mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-04-22 06:00:00 +08:00
0171082cc5
### What problem does this PR solve? ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)
40 lines
1.3 KiB
Python
40 lines
1.3 KiB
Python
# -*- coding: utf-8 -*-
|
|
# 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()
|
|
|
|
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
|