[Python] 开源：小红书无需登录直接下载视频、图片、API版本

软件介绍：

其实小红书下载图片挺简单的，视频也还好，把自用的代码分享出来，大家一起讨论，共同进步。想要什么功能，自己改源码就可以。

软件截图：

源码下载地址：

Python版本：

# -*- coding: utf-8 -*-

import requests
import re
import os

# from PIL import Image


# def webp_to_jpeg(webp_path):
#     # 获取文件名和目录
#     file_dir, file_name = os.path.split(webp_path)

#     # 检查文件扩展名是否为.webp
#     if not file_name.lower().endswith(".webp"):
#         print("输入的文件不是WebP格式！")
#         return

#     # 构建JPEG保存路径
#     jpeg_path = os.path.join(file_dir, os.path.splitext(file_name)[0] + ".jpg")

#     try:
#         # 打开WebP图片
#         webp_image = Image.open(webp_path)

#         # 将WebP图片保存为JPEG格式
#         jpeg_image = webp_image.convert("RGB")
#         jpeg_image.save(jpeg_path, "JPEG")

#         print(f"成功将{file_name}转换为JPEG格式，保存为{os.path.basename(jpeg_path)}")
#         os.remove(webp_path)
#     except Exception as e:
#         print(f"转换过程中出现错误：{str(e)}")


def get_html(url):
    url = url.split("?")[0]
    headers = {
        "authority": "www.xiaohongshu.com",
        "cache-control": "max-age=0",
        "sec-ch-ua": '"Chromium";v="21", " Not;A Brand";v="99"',
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": '"Windows"',
        "upgrade-insecure-requests": "1",
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36",
        "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
        "sec-fetch-site": "same-origin",
        "sec-fetch-mode": "navigate",
        "sec-fetch-user": "?1",
        "sec-fetch-dest": "document",
        "accept-language": "zh-CN,zh;q=0.9",
    }

    response = requests.get(url, headers=headers)

    return response.text


def json_content(html):
    rule = r"<script>window\.__INITIAL_STATE__=(.*?)</script>"
    js = re.search(rule, html, re.I)
    if js:
        content = js.group(1)
        return content
    else:
        return None


def get_img_urls(html):
    """获取图片地址"""
    urls = re.findall(r'url":"(http://[^\":\{\}\[\]]*?wm_1)"', html)
    return set(urls)


def get_video_urls(html):
    """获取视频地址"""
    urls = re.findall(r'masterUrl":"(http://[^\":\{\}\[\]]*?.mp4)"', html)
    return set(urls)


def fix_folder_name(folder_name):
    """
    去除不能作为文件夹名的字符
    """
    # 定义要替换的非法字符正则表达式
    illegal_chars_regex = r'[\\/:\*\?"<>\|]'
    correct_name = re.sub(illegal_chars_regex, "", folder_name)

    return correct_name


def get_note_title(html):
    title = re.findall(r'noteId.*?type.*?title":"(.*?)"', html)
    if title:
        return fix_folder_name(title[0])
    else:
        return "未知标题"


def download(url, save_path):
    response = requests.get(url, stream=True)
    if response.status_code == 200:
        with open(save_path, "wb") as f:
            for chunk in response.iter_content(1024):
                f.write(chunk)
        print("下载完成！")
    else:
        print("下载失败！")


def download_img_urls(urls):
    for n, url in enumerate(urls, 1):
        print(url)
        # 设置下载目录
        save_path = f"D:/小红书下载目录/{title}"

        if not os.path.exists(save_path):
            os.makedirs(save_path)

        webp_img = os.path.join(f"{save_path}/{n}.webp")
        download(url, webp_img)
        # webp_to_jpeg(webp_img)

    os.popen(f"explorer  {os.path.realpath(save_path)}")


def download_video_urls(urls):
    for n, url in enumerate(urls, 1):
        print(url)
        # 设置下载目录
        save_path = f"D:/小红书下载目录/{title}"

        if not os.path.exists(save_path):
            os.makedirs(save_path)

        mp4 = os.path.join(f"{save_path}/{n}.mp4")
        download(url, mp4)

    os.popen(f"explorer  {os.path.realpath(save_path)}")


if __name__ == "__main__":
    # 图片 https://www.xiaohongshu.com/explore/639aa24f000000001f001b8f
    # 视频 https://www.xiaohongshu.com/explore/64578c160000000013030eeb
    url = input("请输入笔记URL：")
    select = input("请输入数字要下载的类型：  1 图片   2 视频\n直接回车则下载图片：")
    # main(url)

    html = get_html(url)
    js = json_content(html)
    js = js.replace(r"\u002F", r"/")

    title = get_note_title(js)

    if not select.strip() or select.strip() == "1":
        all_urls = get_img_urls(js)
        print(all_urls)
        download_img_urls(all_urls)
    elif select.strip() == "2":
        all_urls = get_video_urls(js)
        print(all_urls)
        download_video_urls(all_urls)

    os.system("pause")

PHP接口版本：

<?php
 
    function get_html($url) {
        $headers = array(
            "authority" => "www.xiaohongshu.com",
            "cache-control" => "max-age=0",
            "sec-ch-ua" => '"Chromium";v="21", " Not;A Brand";v="99"',
            "sec-ch-ua-mobile" => "?0",
            "sec-ch-ua-platform" => '"Windows"',
            "upgrade-insecure-requests" => "1",
            "user-agent" => "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36",
            "accept" => "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
            "sec-fetch-site" => "same-origin",
            "sec-fetch-mode" => "navigate",
            "sec-fetch-user" => "?1",
            "sec-fetch-dest" => "document",
            "accept-language" => "zh-CN,zh;q=0.9",
        );
     
        $options = array(
            'http' => array(
                'header' => implode("\r\n", array_map(
                    function ($v, $k) {
                        return $k . ':' . $v;
                    },
                    $headers,
                    array_keys($headers)
                )),
            ),
        );
     
        $context = stream_context_create($options);
        $response = file_get_contents($url, false, $context);
     
        return $response;
    }
     
    function json_content($html) {
        $rule = '/<script>window\.__INITIAL_STATE__=(.*?)<\/script>/i';
        preg_match($rule, $html, $matches);
     
        if ($matches) {
            $content = $matches[1];
            return $content;
        } else {
            return null;
        }
    }
     
    function get_image_urls($url) {
        $html = get_html($url);
        $js = json_content($html);
        $js = str_replace("\\u002F", "/", $js);
     
        preg_match_all('/"url":"(http:\/\/[^":\{\}\[\]]*?wm_1)"/', $js, $all_urls);
     
        return array('image_urls' => $all_urls[1]);
    }
     
    if ($_SERVER['REQUEST_METHOD'] === 'GET') {
        $url = $_GET['url'];
        if ($url) {
            $result = get_image_urls($url);
            header('Content-Type: application/json');
            echo json_encode($result);
        } else {
            header('Content-Type: application/json');
            echo json_encode(array('error' => 'Missing URL parameter'));
        }
    }
     
?>

Python接口版本：

from flask import Flask, request, jsonify
import requests
import re
 
app = Flask(__name__)
 
@app.route('/')
def index():
    url = request.args.get('url')
    if url:
        result = get_image_urls(url)
        return jsonify(result)
    else:
        return jsonify({'error': 'Missing URL parameter'})
 
def get_html(url):
    headers = {
        "authority": "www.xiaohongshu.com",
        "cache-control": "max-age=0",
        "sec-ch-ua": '"Chromium";v="21", " Not;A Brand";v="99"',
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": '"Windows"',
        "upgrade-insecure-requests": "1",
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36",
        "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
        "sec-fetch-site": "same-origin",
        "sec-fetch-mode": "navigate",
        "sec-fetch-user": "?1",
        "sec-fetch-dest": "document",
        "accept-language": "zh-CN,zh;q=0.9",
    }
    response = requests.get(url, headers=headers)
    return response.text
 
def json_content(html):
    rule = r"<script>window\.__INITIAL_STATE__=(.*?)</script>"
    js = re.search(rule, html, re.I)
    if js:
        content = js.group(1)
        return content
    else:
        return None
 
def get_image_urls(url):
    html = get_html(url)
    js = json_content(html)
    js = js.replace(r"\u002F", r"/")
 
    all_urls = re.findall(r'url":"(http://[^\":\{\}\[\]]*?wm_1)"', js)
     
    return {'image_urls': all_urls}
 
if __name__ == "__main__":
    app.run(debug=True)

本站所有资源下载后请自行杀毒！
所有资源站长均在虚拟机内完成测试！

免责声明：
1、本站所发布的一切资源仅限用于学习和研究目的；
2、不得将上述内容用于商业或者非法用途，否则，一切后果请用户自负。
3、本站信息来自网络，版权争议与本站无关。
4、您必须在下载后的24个小时之内，从您的电脑中彻底删除上述内容。
5、如果您喜欢该程序，请支持正版软件，购买注册，得到更好的正版服务。

Centos虚拟机镜像下载地址：https://www.aae.ink/35201.html
Window虚拟机镜像下载地址：https://www.aae.ink/35207.html