mirror of
https://github.com/suyiiyii/nonebot-bison.git
synced 2025-06-04 02:26:11 +08:00
cfa91df5e4
* 🐞 fix(text-similarity): 修复除0报错 没有考虑到bilibili的推送出现动态或者视频简介长度为零的情况，出现文本相似度除0Error * 🧪 test(bilibili): 添加视频动态内容为空的情况的测试 * 🧪 test(text-similarity): 增加文本相似度函数的测试 * Update test_rss.py * 📃 docs(text_similarity): 添加文本相似度函数的注释 * 🦄 refactor(text_similarity): 重构文本相似度的比较方法 * 🎈 perf(similar_text): 将比较函数的return改成raise * 🦄 refactor(text_similarity): 重构文本相似度比较方法 * Update nonebot_bison/platform/bilibili.py Co-authored-by: felinae98 <731499577@qq.com> * Update nonebot_bison/platform/rss.py Co-authored-by: felinae98 <731499577@qq.com> --------- Co-authored-by: felinae98 <731499577@qq.com>
104 lines
3.0 KiB
Python
104 lines
3.0 KiB
Python
import re
|
||
import sys
|
||
import difflib
|
||
|
||
import nonebot
|
||
from nonebot.plugin import require
|
||
from bs4 import BeautifulSoup as bs
|
||
from nonebot.log import logger, default_format
|
||
from nonebot_plugin_saa import Text, Image, MessageSegmentFactory
|
||
|
||
from .http import http_client
|
||
from .context import ProcessContext
|
||
from ..plugin_config import plugin_config
|
||
from .scheduler_config import SchedulerConfig, scheduler
|
||
|
||
__all__ = [
|
||
"http_client",
|
||
"Singleton",
|
||
"parse_text",
|
||
"ProcessContext",
|
||
"html_to_text",
|
||
"SchedulerConfig",
|
||
"scheduler",
|
||
]
|
||
|
||
|
||
class Singleton(type):
|
||
_instances = {}
|
||
|
||
def __call__(cls, *args, **kwargs):
|
||
if cls not in cls._instances:
|
||
cls._instances[cls] = super().__call__(*args, **kwargs)
|
||
return cls._instances[cls]
|
||
|
||
|
||
async def parse_text(text: str) -> MessageSegmentFactory:
|
||
"return raw text if don't use pic, otherwise return rendered opcode"
|
||
if plugin_config.bison_use_pic:
|
||
require("nonebot_plugin_htmlrender")
|
||
from nonebot_plugin_htmlrender import text_to_pic as _text_to_pic
|
||
|
||
return Image(await _text_to_pic(text))
|
||
else:
|
||
return Text(text)
|
||
|
||
|
||
if not plugin_config.bison_skip_browser_check:
|
||
require("nonebot_plugin_htmlrender")
|
||
|
||
|
||
def html_to_text(html: str, query_dict: dict = {}) -> str:
|
||
html = re.sub(r"<br\s*/?>", "<br>\n", html)
|
||
html = html.replace("</p>", "</p>\n")
|
||
soup = bs(html, "html.parser")
|
||
if query_dict:
|
||
node = soup.find(**query_dict)
|
||
else:
|
||
node = soup
|
||
assert node is not None
|
||
return node.text.strip()
|
||
|
||
|
||
class Filter:
|
||
def __init__(self) -> None:
|
||
self.level: int | str = "DEBUG"
|
||
|
||
def __call__(self, record):
|
||
module_name: str = record["name"]
|
||
module = sys.modules.get(module_name)
|
||
if module:
|
||
module_name = getattr(module, "__module_name__", module_name)
|
||
record["name"] = module_name.split(".")[0]
|
||
levelno = logger.level(self.level).no if isinstance(self.level, str) else self.level
|
||
nonebot_warning_level = logger.level("WARNING").no
|
||
return (
|
||
record["level"].no >= levelno
|
||
if record["name"] != "nonebot"
|
||
else record["level"].no >= nonebot_warning_level
|
||
)
|
||
|
||
|
||
if plugin_config.bison_filter_log:
|
||
logger.remove()
|
||
default_filter = Filter()
|
||
logger.add(
|
||
sys.stdout,
|
||
colorize=True,
|
||
diagnose=False,
|
||
filter=default_filter,
|
||
format=default_format,
|
||
)
|
||
config = nonebot.get_driver().config
|
||
logger.success("Muted info & success from nonebot")
|
||
default_filter.level = ("DEBUG" if config.debug else "INFO") if config.log_level is None else config.log_level
|
||
|
||
|
||
def text_similarity(str1, str2) -> float:
|
||
"""利用最长公共子序列的算法判断两个字符串是否相似，并返回0到1.0的相似度"""
|
||
if len(str1) == 0 or len(str2) == 0:
|
||
raise ValueError("The length of string can not be 0")
|
||
matcher = difflib.SequenceMatcher(None, str1, str2)
|
||
t = sum(temp.size for temp in matcher.get_matching_blocks())
|
||
return t / min(len(str1), len(str2))
|