50 lines
1.7 KiB
Python
50 lines
1.7 KiB
Python
import requests
|
||
from lxml import etree
|
||
import os
|
||
|
||
# 设置目标URL和请求头
|
||
url = "https://www.xiurenwang.cc/bang?f=7"
|
||
headers = {
|
||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
||
"Referer": "https://www.xiurenwang.cc/"
|
||
}
|
||
|
||
# 发送请求获取网页内容
|
||
response = requests.get(url, headers=headers)
|
||
response.encoding = "utf-8" # 确保正确解码
|
||
|
||
# 解析HTML
|
||
html = etree.HTML(response.text)
|
||
|
||
# 提取图片链接和标题（假设最新图片在列表页面中）
|
||
image_items = html.xpath('//div[@class="list"]/li/a[@class="img"]/@href')
|
||
titles = html.xpath('//div[@class="tit"]/a/text()')
|
||
|
||
# 创建保存图片的文件夹
|
||
save_dir = "./xiuren_images"
|
||
if not os.path.exists(save_dir):
|
||
os.makedirs(save_dir)
|
||
|
||
# 只获取最新的一个条目（假设第一个是最新的）
|
||
if image_items:
|
||
latest_url = "https://www.xiurenwang.cc" + image_items[0] # 拼接详情页URL
|
||
latest_title = titles[0] if titles else "latest_image"
|
||
|
||
# 访问详情页获取图片
|
||
detail_response = requests.get(latest_url, headers=headers)
|
||
detail_html = etree.HTML(detail_response.text)
|
||
image_urls = detail_html.xpath('//div[@id="image"]/a/@href')
|
||
|
||
# 下载图片
|
||
for idx, img_url in enumerate(image_urls):
|
||
img_response = requests.get(img_url, headers=headers)
|
||
img_name = f"{latest_title}_{idx + 1}.jpg"
|
||
img_path = os.path.join(save_dir, img_name.replace('/', '_')) # 避免文件名中的斜杠
|
||
with open(img_path, "wb") as f:
|
||
f.write(img_response.content)
|
||
print(f"已下载: {img_path}")
|
||
else:
|
||
print("未找到图片链接，可能需要调整XPath或检查网站结构。")
|
||
|
||
print("最新图片下载完成！")
|