zy123/zbparse
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

2.17 增加读文件pdf接口测试1

Browse Source
This commit is contained in:
zy123 2025-02-17 11:42:37 +08:00
parent 01abc7eb9f
commit e80be4aa9c
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
flask_app/general/读取文件/按页读取pdf.py
View File

@ -47,7 +47,7 @@ def extract_text_by_page(file_path):
return result return result
def process_pages(get_text, total_pages): def process_pages(get_text, common_header, total_pages):
""" """
扫描所有页面，返回第一个和最后一个包含有效文本的页面索引。 扫描所有页面，返回第一个和最后一个包含有效文本的页面索引。
如果所有页面都为空，则返回 0 到 total_pages - 1。 如果所有页面都为空，则返回 0 到 total_pages - 1。
@ -57,6 +57,7 @@ def process_pages(get_text, total_pages):
for page_num in range(total_pages): for page_num in range(total_pages):
try: try:
text = get_text(page_num) text = get_text(page_num)
cleaned_text = clean_page_content(text, common_header)
except Exception as e: except Exception as e:
print(f"读取第 {page_num} 页失败: {e}") print(f"读取第 {page_num} 页失败: {e}")
continue continue
@ -75,12 +76,13 @@ def process_pages(get_text, total_pages):
return start_page, end_page return start_page, end_page
def read_pdf_main(pdf_path): def read_pdf_main(pdf_path):
common_header=extract_common_header(pdf_path)
try: try:
with open(pdf_path, "rb") as f: with open(pdf_path, "rb") as f:
pdf_document = PdfReader(f) pdf_document = PdfReader(f)
total_pages = len(pdf_document.pages) total_pages = len(pdf_document.pages)
get_text = create_get_text_function('pypdf2', pdf_document) get_text = create_get_text_function('pypdf2', pdf_document)
start_page, end_page = process_pages(get_text, total_pages) start_page, end_page = process_pages(get_text, common_header,total_pages)
return start_page, end_page return start_page, end_page
except Exception as e_pypdf2: except Exception as e_pypdf2:
print(f"extract_pages_generic: 使用 PyPDF2 读取 PDF 失败: {e_pypdf2}") print(f"extract_pages_generic: 使用 PyPDF2 读取 PDF 失败: {e_pypdf2}")
@ -90,7 +92,7 @@ def read_pdf_main(pdf_path):
with fitz.open(pdf_path) as pdf_document: with fitz.open(pdf_path) as pdf_document:
total_pages = pdf_document.page_count total_pages = pdf_document.page_count
get_text = create_get_text_function('fitz', pdf_document) get_text = create_get_text_function('fitz', pdf_document)
start_page, end_page = process_pages(get_text, total_pages) start_page, end_page = process_pages(get_text, common_header,total_pages)
return start_page, end_page return start_page, end_page
except Exception as e_pypdf2: except Exception as e_pypdf2:
print(f"extract_pages_generic: 使用 fitz 读取 PDF 失败: {e_pypdf2}") print(f"extract_pages_generic: 使用 fitz 读取 PDF 失败: {e_pypdf2}")