Merge branch '12.18doubao' into develop
This commit is contained in:
commit
9015ad525b
@ -1,9 +1,6 @@
|
||||
import re
|
||||
from PyPDF2 import PdfReader
|
||||
|
||||
from flask_app.general.format_change import docx2pdf
|
||||
|
||||
|
||||
def extract_common_header(pdf_path):
|
||||
|
||||
def get_headers(pdf_document, start_page, pages_to_read):
|
||||
@ -84,10 +81,6 @@ def clean_page_content(text, common_header):
|
||||
text = re.sub(r'^\s*[—-]\s*\d{1,3}\s*[—-]\s*', '', text) # 删除形如 '—2—' 或 '-2-' 的页码
|
||||
return text
|
||||
|
||||
|
||||
from PyPDF2 import PdfReader
|
||||
|
||||
|
||||
def is_scanned_pdf(file_path, max_pages=15):
|
||||
"""
|
||||
检查 PDF 是否为扫描件(即前 15 页无文本)。
|
||||
@ -109,19 +102,6 @@ def is_scanned_pdf(file_path, max_pages=15):
|
||||
return False # 不是扫描型
|
||||
return True # 前 max_pages 页都没有文本
|
||||
|
||||
def get_pdf_page_count(file_path):
|
||||
"""
|
||||
获取 PDF 文件的页码数量
|
||||
"""
|
||||
try:
|
||||
pdf_path=file_path
|
||||
if file_path.lower().endswith(('.doc', '.docx')):
|
||||
pdf_path = docx2pdf(file_path)
|
||||
reader = PdfReader(pdf_path)
|
||||
return len(reader.pages)
|
||||
except Exception as e:
|
||||
print(f"读取 PDF 页码时出错:{e}")
|
||||
return 0
|
||||
if __name__ == '__main__':
|
||||
file_path = r"C:\Users\Administrator\Documents\WeChat Files\wxid_d11awe5rp1y722\FileStorage\File\2024-12\2020-安徽-安徽省生态环境厅电梯采购.pdf"
|
||||
res=is_scanned_pdf(file_path)
|
||||
|
@ -2,6 +2,7 @@ import json
|
||||
import os
|
||||
import mimetypes
|
||||
import requests
|
||||
from PyPDF2 import PdfReader
|
||||
|
||||
from flask_app.general.clean_pdf import is_scanned_pdf
|
||||
def download_file(url, local_filename):
|
||||
@ -172,6 +173,20 @@ def docx2pdf(local_path_in):
|
||||
print(f"format_change d2p:have downloaded file to: {downloaded_filepath}")
|
||||
return downloaded_filepath
|
||||
|
||||
def get_pdf_page_count(file_path):
|
||||
"""
|
||||
获取 PDF 文件的页码数量
|
||||
"""
|
||||
try:
|
||||
pdf_path=file_path
|
||||
if file_path.lower().endswith(('.doc', '.docx')):
|
||||
pdf_path = docx2pdf(file_path)
|
||||
reader = PdfReader(pdf_path)
|
||||
return len(reader.pages)
|
||||
except Exception as e:
|
||||
print(f"读取 PDF 页码时出错:{e}")
|
||||
return 0
|
||||
|
||||
# def docx2pdf(file_path):
|
||||
# """
|
||||
# 将本地的 .docx 或 .doc 文件转换为 .pdf 文件。
|
||||
|
@ -1,7 +1,7 @@
|
||||
import concurrent.futures
|
||||
import json
|
||||
import time
|
||||
from flask_app.general.clean_pdf import get_pdf_page_count
|
||||
from flask_app.general.format_change import get_pdf_page_count
|
||||
from flask_app.general.doubao import pdf2txt
|
||||
from flask_app.general.file2markdown import convert_file_to_markdown
|
||||
from flask_app.general.format_change import pdf2docx
|
||||
|
Loading…
x
Reference in New Issue
Block a user