爬虫竟然如此简单！只需一键下载，轻松获取百度千万张高清图片！附赠爬虫软件！

import re import requests import urllib.parse from PIL import Image from io import BytesIO import time import json

class BaiduImageCrawler: def __init__(self): self.headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36' } # 百度图片搜索API self.search_url = 'https://image.baidu.com/search/acjson'

def create_folder(self, keyword): """创建保存图片的文件夹""" folder_path = f'./images/{keyword}' if not os.path.exists(folder_path): os.makedirs(folder_path) return folder_path

def get_images_url(self, keyword, page_num=1): """获取图片URL列表""" urls = [] pn = 30 # 每页显示30张图片

for page in range(page_num): params = { 'tn': 'resultjson_com', 'logid': '7603311155072595725', 'ipn': 'rj', 'ct': '201326592', 'fp': 'result', 'queryWord': keyword, 'cl': '2', 'lm': '-1', 'ie': 'utf-8', 'oe': 'utf-8', 'adpicid': '', 'st': '-1', 'z': '', 'ic': '', 'hd': '', 'latest': '', 'copyright': '', 'word': keyword, 's': '', 'se': '', 'tab': '', 'width': '', 'height': '', 'face': '0', 'istype': '2', 'qc': '', 'nc': '1', 'fr': '', 'expermode': '', 'force': '', 'pn': page * pn, 'rn': '30', 'gsm': '1e', }

try: response = requests.get(self.search_url, headers=self.headers, params=params) response.raise_for_status() data = response.json()

for item in data.get('data', []): if item and 'thumbURL' in item: urls.append({ 'url': item['thumbURL'], 'width': item.get('width', 0), 'height': item.get('height', 0) }) except Exception as e: print(f"获取图片URL时出错: {e}") continue

return urls

def download_image(self, url, folder_path, index, min_width=300, min_height=300): """下载并保存图片，过滤小尺寸图片""" try: response = requests.get(url['url'], headers=self.headers) response.raise_for_status()

# 读取图片 img = Image.open(BytesIO(response.content)) width, height = img.size

# 检查图片尺寸 if width < min_width or height < min_height: print(f"图片尺寸太小 ({width}x{height}), 已跳过") return False

# 保存图片 file_extension = img.format.lower() if img.format else 'jpg' file_path = os.path.join(folder_path, f'{index}.{file_extension}') img.save(file_path) print(f"成功下载图片: {file_path}") return True

except Exception as e: print(f"下载图片时出错: {e}") return False

def crawl_images(self, keyword, max_images=100, min_width=300, min_height=300): """主要爬取函数""" print(f"开始爬取关键词 '{keyword}' 的图片...")

# 创建保存文件夹 folder_path = self.create_folder(keyword)

# 计算需要爬取的页数 pages_needed = (max_images + 29) // 30

# 获取图片URL列表 image_urls = self.get_images_url(keyword, pages_needed)

# 下载图片 success_count = 0 index = 1

for url in image_urls: if success_count >= max_images: break

if self.download_image(url, folder_path, index, min_width, min_height): success_count += 1 index += 1

# 添加延时，避免请求过快 time.sleep(0.5)

print(f"\n爬取完成! 成功下载 {success_count} 张图片") print(f"图片保存在: {os.path.abspath(folder_path)}")

def main(): # 创建爬虫实例 crawler = BaiduImageCrawler()

# 设置爬取参数 keyword = input("请输入要搜索的关键词: ") max_images = int(input("请输入要下载的图片数量: ")) min_width = int(input("请输入图片最小宽度 (像素): ")) min_height = int(input("请输入图片最小高度 (像素): "))

# 开始爬取 crawler.crawl_images( keyword=keyword, max_images=max_images, min_width=min_width, min_height=min_height )

if __name__ == '__main__': main()