LiteyukiStudio/nonebot-plugin-marshoai
5
4
Fork 0
mirror of https://github.com/LiteyukiStudio/nonebot-plugin-marshoai.git synced 2026-04-27 00:35:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

统一格式(无实质改动) & 添加了图片 (#23)

Browse Source 
* 修复了style和script标签无法去除的问题

* 添加了图片展示 & 统一了引号格式

* 添加了图片展示 & 统一了引号格式

* 统一引号格式并异步处理函数
This commit is contained in:
Nya_Twisuki
2024-12-12 13:47:28 +08:00
committed by GitHub
parent 6a4b0bbd0d
commit b939a48b0b
6 changed files with 74 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
nonebot_plugin_marshoai/tools/marshoai-meogirl/mg_Search.py
View File

@@ -6,7 +6,7 @@ import urllib.parse
from bs4 import BeautifulSoup
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"
}
async def get_async_data (url):
@@ -19,7 +19,7 @@ async def search(msg : str, num : int):
url = "https://mzh.moegirl.org.cn/index.php?search=" + urllib.parse.quote_plus(msg)
response = await get_async_data(url)
logger.success(f"连接{url}完成, 状态码 : {response.status_code}")
logger.success(f"连接\"{url}\"完成, 状态码 : {response.status_code}")
# 正常搜索
if response.status_code == 200:
@@ -35,25 +35,25 @@ async def search(msg : str, num : int):
└── li ...
└── li ...
"""
soup = BeautifulSoup(response.text, 'html.parser')
soup = BeautifulSoup(response.text, "html.parser")
# 检测ul.mw-search-results, 是否有结果
if soup.find('ul', class_='mw-search-results'):
ul_tag = soup.select('ul.mw-search-results')[0]
li_tags = ul_tag.select('li')
ul_tag = soup.find("ul", class_ = "mw-search-results")
if ul_tag:
li_tags = ul_tag.find_all("li")
for li_tag in li_tags:
div_heading = li_tag.select('div.mw-search-result-heading')[0]
div_heading = li_tag.find("div", class_ = "mw-search-result-heading")
if div_heading:
a_tag = div_heading.select('a')[0]
result += a_tag['title'] + "\n"
logger.info(f"搜索到 : \"{a_tag['title']}\"")
a_tag = div_heading.find("a")
result += a_tag["title"] + "\n"
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:
content = str(div_result).replace('<div class=\"searchresult\">', '').replace('</div>', '')
content = content.replace('<span class=\"searchmatch\">', '').replace('</span>', '')
result += content + "\n\n"
content = str(div_result).replace("<div class=\"searchresult\">", "").replace("</div>", "")
content = content.replace("<span class=\"searchmatch\">", "").replace("</span>", "")
result += content + "\n"
num -= 1
if num == 0:
@@ -67,10 +67,10 @@ async def search(msg : str, num : int):
# 重定向
elif response.status_code == 302:
logger.info(f"\"{msg}\"已被重定向至\"{response.headers.get('location')}\"")
logger.info(f"\"{msg}\"已被重定向至\"{response.headers.get("location")}\"")
# 读取重定向结果
response = await get_async_data(response.headers.get('location'))
soup = BeautifulSoup(response.text, 'html.parser')
response = await get_async_data(response.headers.get("location"))
soup = BeautifulSoup(response.text, "html.parser")
logger.success("重定向成功")
num = 0
@@ -83,19 +83,28 @@ async def search(msg : str, num : int):
└── 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')
result += msg + "\n"
img = soup.find("img", class_="infobox-image")
if img:
logger.info(f"照片{img["src"]}")
result += f"![ {msg} ]( {img["src"]} ) \n"
div = soup.find("div", class_="mw-parser-output")
if div:
p_tags = div.find_all("p")
for p_tag in p_tags:
p = str(p_tag)
p = re.sub(r'<.*?>', '', p)
if p != '':
p = re.sub(r"<script.*?</script>|<style.*?</style>", "", p, flags=re.DOTALL)
p = re.sub(r"<.*?>", "", p, flags = re.DOTALL)
p = re.sub(r"\[.*?]", "", p, flags = re.DOTALL)
if p != "":
result += str(p)
num += 1
if num >= 5:
break
return result
return result
# 状态码非200或302
else: