Python爬虫，爬取蕾丝猫美女图（新手练习）

目标网址：aHR0cHM6Ly93d3cubGVpc2ltYW8uY29tLw==

直接上代码

这个网站请求频繁之后会阻止你的请求，所以加了一些防护措施，会有一些延迟，并且没有破解会员的，只能下载前20张好像。

仅供学习，请勿用于非法用途！

import requests
from lxml import etree
from urllib.parse import urljoin
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry
import re


def get_main_page():
    num = int(input("请输入需要爬取蕾丝猫的页码:"))
    header = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                      "Chrome/125.0.0.0 Safari/537.36",
        "Referer": "https://www.lesmao.com/"
    }
    url = f"https://www.leisimao.com/page/{num}"
    session = requests.Session()
    retry = Retry(
        total=5,
        backoff_factor=1,
        status_forcelist=[500, 502, 503, 504]
    )
    adapter = HTTPAdapter(max_retries=retry)
    session.mount('http://', adapter)
    session.mount('https://', adapter)
    
    try:
        resp = session.get(url, headers=header, timeout=10)  # 设置超时时间
        resp.raise_for_status()
    except requests.exceptions.RequestException as e:
        print(f"请求出错: {e}")
        return
    
    main_page = etree.HTML(resp.text)
    main_url = main_page.xpath("//div[@class='photo group']/a/@href")
    for img_url in main_url:
        href = urljoin(url, img_url)
        # print(href)
        get_json_data(url, href)


def get_json_data(url, href):
    # print(href)
    header = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                      "Chrome/125.0.0.0 Safari/537.36",
        "Referer": url
    }
    session = requests.Session()
    retry = Retry(
        total=5,
        backoff_factor=1,
        status_forcelist=[500, 502, 503, 504]
    )
    adapter = HTTPAdapter(max_retries=retry)
    session.mount('http://', adapter)
    session.mount('https://', adapter)
    
    try:
        resp = session.get(href, headers=header, timeout=10)  # 设置超时时间
        resp.raise_for_status()
    except requests.exceptions.RequestException as e:
        print(f"请求出错: {e}")
        return
    
    # 解析页面内容，查找包含 JSON 数据的 script 标签
    page = etree.HTML(resp.text)
    script_content = page.xpath("//script[@id='__NUXT_DATA__']/text()")
    if script_content:
        json_data = script_content[0]
        parse_json_data(json_data)


def parse_json_data(json_data):
    header = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                      "Chrome/125.0.0.0 Safari/537.36",
        "Referer": "https://www.lesmao.com/"
    }
    # 使用正则表达式找到最后的几个 JPG 链接
    pattern = r'"T/XiuRen/.*?\.jpg"'
    jpg_links = re.findall(pattern, json_data)
    
    # 打印最后的 JPG 链接
    for link in jpg_links:
        link = link.strip('"')  # 去除双引号
        href = urljoin("https://img.lesmao.vip/1178/", link)
        href = href.replace(".jpg", ".webp")  # 替换为 .webp 格式
        # print(href)
        if href:
            print(f"正在下载图片: {href}")
            img_resp = requests.get(href, headers=header)
            file_name = href.split("/")[-1]
            with open(f"img/{file_name}", "wb") as f:
                f.write(img_resp.content)
        else:
            print(f"未找到图片的 src 属性，URL: {href}")


if __name__ == '__main__':
    get_main_page()

运行图片

总结

学习一些爬虫的知识（刚入门），正好看到这个网站就拿来实践了一下。有问题可以评论，一起交流一起学习。