LiteyukiStudio/nonebot-plugin-marshoai
4
4
Fork 0
mirror of https://github.com/LiteyukiStudio/nonebot-plugin-marshoai.git synced 2025-02-07 21:46:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

修改, 但搜索功能完全无法使用了

Browse Source
This commit is contained in:
Twisuki 2024-12-11 18:09:08 +08:00
parent ccb12f0f63
commit 086f21272f
1 changed files with 80 additions and 68 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

148
nonebot_plugin_marshoai/tools/marshoai-meogirl/mg_Search.py
View File

@ -2,24 +2,34 @@ from nonebot.log import logger
import re import re
import httpx import httpx
import urllib.parse
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from watchfiles import awatch
async def get_async_data (url):
async with httpx.AsyncClient() as client:
return await client.get(url)
async def search(msg : str, num : int): async def search(msg : str, num : int):
logger.info(f"搜索 : \"{msg}\"") logger.info(f"搜索 : \"{msg}\"")
result = "" result = ""
headers = { # headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36' # 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36'
} # }
url = "https://mzh.moegirl.org.cn/index.php?search=" + msg url = "https://mzh.moegirl.org.cn/index.php?search=" + urllib.parse.quote_plus(msg)
async with httpx.AsyncClient() as client: # client = httpx.AsyncClient()
response = await client.get(url, headers = headers) # async with client:
logger.info(response.headers.get('Location')) # response = await client.post(url, headers = headers)
logger.info(f"连接萌娘百科中, 状态码 : {response.status_code}") response = await get_async_data(url)
logger.info(f"连接\"{response.headers.get('location')}\"中, 状态码 : {response.status_code}")
# 正常搜索
if response.status_code == 200:
""" """
萌娘百科搜索页面结构 萌娘百科搜索页面结构
div.searchresults # 若无, 证明页面已重定向 div.searchresults
└── p ... └── p ...
└── ul.mw-search-results # 若无, 证明无搜索结果 └── ul.mw-search-results # 若无, 证明无搜索结果
└── li # 一个搜索结果 └── li # 一个搜索结果
@ -29,68 +39,70 @@ async def search(msg : str, num : int):
└── li ... └── li ...
└── li ... └── li ...
""" """
if response.status_code == 200: soup = BeautifulSoup(response.text, 'html.parser')
soup = BeautifulSoup(response.text, 'html.parser')
# 检测div.searchresults, 是否已重定向 # 检测ul.mw-search-results, 是否有结果
if soup.find('div', class_='searchresults'): if soup.find('ul', class_='mw-search-results'):
# 检测ul.mw-search-results, 是否有结果 ul_tag = soup.select('ul.mw-search-results')[0]
if soup.find('ul', class_='mw-search-results'): li_tags = ul_tag.select('li')
ul_tag = soup.select('ul.mw-search-results')[0] for li_tag in li_tags:
li_tags = ul_tag.select('li')
for li_tag in li_tags:
div_heading = li_tag.select('div.mw-search-result-heading')[0] div_heading = li_tag.select('div.mw-search-result-heading')[0]
if div_heading: if div_heading:
a_tag = div_heading.select('a')[0] a_tag = div_heading.select('a')[0]
result += a_tag['title'] + "\n" result += a_tag['title'] + "\n"
logger.info(f"搜索到 : \"{a_tag['title']}\"") logger.info(f"搜索到 : \"{a_tag['title']}\"")
div_result = li_tag.find('div', class_='searchresult') div_result = li_tag.find('div', class_='searchresult')
if div_result: if div_result:
content = str(div_result).replace('<div class=\"searchresult\">', '').replace('</div>', '') content = str(div_result).replace('<div class=\"searchresult\">', '').replace('</div>', '')
content = content.replace('<span class=\"searchmatch\">', '').replace('</span>', '') content = content.replace('<span class=\"searchmatch\">', '').replace('</span>', '')
result += content + "\n\n" result += content + "\n\n"
num -= 1 num -= 1
if num == 0: if num == 0:
break break
return result return result
# 无ul.mw-search-results, 无结果 # 无ul.mw-search-results, 无结果
else:
logger.info("无结果")
return "无结果"
# 无div.searchresults, 重定向
else:
logger.info(f"\"{msg}\"已被重定向")
num = 0
"""
萌娘百科重定向介绍页面结构
div#mw-content-text
└── div.mw-parser-output # 介绍页面
└── ....
└── p ? # 可能存在的空p
└── p # 人物介绍
└── ...
"""
if soup.find('div', class_='mw-parser-output'):
div = soup.find('div', class_='mw-parser-output')
p_tags = div.select('p')
for p_tag in p_tags:
p = str(p_tag)
p = re.sub(r'<.*?>', '', p)
if p != '':
result += str(p) + "/n"
num += 1
if num >= 5:
break
return result
# 状态码非200
else: else:
logger.error(f"网络错误, 状态码 : {response.status_code}") logger.info("无结果")
return f"网络错误, 状态码 : {response.status_code}" return "无结果"
# 重定向
elif response.status_code == 302:
logger.info(f"\"{msg}\"已被重定向")
# 读取重定向结果
soup = BeautifulSoup(response.text, 'html.parser')
logger.success("重定向成功")
logger.info(response)
num = 0
"""
萌娘百科重定向介绍页面结构
div#mw-content-text
└── div.mw-parser-output # 介绍页面
└── ....
└── p ? # 可能存在的空p
└── p # 人物介绍
└── ...
"""
if soup.find('div', class_='mw-parser-output'):
div = soup.find('div', class_='mw-parser-output')
p_tags = div.select('p')
for p_tag in p_tags:
p = str(p_tag)
p = re.sub(r'<.*?>', '', p)
if p != '':
result += str(p) + "\n"
num += 1
if num >= 5:
break
return result
# 状态码非200或302
else:
logger.error(f"网络错误, 状态码 : {response.status_code}")
return f"网络错误, 状态码 : {response.status_code}"