mirror of
https://github.com/zhenxun-org/zhenxun_bot.git
synced 2026-10-01 01:30:04 +08:00
first_commit .gitignore
This commit is contained in:
hibiki
@@ -0,0 +1,149 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import traceback
|
||||
from typing import Dict
|
||||
|
||||
from aiohttp.client_exceptions import ClientError
|
||||
from nonebot.plugin import on_command, on_message
|
||||
from nonebot.adapters.cqhttp import Bot, MessageEvent, GroupMessageEvent
|
||||
from nonebot.typing import T_State
|
||||
from services.log import logger
|
||||
from util.utils import get_message_text, get_message_imgs
|
||||
from configs.config import MAX_FIND_IMG_COUNT
|
||||
|
||||
from .ex import get_des as get_des_ex
|
||||
from .iqdb import get_des as get_des_iqdb
|
||||
from .saucenao import get_des as get_des_sau
|
||||
from .ascii2d import get_des as get_des_asc
|
||||
from .trace import get_des as get_des_trace
|
||||
from .yandex import get_des as get_des_yandex
|
||||
|
||||
|
||||
async def get_des(url: str, mode: str, user_id: int):
|
||||
"""
|
||||
:param url: 图片链接
|
||||
:param mode: 图源
|
||||
:return:
|
||||
"""
|
||||
if mode == "iqdb":
|
||||
async for msg in get_des_iqdb(url):
|
||||
yield msg
|
||||
elif mode == "ex":
|
||||
async for msg in get_des_ex(url):
|
||||
yield msg
|
||||
elif mode == "trace":
|
||||
async for msg in get_des_trace(url):
|
||||
yield msg
|
||||
elif mode == "yandex":
|
||||
async for msg in get_des_yandex(url):
|
||||
yield msg
|
||||
elif mode.startswith("asc"):
|
||||
async for msg in get_des_asc(url, user_id):
|
||||
yield msg
|
||||
else:
|
||||
async for msg in get_des_sau(url, user_id):
|
||||
yield msg
|
||||
|
||||
|
||||
setu = on_command("识图", aliases={"search"}, block=True, priority=5)
|
||||
|
||||
|
||||
@setu.handle()
|
||||
async def handle_first_receive(bot: Bot, event: MessageEvent, state: T_State):
|
||||
msg = get_message_text(event.json())
|
||||
imgs = get_message_imgs(event.json())
|
||||
if msg in ['帮助']:
|
||||
await setu.finish('示例：\n\t识图 (图片)\n\t识图asc (图片)')
|
||||
if imgs:
|
||||
state["setu"] = imgs[0]
|
||||
if msg:
|
||||
state["mod"] = msg
|
||||
|
||||
|
||||
# ex/nao/trace/iqdb/ascii2d
|
||||
# @setu.got("mod", prompt="从哪里查找呢? ex/nao/trace/iqdb/ascii2d")
|
||||
# async def get_func(bot: Bot, event: MessageEvent, state: dict):
|
||||
# pass
|
||||
|
||||
@setu.args_parser
|
||||
async def get_setu(bot: Bot, event: MessageEvent, state: T_State):
|
||||
imgs = get_message_imgs(event.json())
|
||||
msg = get_message_text(event.json())
|
||||
if not imgs:
|
||||
await setu.reject()
|
||||
if msg:
|
||||
state['mod'] = msg
|
||||
state["setu"] = imgs[0]
|
||||
|
||||
|
||||
@setu.got("setu", prompt="图呢？")
|
||||
async def get_setu(bot: Bot, event: MessageEvent, state: T_State):
|
||||
"""
|
||||
发现没有的时候要发问
|
||||
:return:
|
||||
"""
|
||||
url: str = state["setu"]
|
||||
mod: str = state["mod"] if state.get("mod") else "nao" # 模式
|
||||
try:
|
||||
await bot.send(event=event, message="正在处理图片")
|
||||
idx = 1
|
||||
async for msg in get_des(url, mod, event.user_id):
|
||||
await bot.send(event=event, message=msg)
|
||||
if idx == MAX_FIND_IMG_COUNT:
|
||||
break
|
||||
idx += 1
|
||||
logger.info(f"(USER {event.user_id}, GROUP "
|
||||
f"{event.group_id if event.message_type != 'private' else 'private'}) 识图:{url}")
|
||||
# image_data: List[Tuple] = await get_pic_from_url(url)
|
||||
# await setu.finish("hso")
|
||||
except IndexError:
|
||||
# await bot.send(event, traceback.format_exc())
|
||||
await setu.finish("参数错误")
|
||||
except ClientError:
|
||||
await setu.finish("连接失败")
|
||||
|
||||
|
||||
pic_map: Dict[str, str] = {} # 保存这个群的其阿金一张色图 {"123456":http://xxx"}
|
||||
|
||||
|
||||
async def check_pic(bot: Bot, event: MessageEvent, state: T_State) -> bool:
|
||||
if isinstance(event, MessageEvent):
|
||||
for msg in event.message:
|
||||
if msg.type == "image":
|
||||
url: str = msg.data["url"]
|
||||
state["url"] = url
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
notice_pic = on_message(check_pic, block=False, priority=1)
|
||||
|
||||
|
||||
@notice_pic.handle()
|
||||
async def handle_pic(bot: Bot, event: GroupMessageEvent, state: T_State):
|
||||
try:
|
||||
group_id: str = str(event.group_id)
|
||||
pic_map.update({group_id: state["url"]})
|
||||
except AttributeError:
|
||||
pass
|
||||
|
||||
|
||||
previous = on_command("上一张图是什么", aliases={"上一张", "这是什么"})
|
||||
|
||||
|
||||
@previous.handle()
|
||||
async def handle_previous(bot: Bot, event: GroupMessageEvent, state: T_State):
|
||||
await bot.send(event=event, message="processing...")
|
||||
try:
|
||||
url: str = pic_map[str(event.group_id)]
|
||||
idx = 1
|
||||
async for msg in get_des(url, "nao", event.user_id):
|
||||
await bot.send(event=event, message=msg)
|
||||
if idx == MAX_FIND_IMG_COUNT:
|
||||
break
|
||||
idx += 1
|
||||
except IndexError:
|
||||
await previous.finish("参数错误")
|
||||
except ClientError:
|
||||
await previous.finish("连接错误")
|
||||
except KeyError:
|
||||
await previous.finish("没有图啊QAQ")
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,63 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from typing import List, Tuple
|
||||
from urllib.parse import urljoin
|
||||
import aiofiles
|
||||
from util.utils import get_local_proxy
|
||||
from util.user_agent import get_user_agent
|
||||
from configs.path_config import IMAGE_PATH
|
||||
from asyncio.exceptions import TimeoutError
|
||||
from util.init_result import image
|
||||
|
||||
from lxml.html import fromstring
|
||||
import aiohttp
|
||||
|
||||
|
||||
def parse_html(html: str):
|
||||
selector = fromstring(html)
|
||||
for tag in selector.xpath('//div[@class="container"]/div[@class="row"]/div/div[@class="row item-box"]')[1:5]:
|
||||
if pic_url := tag.xpath('./div/img[@loading="lazy"]/@src'): # 缩略图url
|
||||
pic_url = urljoin("https://ascii2d.net/", pic_url[0])
|
||||
if description := tag.xpath('./div/div/h6/a[1]/text()'): # 名字
|
||||
description = description[0]
|
||||
if author := tag.xpath('./div/div/h6/a[2]/text()'): # 作者
|
||||
author = author[0]
|
||||
if origin_url := tag.xpath('./div/div/h6/a[1]/@href'): # 原图地址
|
||||
origin_url = origin_url[0]
|
||||
if author_url := tag.xpath('./div/div/h6/a[2]/@href'): # 作者地址
|
||||
author_url = author_url[0]
|
||||
yield pic_url, description, author, origin_url, author_url
|
||||
|
||||
pass
|
||||
|
||||
|
||||
async def get_pic_from_url(url: str):
|
||||
real_url = "https://ascii2d.net/search/url/" + url
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.get(real_url) as resp:
|
||||
html: str = await resp.text()
|
||||
return [i for i in parse_html(html)]
|
||||
|
||||
|
||||
async def get_des(url: str, user_id):
|
||||
image_data: List[Tuple] = await get_pic_from_url(url)
|
||||
if not image_data:
|
||||
msg: str = "找不到高相似度的"
|
||||
yield msg
|
||||
return
|
||||
for pic in image_data:
|
||||
msg = await download_img(pic[0], user_id) + "\n"
|
||||
for i in pic[1:]:
|
||||
msg = msg + f"{i}\n"
|
||||
yield msg
|
||||
|
||||
|
||||
async def download_img(url, user_id):
|
||||
try:
|
||||
async with aiohttp.ClientSession(headers=get_user_agent()) as session:
|
||||
async with session.get(url, proxy=get_local_proxy(), timeout=7) as response:
|
||||
async with aiofiles.open(IMAGE_PATH + f'temp/{user_id}_pic_find.png', 'wb') as f:
|
||||
await f.write(await response.read())
|
||||
return image(f'{user_id}_pic_find.png', 'temp')
|
||||
except TimeoutError:
|
||||
return image(url)
|
||||
|
||||
@@ -0,0 +1,107 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from base64 import b64encode
|
||||
from typing import List, Tuple
|
||||
import io
|
||||
|
||||
from lxml.html import fromstring
|
||||
import aiohttp
|
||||
import nonebot
|
||||
from aiohttp.client_exceptions import InvalidURL
|
||||
from nonebot.adapters.cqhttp import MessageSegment
|
||||
|
||||
from .formdata import FormData
|
||||
|
||||
driver = nonebot.get_driver()
|
||||
cookie: str = driver.config.ex_cookie
|
||||
proxy: str = driver.config.proxy
|
||||
target: str = "https://exhentai.org/upload/image_lookup.php"
|
||||
|
||||
headers = {
|
||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
|
||||
'Accept-Encoding': 'gzip, deflate',
|
||||
'Accept-Language': 'zh-CN,zh;q=0.9',
|
||||
'Cache-Control': 'max-age=0',
|
||||
'Connection': 'keep-alive',
|
||||
'Content-Type': 'multipart/form-data; boundary=----WebKitFormBoundaryB0NrMSYMfjY5r0l1',
|
||||
'Host': 'exhentai.org',
|
||||
'Origin': 'https://exhentai.org',
|
||||
'Referer': 'https://exhentai.org/?filesearch=1',
|
||||
'Sec-Fetch-Dest': 'document',
|
||||
'Sec-Fetch-Mode': 'navigate',
|
||||
'Sec-Fetch-Site': 'same-origin',
|
||||
'Sec-Fetch-User': '?1',
|
||||
'Upgrade-Insecure-Requests': '1',
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36'}
|
||||
|
||||
if cookie:
|
||||
headers['Cookie'] = cookie
|
||||
else:
|
||||
headers['Host'] = 'e-hentai.org'
|
||||
headers['Origin'] = 'https://e-hentai.org'
|
||||
headers['Referer'] = 'https://e-hentai.org/?filesearch=1'
|
||||
target: str = "https://e-hentai.org/upload/image_lookup.php"
|
||||
|
||||
|
||||
def parse_html(html: str):
|
||||
"""
|
||||
解析exhentai返回的数据
|
||||
:param html:
|
||||
:return:
|
||||
"""
|
||||
selector = fromstring(html)
|
||||
hrefs = selector.xpath('//td[@class="gl3c glname"]/a/@href')
|
||||
names = selector.xpath('//td[@class="gl3c glname"]/a/div[1]/text()')
|
||||
pics = selector.xpath('//tr/td[@class="gl2c"]/div[@class="glthumb"]/div[1]/img/@src') # 缩略图
|
||||
for name, href, pic in zip(names, hrefs, pics):
|
||||
yield name, href, pic
|
||||
|
||||
|
||||
async def get_pic_from_url(url: str):
|
||||
"""
|
||||
从接受到的picurl获取图片信息
|
||||
:param url:
|
||||
:return:
|
||||
"""
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.get(url) as resp:
|
||||
content = io.BytesIO(await resp.read())
|
||||
# Content_Length = resp.content_length
|
||||
data = FormData(boundary="----WebKitFormBoundaryB0NrMSYMfjY5r0l1")
|
||||
data.add_field(name="sfile", value=content, content_type="image/jpeg",
|
||||
filename="0.jpg")
|
||||
data.add_field(name="f_sfile", value="search")
|
||||
data.add_field(name="fs_similar", value="on")
|
||||
async with session.post(target, data=data, headers=headers, proxy=proxy) as res:
|
||||
html = await res.text()
|
||||
return [i for i in parse_html(html)]
|
||||
|
||||
|
||||
async def get_content_from_url(url: str):
|
||||
"""
|
||||
从url 获得b64 encode
|
||||
:param url:
|
||||
:return:
|
||||
"""
|
||||
try:
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.get(url, headers=headers) as resp:
|
||||
return "base64://" + b64encode(await resp.read()).decode()
|
||||
except aiohttp.client_exceptions.InvalidURL:
|
||||
return url
|
||||
|
||||
|
||||
async def get_des(url: str):
|
||||
"""
|
||||
迭代要发送的信息
|
||||
:param url:
|
||||
:return:
|
||||
"""
|
||||
image_data: List[Tuple] = await get_pic_from_url(url)
|
||||
if not image_data:
|
||||
msg: str = "找不到高相似度的"
|
||||
yield msg
|
||||
return
|
||||
for name, href, pic_url in image_data:
|
||||
content = await get_content_from_url(pic_url)
|
||||
msg = MessageSegment.image(file=content) + f"\n本子名称：{name}\n" + f"链接{href}\n"
|
||||
yield msg
|
||||
@@ -0,0 +1,27 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from typing import Any, Iterable, List, Optional
|
||||
|
||||
from aiohttp import FormData as _FormData
|
||||
import aiohttp.multipart as multipart
|
||||
|
||||
|
||||
class FormData(_FormData):
|
||||
def __init__(
|
||||
self,
|
||||
fields: Iterable[Any] = (),
|
||||
quote_fields: bool = True,
|
||||
charset: Optional[str] = None,
|
||||
boundary: Optional[str] = None
|
||||
) -> None:
|
||||
self._writer = multipart.MultipartWriter("form-data", boundary=boundary)
|
||||
self._fields = [] # type: List[Any]
|
||||
self._is_multipart = False
|
||||
self._is_processed = False
|
||||
self._quote_fields = quote_fields
|
||||
self._charset = charset
|
||||
|
||||
if isinstance(fields, dict):
|
||||
fields = list(fields.items())
|
||||
elif not isinstance(fields, (list, tuple)):
|
||||
fields = (fields,)
|
||||
self.add_fields(*fields)
|
||||
@@ -0,0 +1,79 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import asyncio
|
||||
from typing import List, Tuple
|
||||
import io
|
||||
|
||||
from urllib.parse import urljoin
|
||||
from lxml.html import fromstring
|
||||
import aiohttp
|
||||
from nonebot.adapters.cqhttp import MessageSegment
|
||||
|
||||
from .formdata import FormData
|
||||
|
||||
headers = {
|
||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
|
||||
'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'zh-CN,zh;q=0.9', 'Cache-Control': 'max-age=0',
|
||||
'Connection': 'keep-alive',
|
||||
'Content-Type': 'multipart/form-data; boundary=----WebKitFormBoundaryuwjSiBcpPag4k159',
|
||||
'Cookie': 'Hm_lvt_765ecde8c11b85f1ac5f168fa6e6821f=1602471368; Hm_lpvt_765ecde8c11b85f1ac5f168fa6e6821f=1602472300',
|
||||
'Host': 'iqdb.org', 'Origin': 'http://iqdb.org', 'Referer': 'http://iqdb.org/', 'Upgrade-Insecure-Requests': '1',
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36'}
|
||||
|
||||
|
||||
def parse_html(html: str):
|
||||
selector = fromstring(html)
|
||||
for tag in selector.xpath('//div[@id="pages"]/div[position()>1]/table'):
|
||||
# 第一个是bestmatch
|
||||
if pic_url := tag.xpath('./tr[2]/td/a/img/@src'):
|
||||
pic_url = urljoin("http://iqdb.org/", pic_url[0]) # 缩略图
|
||||
else:
|
||||
pic_url = "没有最相似的"
|
||||
similarity = tag.xpath('./tr[last()]/td/text()')[0] # 相似度
|
||||
href: List[str] = tag.xpath('./tr/td/a/@href') # 第一个href
|
||||
href.extend(tag.xpath('./tr/td/span/a/@href')) # 第二个 可能是空
|
||||
href = list(map(lambda x: "https:" + x if not x.startswith("https") else x, href))
|
||||
yield pic_url, similarity, href
|
||||
|
||||
pass
|
||||
|
||||
|
||||
async def get_pic_from_url(url: str):
|
||||
"""
|
||||
返回信息元祖
|
||||
:param url:
|
||||
:return:
|
||||
"""
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.get(url) as resp:
|
||||
content = io.BytesIO(await resp.read())
|
||||
data = FormData(boundary="----WebKitFormBoundaryuwjSiBcpPag4k159")
|
||||
data.add_field(name="MAX_FILE_SIZE", value="")
|
||||
for i in range(1, 7):
|
||||
data.add_field(name="service[]", value=str(i))
|
||||
data.add_field(name="service[]", value="11")
|
||||
data.add_field(name="service[]", value="13")
|
||||
data.add_field(name="file", value=content, content_type="application/octet-stream", filename="0.jpg")
|
||||
data.add_field(name="url", value="")
|
||||
async with session.post("http://iqdb.org/", data=data, headers=headers) as res:
|
||||
html = await res.text()
|
||||
return [i for i in parse_html(html)]
|
||||
pass
|
||||
|
||||
|
||||
async def get_des(url: str):
|
||||
"""
|
||||
返回详细简介 cq码转义
|
||||
:param url:
|
||||
:return:
|
||||
"""
|
||||
image_data: List[Tuple] = await get_pic_from_url(url)
|
||||
if not image_data:
|
||||
msg: str = "找不到高相似度的"
|
||||
yield msg
|
||||
return
|
||||
for pic in image_data:
|
||||
msg = MessageSegment.image(file=pic[0]) + f"\n{pic[1]}\n"
|
||||
for i in pic[2]:
|
||||
msg = msg + f"{i}\n"
|
||||
yield msg
|
||||
|
||||
@@ -0,0 +1,116 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import io
|
||||
from typing import List, Tuple, Union
|
||||
import aiofiles
|
||||
from util.utils import get_local_proxy
|
||||
from util.user_agent import get_user_agent
|
||||
from configs.path_config import IMAGE_PATH
|
||||
from asyncio.exceptions import TimeoutError
|
||||
from util.init_result import image
|
||||
|
||||
import aiohttp
|
||||
from lxml.html import fromstring
|
||||
from nonebot.adapters.cqhttp import Message
|
||||
|
||||
from .formdata import FormData
|
||||
|
||||
header = {
|
||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
|
||||
'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'zh-CN,zh;q=0.9',
|
||||
'Cache-Control': 'max-age=0',
|
||||
"Content-Type": "multipart/form-data; boundary=----WebKitFormBoundaryPpuR3EZ1Ap2pXv8W",
|
||||
'Connection': 'keep-alive',
|
||||
'Host': 'saucenao.com', 'Origin': 'https://saucenao.com', 'Referer': 'https://saucenao.com/index.php',
|
||||
'Sec-Fetch-Dest': 'document', 'Sec-Fetch-Mode': 'navigate', 'Sec-Fetch-Site': 'same-origin', 'Sec-Fetch-User': '?1',
|
||||
'Upgrade-Insecure-Requests': '1',
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36'}
|
||||
|
||||
|
||||
def parse_html(html: str):
|
||||
"""
|
||||
解析nao返回的html
|
||||
:param html:
|
||||
:return:
|
||||
"""
|
||||
selector = fromstring(html)
|
||||
for tag in selector.xpath('//div[@class="result"]/table'):
|
||||
pic_url = tag.xpath('./tr/td/div/a/img/@src')
|
||||
if pic_url:
|
||||
pic_url = pic_url[0]
|
||||
else:
|
||||
pic_url = None # 相似度
|
||||
xsd: List[str] = tag.xpath(
|
||||
'./tr/td[@class="resulttablecontent"]/div[@class="resultmatchinfo"]/div[@class="resultsimilarityinfo"]/text()')
|
||||
if xsd:
|
||||
xsd = xsd[0]
|
||||
else:
|
||||
xsd = "没有写" # 相似度
|
||||
title: List[str] = tag.xpath(
|
||||
'./tr/td[@class="resulttablecontent"]/div[@class="resultcontent"]/div[@class="resulttitle"]/strong/text()')
|
||||
if title:
|
||||
title = title[0]
|
||||
else:
|
||||
title = "没有写" # 标题
|
||||
# pixiv id
|
||||
pixiv_id: List[str] = tag.xpath(
|
||||
'./tr/td[@class="resulttablecontent"]/div[@class="resultcontent"]/div[@class="resultcontentcolumn"]/a[1]/@href')
|
||||
if pixiv_id:
|
||||
pixiv_id = pixiv_id[0]
|
||||
else:
|
||||
pixiv_id = "没有说"
|
||||
member: List[str] = tag.xpath(
|
||||
'./tr/td[@class="resulttablecontent"]/div[@class="resultcontent"]/div[@class="resultcontentcolumn"]/a[2]/@href')
|
||||
if member:
|
||||
member = member[0]
|
||||
else:
|
||||
member = "没有说"
|
||||
yield pic_url, xsd, title, pixiv_id, member
|
||||
|
||||
|
||||
async def get_pic_from_url(url: str):
|
||||
"""
|
||||
从url搜图
|
||||
:param url:
|
||||
:return:
|
||||
"""
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.get(url) as resp:
|
||||
content = io.BytesIO(await resp.read())
|
||||
data = FormData(boundary="----WebKitFormBoundaryPpuR3EZ1Ap2pXv8W")
|
||||
data.add_field(name="file", value=content, content_type="image/jpeg",
|
||||
filename="blob")
|
||||
async with session.post("https://saucenao.com/search.php", data=data, headers=header) as res:
|
||||
html = await res.text()
|
||||
image_data = [each for each in parse_html(html)]
|
||||
return image_data
|
||||
|
||||
|
||||
async def get_des(url: str, user_id: int):
|
||||
image_data: List[Tuple] = await get_pic_from_url(url)
|
||||
if not image_data:
|
||||
msg: Union[str, Message] = "找不到高相似度的"
|
||||
yield msg
|
||||
return
|
||||
for pic in image_data:
|
||||
# print(pic)
|
||||
msg = await download_img(pic[0], user_id) \
|
||||
+ f"\n相似度:{pic[1]}" \
|
||||
f"\n标题:{pic[2] if (str(pic[2]).strip() != 'Creator:' and len(str(pic[2]).split('-')) < 3) else '未知'}" \
|
||||
f"\nPID:{pic[3]}" \
|
||||
f"\nmember:{pic[4]}\n"
|
||||
yield msg
|
||||
pass
|
||||
|
||||
|
||||
async def download_img(url, user_id):
|
||||
try:
|
||||
async with aiohttp.ClientSession(headers=get_user_agent()) as session:
|
||||
async with session.get(url, proxy=get_local_proxy(), timeout=7) as response:
|
||||
async with aiofiles.open(IMAGE_PATH + f'temp/{user_id}_pic_find.png', 'wb') as f:
|
||||
await f.write(await response.read())
|
||||
return image(f'{user_id}_pic_find.png', 'temp')
|
||||
except TimeoutError:
|
||||
return image(url)
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,89 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import io
|
||||
from copy import deepcopy
|
||||
|
||||
from base64 import b64encode
|
||||
from typing import List, Tuple
|
||||
|
||||
import aiohttp
|
||||
from nonebot.adapters.cqhttp import MessageSegment
|
||||
|
||||
header = {':authority': 'api.trace.moe',
|
||||
'accept': '*/*',
|
||||
'accept-encoding': 'gzip, deflate, br',
|
||||
'accept-language': 'zh-CN,zh;q=0.9',
|
||||
'content-type': 'multipart/form-data; boundary=----WebKitFormBoundary9cyjY8YBBN8SGdG4',
|
||||
'origin': 'https://trace.moe',
|
||||
'sec-fetch-dest': 'empty', 'sec-fetch-mode': 'cors', 'sec-fetch-site': 'same-site',
|
||||
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
|
||||
'Chrome/84.0.4147.105 Safari/537.36'}
|
||||
|
||||
|
||||
async def parse_json(session: aiohttp.ClientSession, data: dict):
|
||||
count = 0
|
||||
for i in data["result"]:
|
||||
title: dict = i["anilist"]["title"]
|
||||
similarity = i["similarity"]
|
||||
from_ = i["from"]
|
||||
to = i["to"]
|
||||
file = i["filename"] # 名字
|
||||
is_adult = i["anilist"]["isAdult"]
|
||||
episode = i["episode"] # 集
|
||||
header_new = deepcopy(header)
|
||||
del header_new["content-type"]
|
||||
header_new[":method"] = 'GET'
|
||||
header_new["accept"] = "image/webp,image/apng,image/*,*/*;q=0.8"
|
||||
header_new["sec-fetch-dest"] = "image"
|
||||
header_new["sec-fetch-mode"] = "no-cors"
|
||||
async with session.get(i["image"], headers=header_new) as resp:
|
||||
pic = "base64://" + b64encode(await resp.read()).decode()
|
||||
yield pic, similarity, file, is_adult, from_, to, title, episode
|
||||
count += 1
|
||||
if count > 4:
|
||||
break
|
||||
|
||||
|
||||
# POST https://api.trace.moe/search?cutBorders=1&anilistID=
|
||||
async def get_pic_from_url(url: str):
|
||||
"""
|
||||
从url搜图
|
||||
:param url:
|
||||
:return:
|
||||
"""
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.get(url) as resp:
|
||||
content = io.BytesIO(await resp.read())
|
||||
# with open("F:\elu.PNG", "rb") as f:
|
||||
# content = io.BytesIO(f.read())
|
||||
data = aiohttp.FormData(boundary="----WebKitFormBoundary9cyjY8YBBN8SGdG4")
|
||||
data.add_field(name="image", value=content, content_type="image/jpeg",
|
||||
filename="blob")
|
||||
# data.add_field(name="filter", value="")
|
||||
# data.add_field(name="trial", value="0")
|
||||
async with session.post("https://api.trace.moe/search?cutBorders=1&anilistID=", data=data,
|
||||
headers=header) as res:
|
||||
data: dict = await res.json()
|
||||
image_data = [each async for each in parse_json(session, data)]
|
||||
return image_data
|
||||
|
||||
|
||||
async def get_des(url: str):
|
||||
image_data: List[Tuple] = await get_pic_from_url(url)
|
||||
if not image_data:
|
||||
msg: str = "找不到高相似度的"
|
||||
yield msg
|
||||
return
|
||||
for pic in image_data:
|
||||
msg = MessageSegment.image(
|
||||
file=pic[
|
||||
0]) + f"\n相似度:{pic[1]}%\n标题:{pic[6]['native'] + ' ' + pic[6]['chinese']}\n第{pic[7]}集\nR18:{pic[3]}\n开始时间:{pic[4]}s\n结束时间{pic[5]}s"
|
||||
yield msg
|
||||
pass
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import asyncio
|
||||
|
||||
data = asyncio.run(get_pic_from_url(
|
||||
"https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1606681978562&di=6d6c90aef5ff1f9f8915bbc2e18e3c98&imgtype=0&src=http%3A%2F%2Fc-ssl.duitang.com%2Fuploads%2Fblog%2F202011%2F15%2F20201115190356_c5b95.thumb.1000_0.jpg"))
|
||||
pass
|
||||
@@ -0,0 +1,53 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from typing import List, Tuple
|
||||
|
||||
import nonebot
|
||||
from nonebot.adapters.cqhttp import MessageSegment
|
||||
from lxml.html import fromstring
|
||||
import aiohttp
|
||||
|
||||
"""
|
||||
http://yandex.com/clck/jsredir?from=yandex.com%3Bimages%2Fsearch%3Bimages%3B%3B&text=&etext=9185.K4iyzsNBG9xrJrSJCUTF4i-XPMAfmBQYR_Igss1ESRc.65568e796f3375fae39da91273ae8a1a82410929&uuid=&state=iric5OQ0sS2054x1_o8yG9mmGMT8WeQxqpuwa4Ft4KVzd9aE_Y4Dfw,,&data=eEwyM2lDYU9Gd1VROE1ZMXhZYkJTYW5fZC1TWjIzaFh5TmR1Z09fQm5DdDB3bFJSSUpVdUxfZmUzcVhfaXhTN1BCU2dINGxmdkY4NFVNcHYyUmw0emFKT2pnOWJoVmlPVzAzX1FIbWh6aXVFV3F0YWFaMGdxeGFtY2dxTzFZZl9VY1huZmlLaGVGOFZleUthZXBlM1pxUGM2elVDLXdvZEo3OGJwdVFqYmVkTDJxWElHSzFZR2NVQUhVcTdzelJwSXlrTjhlS0txdHpYY1RMMHRLOU5HSTYtT0VDb0hpdll6YjVYRXNVcUhCRFJaeDExNTQwZlhMdjh4M2YtTVFUbVJ5ZzBxMTVJcG9DNW51UWhvRzE0WjlFS19uS0VUZWhNRGxOZWlPUkFlRUUs&sign=7ba9ee25d3716868ec8464fb766c9e25&keyno=IMGS_0&b64e=2&l10n=en
|
||||
"""
|
||||
|
||||
driver = nonebot.get_driver()
|
||||
proxy: str = driver.config.proxy
|
||||
|
||||
|
||||
def parse_html(html: str):
|
||||
selector = fromstring(html)
|
||||
for item in selector.xpath('//li[@class="other-sites__item"]'):
|
||||
pic_url = item.xpath('./a[@class="other-sites__preview-link"]/img/@src')[0].lstrip("//") # 图床
|
||||
des = item.xpath(
|
||||
'./div[@class="other-sites__snippet"]/div[@class="other-sites__snippet-title"]/a/text()')[0] # 简介
|
||||
url = item.xpath(
|
||||
'./div[@class="other-sites__snippet"]/div[@class="other-sites__snippet-site"]/a/@href')[0] # 链接
|
||||
yield pic_url, des, url
|
||||
|
||||
|
||||
async def get_pic_from_url(url: str):
|
||||
real_url = f"https://yandex.com/images/search?rpt=imageview&url={url}"
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.get(real_url, proxy=proxy) as resp:
|
||||
html: str = await resp.text()
|
||||
return [i for i in parse_html(html)]
|
||||
|
||||
|
||||
async def get_des(url: str):
|
||||
image_data: List[Tuple] = await get_pic_from_url(url)
|
||||
if not image_data:
|
||||
msg: str = "找不到高相似度的"
|
||||
yield msg
|
||||
return
|
||||
for pic in image_data:
|
||||
msg = MessageSegment.image(file=pic[0]) + "\n"
|
||||
for i in pic[1:]:
|
||||
msg = msg + f"{i}\n"
|
||||
yield msg
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
with open("yandex.html", "r", encoding="utf-8") as f:
|
||||
data = f.read()
|
||||
for item in parse_html(data):
|
||||
print(item)
|
||||
Reference in New Issue
Block a user