anime-pictures好看壁纸爬虫
今天又发现一个壁纸网站https://anime-pictures.net/posts?page=0&lang=zh_CN更新速度快质量也不错，果断写个爬虫拿下，公众号再也不愁素材啦！运行脚本选订图片存储文件夹，同样的下载过的图片会存在根目录log.txt下，重新运行脚本的话，已经下载过的图片会跳过，低于200kb的图片也会跳过，可以随意调整
import requests
from bs4 import BeautifulSoup
import os
import urllib.parse
from concurrent.futures import ThreadPoolExecutor, as_completed
from tkinter import Tk, filedialog
def download_image(img_info, log_file_path):
img_url, image_path = img_info
image_name = os.path.basename(image_path)
# 追加写入log.txt
with open(log_file_path, 'a') as log_file:
log_file.write(f'{image_name},')
if os.path.exists(image_path):
print(f'Skipped image: {image_name}')
else:
# 获取文件大小
response = requests.head(img_url)
file_size = int(response.headers.get('Content-Length', 0))
if file_size < 200 * 1024:# 200KB
print(f'Skipped image: {image_name} (File size too small)')
else:
image_data = requests.get(img_url).content
with open(image_path, 'wb') as f:
f.write(image_data)
print(f'Downloaded image: {image_name}')
def download_images(url, save_path):
# 创建保存图片的文件夹
os.makedirs(save_path, exist_ok=True)
page = 0
log_file_path = os.path.join(save_path, 'log.txt')
# 读取已下载的文件列表
downloaded_files = []
if os.path.exists(log_file_path):
with open(log_file_path, 'r') as log_file:
downloaded_files = log_file.read().split(',')
with ThreadPoolExecutor(max_workers=2) as executor:
while True:
page_url = url + f'?page={page}&lang=en'
response = requests.get(page_url)
soup = BeautifulSoup(response.text, 'html.parser')
img_tags = soup.find_all('img', class_='svelte-1ibbyvk')
if not img_tags:
break
download_tasks = []
for img_tag in img_tags:
img_src = img_tag['src']
img_path = img_src.split('previews/').replace('_cp', '')
img_url = urllib.parse.urljoin('https://images.anime-pictures.net/', img_path)
image_name = os.path.basename(img_path)
image_path = os.path.join(save_path, image_name)
if image_name not in downloaded_files:
download_tasks.append((img_url, image_path))
for future in as_completed(executor.submit(download_image, task, log_file_path) for task in download_tasks):
try:
future.result()
except Exception as e:
print(f'Error occurred: {str(e)}')
page += 1
print(f'当前下载第: {page}页')
# 使用文件夹选择对话框选择保存路径
root = Tk()
root.withdraw()
save_path = filedialog.askdirectory(title='选择保存路径')
if save_path:
url = 'https://anime-pictures.net/posts'# 替换为你的链接
download_images(url, save_path)
感谢分享！学习学习！ 不错有
诉讼 可惜不会用Python，有EXE傻瓜式操作就好啦 体积好大的图片啊 学习思路，下来试试看。 学习思路，下来试试看 什么公众号要这种素材:lol分享一下 学习了可惜不会设计程序 感谢大佬，学习下思路
页:
[1]
2