故我得到这个错误。分享下面的代码。调用search_and_download函数的函数时出现错误。我已经在Google colab上完成了这段代码。

!apt-get update
!apt install chromium-chromedriver
!cp /usr/lib/chromium-browser/chromedriver /usr/bin
!pip install selenium

import selenium
from selenium import webdriver
from selenium.webdriver.chrome.options import Options

chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--no-sandbox')
chrome_options.add_argument('--disable-dev-shm-usage')
DRIVER_PATH = '/usr/bin/chromedriver'

wd.get('https://google.com')

search_box = wd.find_element_by_css_selector('input.gLFyf')
search_box.send_keys('Dogs')
wd.quit()

import time
def fetch_image_urls(query:str, max_links_to_fetch:int, wd:webdriver, sleep_between_interactions:int=1):
    def scroll_to_end(wd):
        wd.execute_script("window.scrollTo(0, document.body.scrollHeight);")
        time.sleep(sleep_between_interactions)    
    
    # build the google query
    search_url = "https://www.google.com/search?safe=off&site=&tbm=isch&source=hp&q={q}&oq={q}&gs_l=img"

    # load the page
    wd.get(search_url.format(q=query))

    image_urls = set()
    image_count = 0
    results_start = 0
    while image_count < max_links_to_fetch:
        scroll_to_end(wd)

        # get all image thumbnail results
        thumbnail_results = wd.find_elements_by_css_selector("img.rg_ic")
        number_results = len(thumbnail_results)
        
        print(f"Found: {number_results} search results. Extracting links from {results_start}:{number_results}")
        
        for img in thumbnail_results[results_start:number_results]:
            # try to click every thumbnail such that we can get the real image behind it
            try:
                img.click()
                time.sleep(sleep_between_interactions)
            except Exception:
                continue

            # extract image urls    
            actual_images = wd.find_elements_by_css_selector('img.irc_mi')
            for actual_image in actual_images:
                if actual_image.get_attribute('src'):
                    image_urls.add(actual_image.get_attribute('src'))

            image_count = len(image_urls)

            if len(image_urls) >= max_links_to_fetch:
                print(f"Found: {len(image_urls)} image links, done!")
                break
        else:
            print("Found:", len(image_urls), "image links, looking for more ...")
            time.sleep(1)
            load_more_button = wd.find_element_by_css_selector(".ksb")
            if load_more_button:
                wd.execute_script("document.querySelector('.ksb').click();")

        # move the result startpoint further down
        results_start = len(thumbnail_results)

    return image_urls
import os
def search_and_download(search_term:str, driver_path:str, target_path='/content/images',number_images=5):
    target_folder = os.path.join(target_path,'_'.join(search_term.lower().split(' ')))

    if not os.path.exists(target_folder):
        os.makedirs(target_folder)

    with wd:
        res = fetch_image_urls(search_term, number_images, wd=wd, sleep_between_interactions=0.5)
        
    for elem in res:
        persist_image(target_folder,elem)
search_term='Dogs'
search_and_download(search_term=search_term, driver_path= DRIVER_PATH)

这是错误部分：


---------------------------------------------------------------------------
ConnectionRefusedError                    Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/urllib3/connection.py in _new_conn(self)
    158             conn = connection.create_connection(
--> 159                 (self._dns_host, self.port), self.timeout, **extra_kw)
    160 

25 frames
ConnectionRefusedError: [Errno 111] Connection refused

During handling of the above exception, another exception occurred:

NewConnectionError                        Traceback (most recent call last)
NewConnectionError: <urllib3.connection.HTTPConnection object at 0x7f7458f60eb8>: Failed to establish a new connection: [Errno 111] Connection refused

During handling of the above exception, another exception occurred:

MaxRetryError                             Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/urllib3/util/retry.py in increment(self, method, url, response, error, _pool, _stacktrace)
    397 
    398         if new_retry.is_exhausted():
--> 399             raise MaxRetryError(_pool, url, error or ResponseError(cause))
    400 
    401         log.debug("Incremented Retry for (url='%s'): %r", url, new_retry)

MaxRetryError: HTTPConnectionPool(host='127.0.0.1', port=43465): Max retries exceeded with url: /session/97f397fa9f8f046a5b44bf75808d09c6/url (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f7458f60eb8>: Failed to establish a new connection: [Errno 111] Connection refused',))

我认为使用fetch_image_urls函数连接到网络驱动程序时出错。

HTTP连接池错误：无法建立新连接

0 个答案: