mirror of
https://github.com/JoeanAmier/XHS-Downloader.git
synced 2025-12-26 04:48:05 +08:00
新增 Web API 模式
This commit is contained in:
JoeanAmier
parent
e26d4875e3
commit
bd0780c344
61
README.md
61
README.md
@ -28,7 +28,7 @@
|
||||
<li>✅ 支持命令行下载作品文件</li>
|
||||
<li>✅ 从浏览器读取 Cookie</li>
|
||||
<li>✅ 自定义文件名称格式</li>
|
||||
<li>☑️ 支持 API 调用功能</li>
|
||||
<li>✅ 支持 API 调用功能</li>
|
||||
</ul>
|
||||
<ul><b>脚本功能</b>
|
||||
<li>✅ 下载小红书无水印作品文件</li>
|
||||
@ -70,14 +70,66 @@
|
||||
<li>运行 <code>main.py</code> 即可使用</li>
|
||||
</ol>
|
||||
<h1>🛠 命令行模式</h1>
|
||||
<p>项目支持命令行运行模式，若想要下载图文作品的部分图片，可以使用此模式传入需要下载的图片序号！</p>
|
||||
<p>可以使用命令行从浏览器读取 Cookie 并写入配置文件！注意需要关闭对应浏览器才能读取数据！</p>
|
||||
<p><code>bool</code> 类型参数支持使用 <code>true</code>、<code>false</code>、<code>1</code>、<code>0</code>、<code>yes</code>、<code>no</code>、<code>on</code> 或 <code>off</code>（不区分大小写）来设置。</p>
|
||||
<p>项目支持命令行运行模式，若想要下载图文作品的部分图片，可以使用此模式设置需要下载的图片序号！</p>
|
||||
<p>可以使用命令行<b>从浏览器读取 Cookie 并写入配置文件</b>！注意需要关闭浏览器才能读取数据！</p>
|
||||
<p>命令示例：<code>python .\main.py --browser_cookie Chrome --update_settings</code></p>
|
||||
<p><code>bool</code> 类型参数支持使用 <code>true</code>、<code>false</code>、<code>1</code>、<code>0</code>、<code>yes</code>、<code>no</code>、<code>on</code> 或 <code>off</code>（不区分大小写）来设置。</p>
|
||||
<hr>
|
||||
<img src="static/screenshot/命令行模式截图1.png" alt="">
|
||||
<hr>
|
||||
<img src="static/screenshot/命令行模式截图2.png" alt="">
|
||||
<h1>🖥 服务器模式</h1>
|
||||
<p><b>启动：</b>运行命令：<code>python .\main.py server</code></p>
|
||||
<p><b>关闭：</b>按下 <code>Ctrl</code> + <code>C</code> 关闭服务器</p>
|
||||
<p><b>请求接口：</b><code>/xhs/</code></p>
|
||||
<p><b>请求类型：</b><code>POST</code></p>
|
||||
<p><b>请求参数：</b></p>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th align="center">参数</th>
|
||||
<th align="center">类型</th>
|
||||
<th align="center">含义</th>
|
||||
<th align="center">默认值</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td align="center">url</td>
|
||||
<td align="center">str</td>
|
||||
<td align="center">小红书作品链接，自动提取，不支持多链接</td>
|
||||
<td align="center">无</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">download</td>
|
||||
<td align="center">bool</td>
|
||||
<td align="center">是否下载作品文件；设置为 <code>true</code> 将会耗费更多时间</td>
|
||||
<td align="center">false</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">index</td>
|
||||
<td align="center">str</td>
|
||||
<td align="center">下载指定序号的图片文件，仅对图文作品生效；多个序号之间使用空格分隔；<code>download</code> 参数设置为 <code>false</code> 时不生效</td>
|
||||
<td align="center">null</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">skip</td>
|
||||
<td align="center">bool</td>
|
||||
<td align="center">是否跳过存在下载记录的作品；设置为 <code>true</code> 将不会返回存在下载记录的作品数据</td>
|
||||
<td align="center">false</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<p><b>代码示例：</b></p>
|
||||
<pre>
|
||||
def api_demo():
|
||||
server = "http://127.0.0.1:8080"
|
||||
data = {
|
||||
"url": "https://www.xiaohongshu.com/explore/123456789",
|
||||
}
|
||||
response = requests.post(server, data=data)
|
||||
print(response.json())
|
||||
</pre>
|
||||
<h1>🕹 用户脚本</h1>
|
||||
<img src="static/screenshot/用户脚本截图1.png" alt="">
|
||||
<hr>
|
||||
@ -235,6 +287,7 @@ async def example():
|
||||
<h1>🌐 Cookie</h1>
|
||||
<ol>
|
||||
<li>打开浏览器（可选无痕模式启动），访问 <code>https://www.xiaohongshu.com/explore</code></li>
|
||||
<li>登录小红书账号（可跳过）</li>
|
||||
<li>按下 <code>F12</code> 打开开发人员工具</li>
|
||||
<li>选择 <code>网络</code> 选项卡</li>
|
||||
<li>勾选 <code>保留日志</code></li>
|
||||
|
||||
Binary file not shown.
@ -255,3 +255,18 @@ msgstr "Format of works file name"
|
||||
|
||||
msgid "邀请链接："
|
||||
msgstr "Invitation link: "
|
||||
|
||||
msgid "获取小红书作品数据成功"
|
||||
msgstr "Successfully obtained data on Xiaohongshu's works"
|
||||
|
||||
msgid "获取小红书作品数据失败"
|
||||
msgstr "Failed to obtain data on Xiaohongshu's works"
|
||||
|
||||
msgid "Web API 服务器已启动！"
|
||||
msgstr "Web API server started!"
|
||||
|
||||
msgid "Web API 服务器已关闭！"
|
||||
msgstr "Web API server has been shut down!"
|
||||
|
||||
msgid "服务器主机及端口: {0}"
|
||||
msgstr "Server host and port: {0}"
|
||||
|
||||
@ -255,3 +255,18 @@ msgstr ""
|
||||
|
||||
msgid "邀请链接："
|
||||
msgstr ""
|
||||
|
||||
msgid "获取小红书作品数据成功"
|
||||
msgstr ""
|
||||
|
||||
msgid "获取小红书作品数据失败"
|
||||
msgstr ""
|
||||
|
||||
msgid "Web API 服务器已启动！"
|
||||
msgstr ""
|
||||
|
||||
msgid "Web API 服务器已关闭！"
|
||||
msgstr ""
|
||||
|
||||
msgid "服务器主机及端口: {0}"
|
||||
msgstr ""
|
||||
|
||||
16
main.py
16
main.py
@ -1,6 +1,7 @@
|
||||
from asyncio import run
|
||||
from sys import argv
|
||||
|
||||
from source import Settings
|
||||
from source import XHS
|
||||
from source import XHSDownloader
|
||||
from source import cli
|
||||
@ -47,13 +48,20 @@ async def example():
|
||||
print(await xhs.extract(multiple_links, download, ))
|
||||
|
||||
|
||||
async def main():
|
||||
async def app():
|
||||
async with XHSDownloader() as xhs:
|
||||
await xhs.run_async()
|
||||
|
||||
|
||||
async def server():
|
||||
async with XHS(**Settings().run()) as xhs:
|
||||
await xhs.run_server()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
if len(argv) > 1:
|
||||
cli()
|
||||
if len(argv) == 1:
|
||||
run(app())
|
||||
elif argv[1] == "server":
|
||||
run(server())
|
||||
else:
|
||||
run(main())
|
||||
cli()
|
||||
|
||||
@ -107,7 +107,7 @@ class Setting(Screen):
|
||||
"language": self.query_one("#language").value,
|
||||
"image_download": self.query_one("#image_download").value,
|
||||
"video_download": self.query_one("#video_download").value,
|
||||
"server": False,
|
||||
# "server": False,
|
||||
})
|
||||
|
||||
@on(Button.Pressed, "#abandon")
|
||||
|
||||
@ -1,5 +1,6 @@
|
||||
from .CLI import cli
|
||||
from .TUI import XHSDownloader
|
||||
from .application import XHS
|
||||
from .module import Settings
|
||||
|
||||
__all__ = ['XHS', 'XHSDownloader', 'cli']
|
||||
__all__ = ['XHS', 'XHSDownloader', 'cli', 'Settings', ]
|
||||
|
||||
@ -1,3 +1,4 @@
|
||||
from asyncio import CancelledError
|
||||
from asyncio import Event
|
||||
from asyncio import Queue
|
||||
from asyncio import QueueEmpty
|
||||
@ -9,6 +10,7 @@ from re import compile
|
||||
from typing import Callable
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from aiohttp import web
|
||||
from pyperclip import paste
|
||||
|
||||
from source.expansion import BrowserCookie
|
||||
@ -22,6 +24,7 @@ from source.module import (
|
||||
ERROR,
|
||||
WARNING,
|
||||
MASTER,
|
||||
REPOSITORY,
|
||||
)
|
||||
from source.module import Translate
|
||||
from source.module import logging
|
||||
@ -62,7 +65,7 @@ class XHS:
|
||||
video_download=True,
|
||||
folder_mode=False,
|
||||
language="zh_CN",
|
||||
server=False,
|
||||
# server=False,
|
||||
transition: Callable[[str], str] = None,
|
||||
read_cookie: int | str = None,
|
||||
*args,
|
||||
@ -85,6 +88,7 @@ class XHS:
|
||||
image_download,
|
||||
video_download,
|
||||
folder_mode,
|
||||
# server,
|
||||
self.message,
|
||||
)
|
||||
self.html = Html(self.manager)
|
||||
@ -98,7 +102,8 @@ class XHS:
|
||||
self.clipboard_cache: str = ""
|
||||
self.queue = Queue()
|
||||
self.event = Event()
|
||||
self.server = server
|
||||
self.runner = self.init_server()
|
||||
self.site = None
|
||||
|
||||
def __extract_image(self, container: dict, data: Namespace):
|
||||
container["下载地址"] = self.image.get_image_link(
|
||||
@ -279,3 +284,50 @@ class XHS:
|
||||
def read_browser_cookie(value: str | int) -> str:
|
||||
return BrowserCookie.get(
|
||||
value, domain="xiaohongshu.com") if value else ""
|
||||
|
||||
@staticmethod
|
||||
async def index(request):
|
||||
return web.HTTPFound(REPOSITORY)
|
||||
|
||||
async def handle(self, request):
|
||||
data = await request.post()
|
||||
url = data.get("url")
|
||||
download = data.get("download", False)
|
||||
index = data.get("index")
|
||||
skip = data.get("skip", False)
|
||||
url = await self.__extract_links(url, None)
|
||||
if not url:
|
||||
msg = self.message("提取小红书作品链接失败")
|
||||
data = None
|
||||
else:
|
||||
if data := await self.__deal_extract(url[0], download, index, None, None, not skip, ):
|
||||
msg = self.message("获取小红书作品数据成功")
|
||||
else:
|
||||
msg = self.message("获取小红书作品数据失败")
|
||||
data = None
|
||||
return web.json_response(dict(message=msg, url=url[0], data=data))
|
||||
|
||||
def init_server(self, ):
|
||||
app = web.Application(debug=True)
|
||||
app.router.add_get('/', self.index)
|
||||
app.router.add_post('/xhs/', self.handle)
|
||||
return web.AppRunner(app)
|
||||
|
||||
async def run_server(self, log=None, ):
|
||||
try:
|
||||
await self.start_server(log)
|
||||
while True:
|
||||
await sleep(3600) # 保持服务器运行
|
||||
except (CancelledError, KeyboardInterrupt):
|
||||
await self.close_server(log)
|
||||
|
||||
async def start_server(self, log=None, ):
|
||||
await self.runner.setup()
|
||||
self.site = web.TCPSite(self.runner, "0.0.0.0")
|
||||
await self.site.start()
|
||||
logging(log, self.message("Web API 服务器已启动！"))
|
||||
logging(log, self.message("服务器主机及端口: {0}".format(self.site.name, )))
|
||||
|
||||
async def close_server(self, log=None, ):
|
||||
await self.runner.cleanup()
|
||||
logging(log, self.message("Web API 服务器已关闭！"))
|
||||
|
||||
@ -13,5 +13,5 @@ class Video:
|
||||
|
||||
@classmethod
|
||||
def get_video_link(cls, data: Namespace) -> list:
|
||||
return [Html.format_url(f"https://sns-video-hw.xhscdn.com/{t}")] if (
|
||||
return [Html.format_url(f"https://sns-video-bd.xhscdn.com/{t}")] if (
|
||||
t := data.safe_extract(".".join(cls.VIDEO_LINK))) else []
|
||||
|
||||
@ -50,6 +50,7 @@ class Manager:
|
||||
image_download: bool,
|
||||
video_download: bool,
|
||||
folder_mode: bool,
|
||||
# server: bool,
|
||||
transition: Callable[[str], str],
|
||||
):
|
||||
self.root = root
|
||||
@ -77,6 +78,7 @@ class Manager:
|
||||
self.message = transition
|
||||
self.image_download = self.check_bool(image_download, True)
|
||||
self.video_download = self.check_bool(video_download, True)
|
||||
# self.server = self.check_bool(server, False)
|
||||
|
||||
def __check_path(self, path: str) -> Path:
|
||||
if not path:
|
||||
|
||||
@ -3,6 +3,8 @@ from json import load
|
||||
from pathlib import Path
|
||||
from platform import system
|
||||
|
||||
from .static import ROOT
|
||||
|
||||
__all__ = ['Settings']
|
||||
|
||||
|
||||
@ -23,11 +25,11 @@ class Settings:
|
||||
"video_download": True,
|
||||
"folder_mode": False,
|
||||
"language": "zh_CN",
|
||||
"server": False,
|
||||
# "server": False,
|
||||
}
|
||||
encode = "UTF-8-SIG" if system() == "Windows" else "UTF-8"
|
||||
|
||||
def __init__(self, root: Path):
|
||||
def __init__(self, root: Path = ROOT):
|
||||
self.file = root.joinpath("./settings.json")
|
||||
|
||||
def run(self):
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
// ==UserScript==
|
||||
// @name XHS-Downloader
|
||||
// @namespace https://github.com/JoeanAmier/XHS-Downloader
|
||||
// @version 1.4.3
|
||||
// @version 1.4.4
|
||||
// @description 提取小红书作品/用户链接，下载小红书无水印图文/视频作品文件
|
||||
// @author JoeanAmier
|
||||
// @match http*://xhslink.com/*
|
||||
@ -42,7 +42,7 @@
|
||||
2. 提取账号发布、收藏、点赞作品链接时，脚本会尝试自动滚动屏幕直至加载全部作品，滚动检测间隔：2.5 秒
|
||||
3. 提取搜索结果作品、用户链接时，脚本会自动滚动屏幕以尝试加载更多内容，滚动屏幕次数：10 次
|
||||
4. 可以修改滚动检测间隔、滚动屏幕次数，修改后立即生效；亦可关闭自动滚动屏幕功能，手动滚动屏幕加载内容
|
||||
5. XHS-Downloader 用户脚本仅实现可见即可得的数据采集功能，无任何破解功能
|
||||
5. XHS-Downloader 用户脚本仅实现可见即可得的数据采集功能，无任何收费功能和破解功能
|
||||
|
||||
项目开源地址：https://github.com/JoeanAmier/XHS-Downloader
|
||||
`
|
||||
@ -132,7 +132,7 @@
|
||||
|
||||
const generateVideoUrl = note => {
|
||||
try {
|
||||
return [`https://sns-video-hw.xhscdn.com/${note.video.consumer.originVideoKey}`];
|
||||
return [`https://sns-video-bd.xhscdn.com/${note.video.consumer.originVideoKey}`];
|
||||
} catch (error) {
|
||||
console.error("Error generating video URL:", error);
|
||||
return [];
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user