Download image with selenium python

Here's a complete example (using google's recaptcha as a target):

import urllib
from selenium import webdriver

driver = webdriver.Firefox()
driver.get('http://www.google.com/recaptcha/demo/recaptcha')

# get the image source
img = driver.find_element_by_xpath('//div[@id="recaptcha_image"]/img')
src = img.get_attribute('src')

# download the image
urllib.urlretrieve(src, "captcha.png")

driver.close()

UPDATE:

The problem with dynamic generated images is that there is a new image generated each time you request it. In that case, you have several options:

take a screenshot

from selenium import webdriver

driver = webdriver.Firefox()
driver.get('https://moscowsg.megafon.ru/ps/scc/php/cryptographp.php?PHPSESSID=mfc540jkbeme81qjvh5t0v0bnjdr7oc6&ref=114&w=150')

driver.save_screenshot("screenshot.png")

driver.close()

simulate right click + "Save As". See this thread for more info.

Hope that helps.

It's ok to save a screenshot from the whole page and then cut the image from, but you can also to use the "find" method from "webdriver" to locate the image you want to save, and write the "screenshot_as_png" property like below:

from selenium import webdriver
driver = webdriver.Firefox()
driver.get('https://www.webpagetest.org/')
with open('filename.png', 'wb') as file:
    file.write(driver.find_element_by_xpath('/html/body/div[1]/div[5]/div[2]/table[1]/tbody/tr/td[1]/a/div').screenshot_as_png)

Sometimes it could get an error because of the scroll, but depending on your necessity, it's a good way to get the image.

The problem of using save_screenshot is that we cannot save an image in its original quality and cannot restore the alpha channel in an image. Therefore, I propose another solution. Here is a complete example using the selenium-wire library suggested by @codam_hsmits. It is possible to download images via ChromeDriver.

I have defined the following function to parse each request and save the request body to a file when necessary.

from seleniumwire import webdriver  # Import from seleniumwire
from urllib.parse import urlparse
import os
from mimetypes import guess_extension
import time
import datetime

def download_assets(requests,
                   asset_dir="temp",
                   default_fname="unnamed",
                   skip_domains=["facebook", "google", "yahoo", "agkn", "2mdn"],
                   exts=[".png", ".jpeg", ".jpg", ".svg", ".gif", ".pdf", ".bmp", ".webp", ".ico"],
                   append_ext=False):
    asset_list = {}
    for req_idx, request in enumerate(requests):
        # request.headers
        # request.response.body is the raw response body in bytes
        if request is None or request.response is None or request.response.headers is None or 'Content-Type' not in request.response.headers:
            continue
            
        ext = guess_extension(request.response.headers['Content-Type'].split(';')[0].strip())
        if ext is None or ext == "" or ext not in exts:
            #Don't know the file extention, or not in the whitelist
            continue
        parsed_url = urlparse(request.url)
        
        skip = False
        for d in skip_domains:
            if d in parsed_url.netloc:
                skip = True
                break
        if skip:
            continue
        
        frelpath = parsed_url.path.strip()
        if frelpath == "":
            timestamp = str(datetime.datetime.now().replace(microsecond=0).isoformat())
            frelpath = f"{default_fname}_{req_idx}_{timestamp}{ext}"
        elif frelpath.endswith("\\") or frelpath.endswith("/"):
            timestamp = str(datetime.datetime.now().replace(microsecond=0).isoformat())
            frelpath = frelpath + f"{default_fname}_{req_idx}_{timestamp}{ext}"
        elif append_ext and not frelpath.endswith(ext):
            frelpath = frelpath + f"_{default_fname}{ext}" #Missing file extension but may not be a problem
        if frelpath.startswith("\\") or frelpath.startswith("/"):
            frelpath = frelpath[1:]
        
        fpath = os.path.join(asset_dir, parsed_url.netloc, frelpath)
        if os.path.isfile(fpath):
            continue
        os.makedirs(os.path.dirname(fpath), exist_ok=True)
        print(f"Downloading {request.url} to {fpath}")
        asset_list[fpath] = request.url
        try:
            with open(fpath, "wb") as file:
                file.write(request.response.body)
        except:
            print(f"Cannot download {request.url} to {fpath}")
    return asset_list

Let's download some images from Google homepage to temp folder.

# Create a new instance of the Chrome/Firefox driver
driver = webdriver.Chrome()

# Go to the Google home page
driver.get('https://www.google.com')

# Download content to temp folder
asset_dir = "temp"

while True:
    # Please browser the internet, it will collect the images for every second
    time.sleep(1)
    download_assets(driver.requests, asset_dir=asset_dir)

driver.close()

Note that it cannot decide which images can be seen on the page rather than being hidden in the background, so the users should actively click the buttons or links to trigger new download requests.

Download image with selenium python

Related

Recent Posts