这是一些代码，用于从提供的URL下载所有图像，并将其保存在指定的输出文件夹中。您可以根据自己的需要对其进行修改。
"""
dumpimages.py
Downloads all the images on the supplied URL, and saves them to the
specified output file ("/test/" by default)
Usage:
python dumpimages.py http://example.com/ [output]
"""
from bs4 import BeautifulSoup as bs
from urllib.request import (
urlopen, urlparse, urlunparse, urlretrieve)
import os
import sys
def main(url, out_folder="/test/"):
"""Downloads all the images at 'url' to /test/"""
soup = bs(urlopen(url))
parsed = list(urlparse(url))
for image in soup.findAll("img"):
print("Image: %(src)s" % image)
filename = image["src"].split("/")[-1]
parsed[2] = image["src"]
outpath = os.path.join(out_folder, filename)
if image["src"].lower().startswith("http"):
urlretrieve(image["src"], outpath)
else:
urlretrieve(urlunparse(parsed), outpath)
def _usage():
print("usage: python dumpimages.py http://example.com [outpath]")
if __name__ == "__main__":
url = sys.argv[-1]
out_folder = "/test/"
if not url.lower().startswith("http"):
out_folder = sys.argv[-1]
url = sys.argv[-2]
if not url.lower().startswith("http"):
_usage()
sys.exit(-1)
main(url, out_folder)
602392714
清零编程群