53 lines
1.4 KiB
Python
53 lines
1.4 KiB
Python
|
import os
|
||
|
|
import re
|
||
|
|
|
||
|
|
import requests
|
||
|
|
from bs4 import BeautifulSoup
|
||
|
|
from PIL import Image
|
||
|
|
from io import BytesIO
|
||
|
|
|
||
|
|
|
||
|
|
headers = {
|
||
|
|
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"
|
||
|
|
}
|
||
|
|
|
||
|
|
animal_names = ["猫", "狗", "cat", "dog"]
|
||
|
|
|
||
|
|
save_dir = "D:/project_space/01/005/datasets/001/images"
|
||
|
|
if not os.path.exists(save_dir):
|
||
|
|
os.makedirs(save_dir)
|
||
|
|
|
||
|
|
|
||
|
|
def download_images(fish_name, num_images=5):
|
||
|
|
search_url = f"https://www.google.com/search?hl=zh-CN&tbm=isch&q={fish_name}"
|
||
|
|
|
||
|
|
response = requests.get(search_url, headers=headers)
|
||
|
|
soup = BeautifulSoup(response.text, "html.parser")
|
||
|
|
img_tags = soup.find_all("img")
|
||
|
|
|
||
|
|
img_urls = []
|
||
|
|
|
||
|
|
for img_tag in img_tags:
|
||
|
|
img_url = img_tag.get("src")
|
||
|
|
if img_url and img_url.startswith("http"):
|
||
|
|
img_urls.append(img_url)
|
||
|
|
if len(img_urls) >= num_images:
|
||
|
|
break
|
||
|
|
|
||
|
|
for idx, img_url in enumerate(img_urls):
|
||
|
|
try:
|
||
|
|
img_data = requests.get(img_url).content
|
||
|
|
img_name = os.path.join(save_dir, f"{fish_name}_{idx + 1}.jpg")
|
||
|
|
with open(img_name, "wb") as f:
|
||
|
|
f.write(img_data)
|
||
|
|
print(f"下载成功：{img_name}")
|
||
|
|
except Exception as e:
|
||
|
|
print(f"下载失败：{e}")
|
||
|
|
|
||
|
|
|
||
|
|
for animal_name in animal_names:
|
||
|
|
download_images(animal_name, 200)
|
||
|
|
|
||
|
|
print("所有图片下载完成！")
|
||
|
|
|