使用save_screenshot的问题是我们无法将图像保存为原始质量，也无法恢复图像中的alpha通道。因此，我提出另一种解决方案。这是使用@codam_hsmits 建议的selenium-wire 库的完整示例。可以通过ChromeDriver下载图片。
我已经定义了以下函数来解析每个请求，并在必要时将请求正文保存到文件中。
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
让我们从谷歌主页下载一些图片到temp文件夹。
# 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()
注意它不能决定哪些图片可以在页面上看到而不是隐藏在后台，所以用户应该主动点击按钮或链接来触发新的下载请求。