File size: 1,599 Bytes
858916d fa82d94 3abc590 fa82d94 858916d 95863fc 858916d 3abc590 95863fc 858916d 6ed07a9 3abc590 6ed07a9 0404a52 6ed07a9 858916d 6ed07a9 858916d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
# -*- coding: utf-8 -*-
#
# Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from rag.nlp import find_codec
import readability
import html_text
import chardet
def get_encoding(file):
with open(file,'rb') as f:
tmp = chardet.detect(f.read())
return tmp['encoding']
class RAGFlowHtmlParser:
def __call__(self, fnm, binary=None):
txt = ""
if binary:
encoding = find_codec(binary)
txt = binary.decode(encoding, errors="ignore")
else:
with open(fnm, "r",encoding=get_encoding(fnm)) as f:
txt = f.read()
return self.parser_txt(txt)
@classmethod
def parser_txt(cls, txt):
if not isinstance(txt, str):
raise TypeError("txt type should be str!")
html_doc = readability.Document(txt)
title = html_doc.title()
content = html_text.extract_text(html_doc.summary(html_partial=True))
txt = f"{title}\n{content}"
sections = txt.split("\n")
return sections
|