├── .gitignore
├── 00.jpg
├── LICENSE.txt
├── MANIFEST.in
├── README.md
├── nonebot_plugin_imgexploration
    ├── __init__.py
    └── imgexploration.py
├── pyproject.toml
├── requirements.txt
└── setup.py


/.gitignore:
--------------------------------------------------------------------------------
1 | build/
2 | dist/
3 | nonebot_plugin_imgexploration.egg-info/
4 | *.html
5 | *.json
6 | 


--------------------------------------------------------------------------------
/00.jpg:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/cpuopt/nonebot_plugin_imgexploration/23a6bba5f747092ea3bea7fb391b8f64bf281913/00.jpg


--------------------------------------------------------------------------------
/LICENSE.txt:
--------------------------------------------------------------------------------
 1 | MIT License
 2 | 
 3 | Copyright (c) [year] [fullname]
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.


--------------------------------------------------------------------------------
/MANIFEST.in:
--------------------------------------------------------------------------------
 1 | include pyproject.toml
 2 | 
 3 | # Include the README
 4 | include *.md
 5 | 
 6 | # Include the license file
 7 | include LICENSE.txt
 8 | 
 9 | # Include the data files
10 | #recursive-include data *


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | <div align="center">
 2 | <a href="https://v2.nonebot.dev/"><img src="https://v2.nonebot.dev/logo.png" width="200" height="200" alt="nonebot"></a>
 3 | 
 4 | # nonebot_plugin_imgexploration 
 5 | 
 6 | _✨ [Nonebot2](https://github.com/nonebot/nonebot2) 插件，Google、Yandx和基于PicImageSearch的saucenao、ascii2d搜图  ✨_
 7 | 
 8 | 
 9 | 
10 | </div> 
11 | 
12 | **需要能稳定访问Google等网站的代理**  
13 | ## 一.**安装**
14 | ### 1.使用nb-cli安装
15 | 
16 | ```
17 | nb plugin install nonebot-plugin-imgexploration
18 | ```
19 | 
20 | 或其他任意加载方式
21 | ### 2.需要字体    
22 | ```
23 | HarmonyOS_Sans_SC_Regular.ttf  
24 | HarmonyOS_Sans_SC_Bold.ttf  
25 | HarmonyOS_Sans_SC_Light.ttf
26 | ```
27 | https://developer.harmonyos.com/cn/docs/design/des-guides/font-0000001157868583   
28 | 安装到系统字体即可
29 | 
30 | ### 3.依赖  (nb-cli或pip安装无需配置依赖)
31 | <details>
32 | <summary>展开/收起</summary>
33 | 
34 | ```
35 | pip install -r requirements.txt
36 | ```
37 | 
38 | </details>
39 | 
40 | ## 二.**配置**  
41 | ### 1.env中的配置
42 | ```
43 | #代理端口号(不使用本地代理可缺省，例如：使用软路由透明代理、程序运行在境外)
44 | proxy_port=7890  
45 | 
46 | #saucenao apikey 在https://saucenao.com/user.php?page=search-api注册获取
47 | saucenao_apikey=xxxxx 
48 | 
49 | #Google Cookies json文件路径，建议使用Chrome插件Cookie-Editor复制导出json并手动存入文件
50 | google_cookies_filepath="C:\Users\...\google_cookies.json"
51 | 
52 | #等待用户回复的超时时间(可选)
53 | #注意，nonebot2新版本该配置项格式有变化！请根据nonebot版本参照文档 https://nonebot.dev/docs/api/config#Config-session-expire-timeout
54 | #SESSION_EXPIRE_TIMEOUT=180
55 | #SESSION_EXPIRE_TIMEOUT=PT3M 
56 | ```  
57 | ## 三.**使用**  
58 | ### 
59 | ```
60 | /搜图
61 | /搜图 <图片>
62 | ```  
63 | ### **使用示例**   
64 | 
65 | <div align=center>
66 |     <img decoding="async" align="middle" src="https://p.inari.site/usr/369/63b6cfe0cd8a8.jpg" width="80%">
67 | </div>
68 | 
69 | ### 搜图结果
70 | 
71 | <div align=center>
72 |     <img decoding="async" align="middle" src="https://p.inari.site/usr/369/63b6cd6f24abc.jpg" height="1280px">
73 | </div>
74 | 


--------------------------------------------------------------------------------
/nonebot_plugin_imgexploration/__init__.py:
--------------------------------------------------------------------------------
  1 | import nonebot
  2 | import httpx
  3 | from typing import Union
  4 | from nonebot import on_command, require
  5 | from nonebot.log import logger
  6 | from nonebot.typing import T_State
  7 | from nonebot.params import Arg, CommandArg
  8 | from nonebot.plugin import PluginMetadata
  9 | from nonebot.adapters.onebot.v11 import (
 10 |     Bot,
 11 |     Message,
 12 |     MessageSegment,
 13 |     GroupMessageEvent,
 14 |     PrivateMessageEvent,
 15 | )
 16 | from .imgexploration import Cookies, Imgexploration
 17 | 
 18 | 
 19 | __plugin_meta__ = PluginMetadata(
 20 |     name="查找图片出处",
 21 |     description="通过saucenao、ascii2d、Google、Yandx查询图片出处",
 22 |     usage="command:搜图",
 23 |     type="application",
 24 |     homepage="https://github.com/cpuopt/nonebot_plugin_imgexploration",
 25 |     supported_adapters={"~onebot.v11"},
 26 |     extra={},
 27 | )
 28 | 
 29 | proxy_port = getattr(nonebot.get_driver().config, "proxy_port", None)
 30 | saucenao_apikey = getattr(nonebot.get_driver().config, "saucenao_apikey", "")
 31 | google_cookies_filepath = getattr(nonebot.get_driver().config, "google_cookies_filepath", "")
 32 | 
 33 | 
 34 | proxies = f"http://127.0.0.1:{proxy_port}" if proxy_port else None
 35 | 
 36 | 
 37 | def numspilt(args: str, max: int):
 38 |     args_list = list(args.split())
 39 |     r_li = []
 40 |     for arg in args_list:
 41 |         if arg.isnumeric() and 1 <= int(arg) <= max:
 42 |             r_li.append(int(arg))
 43 |         elif arg.isnumeric() and int(arg) >= max:
 44 |             for i in arg:
 45 |                 if i.isnumeric() and 1 <= int(i) <= max:
 46 |                     r_li.append(int(i))
 47 |     return r_li
 48 | 
 49 | 
 50 | imgexploration = on_command(cmd="搜图", priority=1, block=True)
 51 | 
 52 | 
 53 | @imgexploration.handle()
 54 | async def cmd_receive(
 55 |     event: Union[GroupMessageEvent, PrivateMessageEvent],
 56 |     state: T_State,
 57 |     pic: Message = CommandArg(),
 58 | ):
 59 |     if pic:
 60 |         state["Message_pic"] = pic
 61 | 
 62 | 
 63 | @imgexploration.got("Message_pic", prompt="请发送要搜索的图片")
 64 | async def get_pic(
 65 |     bot: Bot,
 66 |     event: Union[GroupMessageEvent, PrivateMessageEvent],
 67 |     state: T_State,
 68 |     msgpic: Message = Arg("Message_pic"),
 69 | ):
 70 |     for segment in msgpic:
 71 |         if segment.type == "image":
 72 |             pic_url: str = segment.data["url"]  # 图片链接
 73 |             logger.success(f"获取到图片: {pic_url}")
 74 |             async with httpx.AsyncClient(
 75 |                 proxy=proxies,
 76 |                 headers={
 77 |                     "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36",
 78 |                 },
 79 |             ) as client:
 80 |                 search = Imgexploration(
 81 |                     pic_url=pic_url,
 82 |                     client=client,
 83 |                     proxy=proxies,
 84 |                     saucenao_apikey=saucenao_apikey,
 85 |                     google_cookies=Cookies(google_cookies_filepath),
 86 |                 )
 87 |                 await imgexploration.send(
 88 |                     message=Message(MessageSegment.text("搜索进行中……")),
 89 |                     reply_message=True,
 90 |                 )
 91 |                 await search.doSearch()
 92 |             result_dict = search.getResultDict()
 93 |             state["result_dict"] = result_dict
 94 |             await imgexploration.send(
 95 |                 message=Message(
 96 |                     MessageSegment.image(file=result_dict["pic"]) + MessageSegment.text("请在180s内发送序号以获得对应结果的链接，一次可以发送多个序号，例如：1 5 6"),
 97 |                 ),
 98 |                 reply_message=True,
 99 |             )
100 |             break
101 | 
102 |     else:
103 |         await imgexploration.reject("你发送的不是图片，请以“图片”形式发送！")
104 | 
105 | 
106 | @imgexploration.got("need_num")
107 | async def get_num(
108 |     bot: Bot,
109 |     event: Union[GroupMessageEvent, PrivateMessageEvent],
110 |     state: T_State,
111 |     nummsg: Message = Arg("need_num"),
112 | ):
113 |     try:
114 |         args = list(map(int, str(nummsg).split()))
115 |         if args[0] == 0:
116 |             await imgexploration.finish(message=Message(MessageSegment.reply(event.message_id) + MessageSegment.text("搜图结束")))
117 |         msg = MessageSegment.text("")
118 |         res_len = len(state["result_dict"]["info"])
119 |         args = numspilt(str(nummsg), res_len)
120 |         for no in args:
121 |             url = state["result_dict"]["info"][no - 1]["url"]
122 |             msg += MessageSegment.text(f"{no} - {url}\n")
123 |         await bot.send(
124 |             event,
125 |             message=Message(msg + "你还有机会发送序号以获取链接\n发送非数字消息或0以结束搜图"),
126 |             reply_message=True,
127 |         )
128 |         await imgexploration.reject()
129 |     except (IndexError, ValueError):
130 |         logger.error("参数错误，没有发送序号，搜图结束")
131 |         await imgexploration.finish(
132 |             message=Message(MessageSegment.text(f"你没有发送序号，搜图结束！")),
133 |             reply_message=True,
134 |         )
135 | 


--------------------------------------------------------------------------------
/nonebot_plugin_imgexploration/imgexploration.py:
--------------------------------------------------------------------------------
  1 | import asyncio
  2 | import base64
  3 | import re
  4 | import traceback
  5 | from PIL import Image, ImageDraw, ImageFont, ImageFilter
  6 | from PicImageSearch import Ascii2D, Network, SauceNAO
  7 | from lxml import etree
  8 | import httpx, json
  9 | from io import BytesIO
 10 | from loguru import logger
 11 | import PIL
 12 | import urllib
 13 | 
 14 | 
 15 | class Imgexploration:
 16 |     def __init__(self, pic_url, client: httpx.AsyncClient, proxy, saucenao_apikey, google_cookies):
 17 |         """
 18 |         Parameters
 19 |         ----------
 20 |             * pic_url : 图片url
 21 |             * proxy_port : 代理端口
 22 |             * saucenao_apikey : saucenao_apikey
 23 |         """
 24 |         self.client = client
 25 |         self.__proxy = proxy
 26 |         self.__pic_url = pic_url
 27 |         self.setFront(big_size=25, nomal_size=20, small_size=15)
 28 | 
 29 |         general_header = {
 30 |             "sec-ch-ua": '"Chromium";v="104", " Not A;Brand";v="99", "Google Chrome";v="104"',
 31 |             "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36",
 32 |         }
 33 | 
 34 |         self.setHeadersCookieApikey(saucenao_apikey=saucenao_apikey, general_header=general_header, google_cookies=google_cookies)
 35 | 
 36 |     def setHeadersCookieApikey(self, saucenao_apikey, general_header, google_cookies):
 37 |         """
 38 |         Args:
 39 |         ----------
 40 |             * saucenao_apikey (str):
 41 |         """
 42 |         self.__saucenao_apikey = saucenao_apikey
 43 |         self.__generalHeader = general_header
 44 |         self.__google_cookies = google_cookies
 45 | 
 46 |     async def __getImgbytes(self):
 47 |         try:
 48 |             self.__pic_bytes = (await self.client.get(url=self.__pic_url, timeout=10)).content
 49 |             img = Image.open(BytesIO(self.__pic_bytes))
 50 |             img = img.convert("RGB")
 51 |             width = img.width
 52 |             height = img.height
 53 |             if width > 2000 or height > 2000:
 54 |                 radius = width // 1000 if width > height else height // 1000
 55 |                 img = img.resize((int(width / radius), int(height / radius)))
 56 |                 res = BytesIO()
 57 |                 img.save(res, format="JPEG")
 58 |                 self.__pic_bytes = res.getvalue()
 59 |         except Exception as e:
 60 |             logger.error(e)
 61 | 
 62 |     async def __uploadToImgops(self):
 63 |         logger.info("图片上传到Imgops")
 64 |         try:
 65 |             files = {"photo": self.__pic_bytes}
 66 |             data = {"isAjax": "true"}
 67 |             headers = {
 68 |                 "sec-ch-ua": '"Google Chrome";v="113", "Chromium";v="113", "Not-A.Brand";v="24"',
 69 |                 "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36",
 70 |                 "sec-ch-ua-platform": '"Windows"',
 71 |                 "Origin": "https://imgops.com",
 72 |                 "Referer": "https://imgops.com/",
 73 |                 "Accept-Encoding": "gzip, deflate, br",
 74 |                 "Accept-Language": "zh-CN,zh;q=0.9",
 75 |             }
 76 |             post = await self.client.post("https://imgops.com/store", files=files, data=data, headers=headers, timeout=10)
 77 | 
 78 |             self.__imgopsUrl = "https:/" + post.text
 79 |         except Exception as e:
 80 |             self.__imgopsUrl = self.__pic_url
 81 |             logger.error(e)
 82 | 
 83 |     def setFront(self, big_size: int, nomal_size: int, small_size: int):
 84 |         """
 85 |         Parameters
 86 |         ----------
 87 |             * big_size  大号字体字号
 88 |             * nomal_size : 中号字体字号
 89 |             * small_size : 小号字体字号
 90 | 
 91 |         """
 92 |         self.__font_b_size = big_size
 93 |         self.__font_b = ImageFont.truetype("HarmonyOS_Sans_SC_Regular", big_size)
 94 |         self.__font_n = ImageFont.truetype("HarmonyOS_Sans_SC_Bold", nomal_size)
 95 |         self.__font_s = ImageFont.truetype("HarmonyOS_Sans_SC_Light", small_size)
 96 | 
 97 |     @staticmethod
 98 |     async def ImageBatchDownload(urls: list, client: httpx.AsyncClient) -> list[bytes]:
 99 |         tasks = [asyncio.create_task(client.get(url)) for url in urls]
100 |         return [((await task).content) for task in tasks]
101 | 
102 |     async def __draw(self) -> bytes:
103 |         try:
104 |             font_size = self.__font_b_size
105 |             font = self.__font_b
106 |             font2 = self.__font_n
107 |             font3 = self.__font_s
108 |             num = len(self.__result_info)
109 |             width = 900
110 |             height = 200
111 |             total_height = height * num if num != 0 else 10
112 |             line_width = 2
113 |             line_fill = (200, 200, 200)
114 |             text_x = 300
115 |             logger.info(f"Drawing... total:{num}")
116 |             img = Image.new(mode="RGB", size=(width, total_height), color=(255, 255, 255))
117 | 
118 |             draw = ImageDraw.Draw(img)
119 |             margin = 20
120 |             for i in range(1, num):
121 |                 draw.line(
122 |                     (margin, i * height, width - margin, i * height),
123 |                     fill=line_fill,
124 |                     width=line_width,
125 |                 )
126 | 
127 |             vernier = 0
128 |             seat = 0
129 | 
130 |             for single in self.__result_info:
131 |                 seat += 1
132 | 
133 |                 if "thumbnail_bytes" in single:
134 |                     thumbnail = single["thumbnail_bytes"]
135 |                     try:
136 |                         thumbnail = Image.open(fp=BytesIO(thumbnail)).convert("RGB")
137 |                     except PIL.UnidentifiedImageError:
138 |                         thumbnail = Image.new(mode="RGB", size=(200, 200), color=(255, 255, 255))
139 | 
140 |                     thumbnail = thumbnail.resize((int((height - 2 * margin) * thumbnail.width / thumbnail.height), height - 2 * margin))
141 |                     if single["source"] == "ascii2d":
142 |                         thumbnail = thumbnail.filter(ImageFilter.GaussianBlur(radius=3))
143 | 
144 |                     if thumbnail.width > text_x - 2 * margin:
145 |                         thumbnail = thumbnail.crop((0, 0, text_x - 2 * margin, thumbnail.height))
146 |                         img.paste(im=thumbnail, box=(margin, vernier + margin))
147 |                     else:
148 |                         img.paste(im=thumbnail, box=(text_x - thumbnail.width - margin, vernier + margin))
149 | 
150 |                 text_ver = 2 * margin
151 |                 draw.text(
152 |                     xy=(width - margin, vernier + 10),
153 |                     text=f"NO.{seat} from {single['source']}",
154 |                     fill=(150, 150, 150),
155 |                     font=font2,
156 |                     anchor="ra",
157 |                 )
158 | 
159 |                 if single["title"]:
160 |                     text = single["title"].replace("\n", "")
161 |                     lw = font.getlength(text)
162 |                     text = text if lw < 450 else f"{text[:int(len(text)*450/lw)]}..."
163 |                     draw.text(xy=(text_x, vernier + text_ver), text="Title: ", fill=(160, 160, 160), font=font, anchor="la")
164 |                     draw.text(xy=(text_x + 60, vernier + text_ver), text=text, fill=(0, 0, 0), font=font, anchor="la")
165 |                     text_ver = text_ver + font_size + margin / 2
166 | 
167 |                 if ("similarity" in single) and single["similarity"]:  # saucenao
168 |                     text = single["similarity"]
169 |                     draw.text(xy=(text_x, vernier + text_ver), text="similarity: ", fill=(160, 160, 160), font=font, anchor="la")
170 |                     draw.text(xy=(text_x + 115, vernier + text_ver), text=f"{text}", fill=(0, 0, 0), font=font, anchor="la")
171 |                     text_ver = text_ver + font_size + margin / 2
172 | 
173 |                 if ("description" in single) and single["description"]:
174 |                     text = single["description"]
175 |                     lw = font.getlength(text)
176 |                     text = text if lw < 520 else f"{text[:int(len(text)*520/lw)]}..."
177 |                     draw.text(xy=(text_x, vernier + text_ver), text=text, fill=(0, 0, 0), font=font, anchor="la")
178 |                     text_ver = text_ver + font_size + margin / 2
179 | 
180 |                 if ("domain" in single) and single["domain"]:  # Yandex
181 |                     text = single["domain"]
182 |                     draw.text(xy=(text_x, vernier + text_ver), text="Source: ", fill=(160, 160, 160), font=font, anchor="la")
183 |                     draw.text(xy=(text_x + 86, vernier + text_ver), text=f"{text}", fill=(0, 0, 0), font=font, anchor="la")
184 |                     text_ver = text_ver + font_size + margin / 2
185 | 
186 |                 if single["url"]:
187 |                     url = single["url"]
188 |                     lw = font3.getlength(url)
189 |                     url = url if lw < 560 else f"{url[:int(len(url)*560/lw)]}..."
190 |                     draw.text(xy=(text_x, vernier + text_ver), text=url, fill=(100, 100, 100), font=font3, anchor="la")
191 |                 vernier += height
192 | 
193 |             save = BytesIO()
194 |             img.save(save, format="PNG", quality=100)
195 |             return save.getvalue()
196 |         except Exception as e:
197 |             raise e
198 | 
199 |     async def __saucenao_build_result(self, result_num=10, minsim=60, max_num=5) -> dict:
200 |         resList = []
201 |         logger.info("saucenao searching...")
202 |         try:
203 |             async with Network(proxies=self.__proxy, timeout=20) as client:
204 |                 saucenao = SauceNAO(client=client, api_key=self.__saucenao_apikey, numres=result_num)
205 |                 saucenao_result = await saucenao.search(url=self.__imgopsUrl)
206 | 
207 |                 thumbnail_urls = []
208 |                 for single in saucenao_result.raw:
209 |                     if single.similarity < minsim or single.url == "" or single.thumbnail == "":
210 |                         continue
211 |                     thumbnail_urls.append(single.thumbnail)
212 |                 thumbnail_bytes = await self.ImageBatchDownload(thumbnail_urls, self.client)
213 |                 i = 0
214 |                 for single in saucenao_result.raw:
215 |                     if single.similarity < minsim or single.url == "" or single.thumbnail == "":
216 |                         continue
217 |                     sin_di = {
218 |                         "title": single.title,  # 标题
219 |                         "thumbnail": single.thumbnail,  # 缩略图url
220 |                         "url": urllib.parse.unquote(single.url),
221 |                         "similarity": single.similarity,
222 |                         "source": "saucenao",
223 |                         "thumbnail_bytes": thumbnail_bytes[i],
224 |                     }
225 |                     i += 1
226 |                     resList.append(sin_di)
227 |                 return resList
228 |         except IndexError as e:
229 |             logger.error(e)
230 |             return []
231 |         finally:
232 |             logger.success(f"saucenao result:{len(resList)}")
233 |             return resList
234 | 
235 |     async def __google_build_result(self, result_num=5) -> dict:
236 |         google_header = {
237 |             "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=0.7",
238 |             "accept-encoding": "gzip, deflate, br, zstd:gzip, deflate, br, zstd",
239 |             "accept-language": "zh-CN,zh-HK;q=0.9,zh;q=0.8,en-US;q=0.7,en;q=0.6:zh-CN,zh-HK;q=0.9,zh;q=0.8,en-US;q=0.7,en;q=0.6",
240 |             "cache-control": "no-cache:no-cache",
241 |             "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36:Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
242 |         }
243 |         resList = []
244 |         logger.info("google searching...")
245 |         try:
246 |             params = {
247 |                 "url": self.__imgopsUrl,
248 |             }
249 |             google_lens = await self.client.get(f"https://lens.google.com/uploadbyurl", params=params, headers=google_header, timeout=10, cookies=self.__google_cookies.cookies)
250 |             self.__google_cookies.update(google_lens.headers)
251 |             redirect_url = google_lens.headers.get("location")
252 |             google_header["referer"] = str(google_lens.url)
253 |             google_lens = await self.client.get(redirect_url, headers=google_header, timeout=10, cookies=self.__google_cookies.cookies)
254 |             self.__google_cookies.update(google_lens.headers)
255 |             google_lens_text = google_lens.text
256 |             main_page = etree.HTML(google_lens_text)
257 |             elements = main_page.xpath("//span[text()='查看完全匹配的结果']/ancestor::a[1]")
258 |             if elements:
259 |                 href = "https://www.google.com" + elements[0].get("href")
260 |                 google_lens = await self.client.get(href, headers=google_header, timeout=10, cookies=self.__google_cookies.cookies)
261 |                 full_match_page = etree.HTML(google_lens.text)
262 |                 id_base64_mapping = parseBase64Image(full_match_page)
263 |                 with open("Googlelens_test.html", "w+", encoding="utf-8") as file:
264 |                     file.write(google_lens.text)
265 |                 res_items = full_match_page.xpath("//div[@id='search']/div/div/div")
266 |                 for item in res_items:
267 |                     link = item.xpath(".//a")[0].get("href")
268 |                     img_id = item.xpath(".//a//img")[0].get("id")
269 |                     title = item.xpath(".//a/div/div[2]/div[1]/text()")[0]
270 |                     img_base64 = id_base64_mapping[img_id] if img_id in id_base64_mapping.keys() else None
271 |                     img_bytes = base64.b64decode(img_base64) if img_base64 else None
272 |                     if img_bytes != None:
273 |                         sin_di = {
274 |                             "title": title,
275 |                             "thumbnail_bytes": img_bytes,
276 |                             "url": link,
277 |                             "source": "Google",
278 |                         }
279 |                         resList.append(sin_di)
280 |             else:
281 |                 pass
282 | 
283 |             return resList
284 | 
285 |         except Exception as e:
286 |             logger.error(traceback.format_exc())
287 |             with open("Googlelens_error_page.html", "w+", encoding="utf-8") as file:
288 |                 file.write(google_lens_text)
289 |             raise e
290 | 
291 |         finally:
292 |             logger.success(f"google result:{len(resList)}")
293 |             return resList
294 | 
295 |     def __ascii2d_get_external_url(self, rawhtml):
296 |         rawhtml = str(rawhtml)
297 |         external_url_li = etree.HTML(rawhtml).xpath('//div[@class="external"]/a[1]/@href')
298 |         if external_url_li:
299 |             return external_url_li[0]  # 可能的手动登记结果:list
300 |         else:
301 |             return False
302 | 
303 |     async def __ascii2d_build_result(self, sh_num: int = 2, tz_num: int = 3) -> dict:
304 |         """
305 |         Parameters
306 |         ----------
307 |             * sh_num : 色和搜索获取结果数量
308 |             * tz_num : 特征搜索获取结果数量
309 | 
310 |         """
311 |         logger.info("ascii2d searching...")
312 |         result_li = []
313 |         try:
314 |             async with Network(proxies=self.__proxy, timeout=20) as client:
315 |                 ascii2d_sh = Ascii2D(client=client, bovw=False)
316 | 
317 |                 # ascii2d_sh_result = await ascii2d_sh.search(url=self.__pic_url)
318 | 
319 |                 ascii2d_tz = Ascii2D(client=client, bovw=True)
320 |                 # ascii2d_tz_result = await ascii2d_tz.search(url=self.__pic_url)
321 | 
322 |                 ascii2d_sh_result = await asyncio.create_task(ascii2d_sh.search(url=self.__imgopsUrl))
323 |                 ascii2d_tz_result = await asyncio.create_task(ascii2d_tz.search(url=self.__imgopsUrl))
324 | 
325 |                 thumbnail_urls = []
326 |                 for single in ascii2d_tz_result.raw[0:tz_num] + ascii2d_sh_result.raw[0:sh_num]:
327 |                     external_url_li = self.__ascii2d_get_external_url(single.origin)
328 |                     if not external_url_li and not single.url:
329 |                         continue
330 |                     elif single.url:
331 |                         url = single.url
332 |                     else:
333 |                         url = external_url_li
334 |                     sin_di = {
335 |                         "title": single.title,
336 |                         "thumbnail": single.thumbnail,
337 |                         "url": urllib.parse.unquote(url),
338 |                         "source": "ascii2d",
339 |                     }
340 |                     thumbnail_urls.append(single.thumbnail)
341 |                     result_li.append(sin_di)
342 |                 thumbnail_bytes = await self.ImageBatchDownload(thumbnail_urls, self.client)
343 |                 i = 0
344 |                 for single in result_li:
345 |                     single["thumbnail_bytes"] = thumbnail_bytes[i]
346 |                     i += 1
347 |         except Exception as e:
348 |             logger.error(e)
349 |             return []
350 |         finally:
351 |             logger.success(f"ascii2d result:{len(result_li)}")
352 |             return result_li
353 | 
354 |     async def __yandex_build_result(self, result_num=5) -> dict:
355 |         """
356 |         Parameter:
357 |         ---------
358 |             * result_num : 需要的结果数量
359 |         """
360 |         logger.info("yandex searching...")
361 |         try:
362 |             yandexurl = f"https://yandex.com/images/search"
363 |             data = {
364 |                 "rpt": "imageview",
365 |                 "url": self.__imgopsUrl,
366 |             }
367 |             result_li = []
368 | 
369 |             yandexPage = await self.client.get(url=yandexurl, params=data, headers=self.__generalHeader, timeout=20)
370 |             yandexHtml = etree.HTML(yandexPage.text)
371 |             InfoJSON = yandexHtml.xpath('//*[@class="cbir-section cbir-section_name_sites"]/div/@data-state')[0]
372 |             result_dict = json.loads(InfoJSON)
373 |             thumbnail_urls = []
374 |             for single in result_dict["sites"][:result_num]:
375 |                 thumbnail_urls.append("https:" + single["thumb"]["url"])
376 |             thumbnail_bytes = await self.ImageBatchDownload(thumbnail_urls, self.client)
377 |             i = 0
378 |             for single in result_dict["sites"][:result_num]:
379 |                 sin_di = {
380 |                     "source": "Yandex",
381 |                     "title": single["title"],  # 标题
382 |                     "thumbnail": "https:" + single["thumb"]["url"],  # 预览图url
383 |                     "url": urllib.parse.unquote(single["url"]),  # 来源网址
384 |                     "description": single["description"],  # 描述
385 |                     "domain": single["domain"],  # 来源网站域名
386 |                     "thumbnail_bytes": thumbnail_bytes[i],
387 |                 }
388 |                 i += 1
389 |                 result_li.append(sin_di)
390 |             logger.success(f"yandex result:{len(result_li)}")
391 |             return result_li
392 |         except Exception as e:
393 |             raise e
394 |             logger.error(e)
395 |         finally:
396 |             return result_li
397 | 
398 |     async def doSearch(self) -> dict:
399 |         await self.__getImgbytes()
400 |         await self.__uploadToImgops()
401 |         task_saucenao = asyncio.create_task(self.__saucenao_build_result())
402 |         task_ascii2d = asyncio.create_task(self.__ascii2d_build_result())
403 |         task_google = asyncio.create_task(self.__google_build_result())
404 |         task_yandex = asyncio.create_task(self.__yandex_build_result())
405 | 
406 |         # self.__result_info = (await task_saucenao) + (await task_ascii2d) + (await task_google) + (await task_yandex)
407 |         self.__result_info = (await task_saucenao) + (await task_ascii2d) + (await task_google) + (await task_yandex)
408 |         result_pic = await self.__draw()
409 | 
410 |         self.__picNinfo = {
411 |             "pic": result_pic,
412 |             "info": self.__result_info,
413 |         }
414 | 
415 |     def getResultDict(self):
416 |         """
417 |         Returns
418 |         ----------
419 |         {
420 |             "pic": bytes,
421 |             "info": list,
422 |         }
423 |         """
424 |         return self.__picNinfo
425 | 
426 | 
427 | class Cookies:
428 | 
429 |     cookies = httpx.Cookies()
430 |     filepath: str
431 |     cookies_json = []
432 | 
433 |     def __init__(self, filepath):
434 |         self.filepath = filepath
435 | 
436 |         with open(filepath, "r") as f:
437 |             self.cookies_json = json.loads(f.read())
438 | 
439 |         for cookie in self.cookies_json:
440 |             self.cookies.set(cookie["name"], cookie["value"], cookie["domain"])
441 | 
442 |     def update(self, response_headers: httpx.Headers):
443 |         set_cookies = response_headers.get_list("set-cookie")
444 | 
445 |         if not set_cookies:
446 |             return self.cookies
447 | 
448 |         new_cookies = httpx.Cookies()
449 |         for cookie in self.cookies.jar:
450 |             new_cookies.set(cookie.name, cookie.value, cookie.domain)
451 | 
452 |         for cookie_str in set_cookies:
453 |             cookie_parts = cookie_str.split(";")
454 |             if not cookie_parts:
455 |                 continue
456 | 
457 |             name_value = cookie_parts[0].strip().split("=", 1)
458 |             if len(name_value) != 2:
459 |                 continue
460 | 
461 |             name, value = name_value
462 | 
463 |             for part in cookie_parts[1:]:
464 |                 if part.strip().lower().startswith("domain="):
465 |                     domain = part.split("=", 1)[1].strip()
466 |                     break
467 | 
468 |             new_cookies.set(name, value, domain)
469 |             for cookie in self.cookies_json:
470 |                 if cookie["name"] == name:
471 |                     cookie = {"domain": domain, "name": name, "value": value}
472 | 
473 |         self.cookies = new_cookies
474 |         self.save()
475 | 
476 |     def save(self):
477 |         with open(self.filepath, "w", encoding="utf-8") as f:
478 |             json.dump(self.cookies_json, f, ensure_ascii=False, indent=4)
479 | 
480 | def parseBase64Image(document: etree.Element) -> dict[str, str]:
481 |     """从HTML文档中解析id和对应的图片base64
482 |     """
483 |     res_dic = {}
484 |     for script in document.xpath("//script[@nonce]"):
485 |         func = script.xpath("./text()")
486 |         func_text: str = func[0] if func and len(func) > 0 else ""
487 | 
488 |         id_match = re.search(r"\['(.*?)'\]", func_text)
489 |         id = id_match.group(1) if id_match else None
490 | 
491 |         base64_match = re.search(r"data:image/jpeg;base64,(.*?)'", func_text)
492 |         b64 = base64_match.group(1).replace(r"\x3d", "=") if base64_match else None
493 | 
494 |         if id != None and b64 != None:
495 | 
496 |             if "','" in id:
497 |                 for dimg in id.split("','"):
498 |                     res_dic[dimg] = b64
499 |             else:
500 |                 res_dic[id] = b64
501 | 
502 |     return res_dic
503 | 
504 | 
505 | if __name__ == "__main__":
506 |     url = r"https://p.inari.site/usr/369/67821385a0fe3.jpg"
507 |     google_cookies = Cookies("googleaCookies.json")
508 |     proxy_port = 7890
509 | 
510 |     async def main():
511 |         async with httpx.AsyncClient(
512 |             proxies=f"http://127.0.0.1:{proxy_port}",
513 |             headers={
514 |                 "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36",
515 |             },
516 |         ) as client:
517 | 
518 |             aa = Imgexploration(
519 |                 pic_url=url,
520 |                 client=client,
521 |                 proxy=f"http://127.0.0.1:{proxy_port}",
522 |                 saucenao_apikey="",
523 |                 google_cookies=google_cookies,
524 |             )
525 |             await aa.doSearch()
526 |         img = Image.open(BytesIO(aa.getResultDict()["pic"]))
527 |         img.show()
528 |         img.save("00.jpg", format="JPEG", quality=100)
529 | 
530 |     asyncio.run(main())
531 | 


--------------------------------------------------------------------------------
/pyproject.toml:
--------------------------------------------------------------------------------
 1 | [tool.poetry]
 2 | name = "nonebot-plugin-imgexploration"
 3 | version = "0.4.4"
 4 | description = "Google、Yandx和基于PicImageSearch的saucenao、ascii2d搜图"
 5 | authors = ["cpufan"]
 6 | readme = "README.md"
 7 | packages = [{include = "nonebot_plugin_imgexploration"}]
 8 | 
 9 | [tool.poetry.dependencies]
10 | python = "^3.10"
11 | nonebot2 = "^2.0.0rc2"
12 | nonebot-adapter-onebot = "^2.1.5"
13 | brotli = "^1.1.0"
14 | PicImageSearch = "^3.9.0"
15 | httpx = "^0.23.0"
16 | lxml = "^4.9.0"
17 | loguru = "^0.6.0"
18 | pillow = "^9.0.0"
19 | 
20 | [build-system]
21 | requires = ["poetry-core"]
22 | build-backend = "poetry.core.masonry.api"
23 | 


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | httpx>=0.25.2
2 | loguru>=0.7.0
3 | lxml>=4.9.4
4 | Pillow>=10.0.1
5 | nonebot2>=2.0.0rc2
6 | nonebot-adapter-onebot>=2.1.5
7 | PicImageSearch>=3.9.7
8 | brotli>=1.1.0


--------------------------------------------------------------------------------
/setup.py:
--------------------------------------------------------------------------------
  1 | """A setuptools based setup module.
  2 | See:
  3 | https://packaging.python.org/guides/distributing-packages-using-setuptools/
  4 | https://github.com/pypa/sampleproject
  5 | """
  6 | import setuptools
  7 | import os
  8 | 
  9 | CUR_DIR = os.path.abspath(os.path.dirname(__file__))
 10 | README = os.path.join(CUR_DIR, "README.md")
 11 | with open("README.md", "r", encoding="utf-8") as fd:
 12 |     long_description = fd.read()
 13 | 
 14 | # Arguments marked as "Required" below must be included for upload to PyPI.
 15 | # Fields marked as "Optional" may be commented out.
 16 | 
 17 | setuptools.setup(
 18 |     # This is the name of your project. The first time you publish this
 19 |     # package, this name will be registered for you. It will determine how
 20 |     # users can install this project, e.g.:
 21 |     #
 22 |     # $ pip install sampleproject
 23 |     #
 24 |     # And where it will live on PyPI: https://pypi.org/project/sampleproject/
 25 |     #
 26 |     # There are some restrictions on what makes a valid project name
 27 |     # specification here:
 28 |     # https://packaging.python.org/specifications/core-metadata/#name
 29 |     # Required
 30 |     name="nonebot-plugin-imgexploration",
 31 |     # Versions should comply with PEP 440:
 32 |     # https://www.python.org/dev/peps/pep-0440/
 33 |     #
 34 |     # For a discussion on single-sourcing the version across setup.py and the
 35 |     # project code, see
 36 |     # https://packaging.python.org/en/latest/single_source_version.html
 37 |     # Required
 38 |     version="0.4.4",
 39 |     # This is a one-line description or tagline of what your project does. This
 40 |     # corresponds to the "Summary" metadata field:
 41 |     # https://packaging.python.org/specifications/core-metadata/#summary
 42 |     # Optional
 43 |     description="Nonebot2 插件，Google、Yandx和基于PicImageSearch的saucenao、ascii2d搜图",
 44 |     # This is an optional longer description of your project that represents
 45 |     # the body of text which users will see when they visit PyPI.
 46 |     #
 47 |     # Often, this is the same as your README, so you can just read it in from
 48 |     # that file directly (as we have already done above)
 49 |     #
 50 |     # This field corresponds to the "Description" metadata field:
 51 |     # https://packaging.python.org/specifications/core-metadata/#description-optional
 52 |     # Optional
 53 |     long_description=long_description,
 54 |     # Denotes that our long_description is in Markdown; valid values are
 55 |     # text/plain, text/x-rst, and text/markdown
 56 |     #
 57 |     # Optional if long_description is written in reStructuredText (rst) but
 58 |     # required for plain-text or Markdown; if unspecified, "applications should
 59 |     # attempt to render [the long_description] as text/x-rst; charset=UTF-8 and
 60 |     # fall back to text/plain if it is not valid rst" (see link below)
 61 |     #
 62 |     # This field corresponds to the "Description-Content-Type" metadata field:
 63 |     # https://packaging.python.org/specifications/core-metadata/#description-content-type-optional
 64 |     # Optional
 65 |     long_description_content_type="text/markdown",
 66 |     # This should be a valid link to your project's main homepage.
 67 |     #
 68 |     # This field corresponds to the "Home-Page" metadata field:
 69 |     # https://packaging.python.org/specifications/core-metadata/#home-page-optional
 70 |     # Optional
 71 |     url="https://github.com/cpuopt/nonebot_plugin_imgexploration",
 72 |     # This should be your name or the name of the organization which owns the
 73 |     # project.
 74 |     # Optional
 75 |     author="cpufan",
 76 |     # This should be a valid email address corresponding to the author listed
 77 |     # above.
 78 |     # Optional
 79 |     author_email="cpufan2001@gmail.com",
 80 |     # You can just specify package directories manually here if your project is
 81 |     # simple. Or you can use find_packages().
 82 |     #
 83 |     # Alternatively, if you just want to distribute a single Python file, use
 84 |     # the `py_modules` argument instead as follows, which will expect a file
 85 |     # called `my_module.py` to exist:
 86 |     #
 87 |     #   py_modules=["my_module"],
 88 |     #
 89 |     # Required
 90 |     # packages = [""],
 91 |     packages=setuptools.find_packages(),
 92 |     # This field lists other packages that your project depends on to run.
 93 |     # Any package you put here will be installed by pip when your project is
 94 |     # installed, so they must be valid existing projects.
 95 |     #
 96 |     # For an analysis of "install_requires" vs pip's requirements files see:
 97 |     # https://packaging.python.org/en/latest/requirements.html
 98 |     # Optional
 99 |     install_requires=[
100 |         "colorama>=0.4.2",
101 |         "nonebot2 >= 2.0.0rc2",
102 |         "nonebot-adapter-onebot >= 2.1.5",
103 |         "brotli >= 1.0.0",
104 |         "PicImageSearch >= 3.9.0",
105 |         "httpx >= 0.23.0",
106 |         "lxml >= 4.9.0",
107 |         "loguru >= 0.6.0",
108 |         "pillow >= 9.0.0"
109 |     ],
110 |     # To provide executable scripts, use entry points in preference to the
111 |     # "scripts" keyword. Entry points provide cross-platform support and allow
112 |     # `pip` to create the appropriate form of executable for the target
113 |     # platform.
114 |     #
115 |     # For example, the following would provide a command called `sample` which
116 |     # executes the function `main` from this package when invoked:
117 |     # Optional
118 |     entry_points={},
119 |     # Specify which Python versions you support. In contrast to the
120 |     # 'Programming Language' classifiers above, 'pip install' will check this
121 |     # and refuse to install the project if the version does not match. If you
122 |     # do not support Python 2, you can simplify this to '>=3.5' or similar, see
123 |     # https://packaging.python.org/guides/distributing-packages-using-setuptools/#python-requires
124 |     # Optional
125 |     # python_requires='>=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, <4',
126 |     # If there are data files included in your packages that need to be
127 |     # installed, specify them here.
128 |     #
129 |     # If using Python 2.6 or earlier, then these have to be included in
130 |     # MANIFEST.in as well.
131 |     # package_data={  # Optional
132 |     #    'sample': ['package_data.dat'],
133 |     # },
134 |     # Although 'package_data' is the preferred approach, in some case you may
135 |     # need to place data files outside of your packages. See:
136 |     # http://docs.python.org/3.4/distutils/setupscript.html#installing-additional-files
137 |     #
138 |     # In this case, 'data_file' will be installed into '<sys.prefix>/my_data'
139 |     # Optional
140 |     # data_files=[('my_data', ['data/data_file'])],
141 |     # Classifiers help users find your project by categorizing it.
142 |     #
143 |     # For a list of valid classifiers, see https://pypi.org/classifiers/
144 |     # Optional
145 |     classifiers=(
146 |         # How mature is this project? Common values are
147 |         #   3 - Alpha
148 |         #   4 - Beta
149 |         #   5 - Production/Stable
150 |         "Development Status :: 3 - Alpha",
151 |         # Indicate who your project is intended for
152 |         "Intended Audience :: Developers",
153 |         "Topic :: Software Development :: Build Tools",
154 |         # Pick your license as you wish
155 |         "License :: OSI Approved :: MIT License",
156 |         # Specify the Python versions you support here. In particular, ensure
157 |         # that you indicate whether you support Python 2, Python 3 or both.
158 |         # These classifiers are *not* checked by 'pip install'. See instead
159 |         # 'python_requires' below.
160 |         "Programming Language :: Python :: 3.10",
161 |         "Programming Language :: Python :: 3.11",
162 |         "Programming Language :: Python",
163 |     ),
164 |     # This field adds keywords for your project which will appear on the
165 |     # project page. What does your project relate to?
166 |     #
167 |     # Note that this is a string of words separated by whitespace, not a list.
168 |     # Optional
169 |     keywords="nonebot nonebot-plugin imagesearch",
170 |     # When your source code is in a subdirectory under the project root, e.g.
171 |     # `src/`, it is necessary to specify the `package_dir` argument.
172 |     # Optional
173 |     # package_dir={'': 'src'},
174 |     # List additional URLs that are relevant to your project as a dict.
175 |     #
176 |     # This field corresponds to the "Project-URL" metadata fields:
177 |     # https://packaging.python.org/specifications/core-metadata/#project-url-multiple-use
178 |     #
179 |     # Examples listed include a pattern for specifying where the package tracks
180 |     # issues, where the source is hosted, where to say thanks to the package
181 |     # maintainers, and where to support the project financially. The key is
182 |     # what's used to render the link text on PyPI.
183 |     # project_urls={  # Optional
184 |     #    'Bug Reports': 'https://github.com/pypa/sampleproject/issues',
185 |     #    'Funding': 'https://donate.pypi.org',
186 |     #    'Say Thanks!': 'http://saythanks.io/to/example',
187 |     #    'Source': 'https://github.com/pypa/sampleproject/',
188 |     # },
189 | )
190 | 


--------------------------------------------------------------------------------