541 lines
24 KiB
Python
541 lines
24 KiB
Python
#flask_app/general/截取pdf通用函数.py
|
||
import concurrent.futures
|
||
import os
|
||
|
||
import regex
|
||
from PyPDF2 import PdfReader, PdfWriter
|
||
|
||
from flask_app.general.clean_pdf import extract_common_header, clean_page_content
|
||
from flask_app.general.format_change import docx2pdf
|
||
import concurrent.futures
|
||
|
||
|
||
def get_start_and_common_header(input_path,end_page):
|
||
common_header = extract_common_header(input_path)
|
||
last_begin_index = 0
|
||
begin_pattern = regex.compile(
|
||
r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:招标公告|磋商公告|谈判公告|邀请书|邀请函|投标邀请|磋商邀请|谈判邀请|采购公告)[\)）]?\s*$',
|
||
regex.MULTILINE
|
||
)
|
||
# 新增目录匹配模式
|
||
catalog_pattern = regex.compile(r'\s*目\s*录\s*$', regex.MULTILINE)
|
||
pdf_document = PdfReader(input_path)
|
||
for i, page in enumerate(pdf_document.pages):
|
||
if i > end_page:
|
||
return common_header, 0 # 如果页码大于end_page，直接返回last_begin_index=0
|
||
text = page.extract_text()
|
||
if text:
|
||
cleaned_text = clean_page_content(text, common_header)
|
||
# 检查是否存在"目录"
|
||
if catalog_pattern.search(cleaned_text):
|
||
continue # 如果存在目录，跳过当前页面
|
||
if begin_pattern.search(cleaned_text):
|
||
last_begin_index = i # 更新第一个匹配的索引，页码从0开始
|
||
return common_header, last_begin_index
|
||
return common_header, last_begin_index
|
||
|
||
def check_pdf_pages(pdf_path,mode, logger):
|
||
try:
|
||
reader = PdfReader(pdf_path)
|
||
num_pages = len(reader.pages)
|
||
logger.info(f"PDF '{pdf_path}' 的总页数为: {num_pages}")
|
||
if num_pages <= 30:
|
||
logger.info("PDF（invalid_path）页数小于或等于30页，跳过切分逻辑。")
|
||
if mode=='goods':
|
||
return True,['', '', '', '', '', '', pdf_path,'']
|
||
else:
|
||
return True,['', '', '', '', '', pdf_path, '']
|
||
# 若页数大于30页，返回None表示继续处理
|
||
return False, []
|
||
except Exception as e:
|
||
logger.error(f"无法读取 PDF 页数: {e}")
|
||
# 返回空列表意味着无法执行后续处理逻辑
|
||
if mode == 'goods':
|
||
return True,['', '', '', '', '', '', pdf_path, '']
|
||
else:
|
||
return True,['', '', '', '', '', pdf_path, '']
|
||
|
||
|
||
def save_extracted_pages(pdf_path,output_folder,start_page, end_page, output_suffix,common_header):
|
||
try:
|
||
# 检查 start_page 和 end_page 是否为 None
|
||
if start_page is None or end_page is None:
|
||
print("Error: start_page 或 end_page 为 None")
|
||
return ""
|
||
pdf_document = PdfReader(pdf_path)
|
||
total_pages = len(pdf_document.pages)
|
||
base_file_name = os.path.splitext(os.path.basename(pdf_path))[0]
|
||
output_pdf_path = os.path.join(output_folder, f"{base_file_name}_{output_suffix}.pdf")
|
||
|
||
if start_page < 0 or end_page >= total_pages or start_page > end_page:
|
||
print(f"无效的页面范围: {start_page} 到 {end_page}")
|
||
return ""
|
||
|
||
if output_suffix == 'notice' and start_page > 0:
|
||
before_pdf_path = os.path.join(output_folder, f"{base_file_name}_before.pdf")
|
||
before_doc = PdfWriter()
|
||
toc_page = -1
|
||
# 查找目录页
|
||
for page_num in range(min(start_page, total_pages)):
|
||
page_text = pdf_document.pages[page_num].extract_text()
|
||
cleaned_text = clean_page_content(page_text, common_header)
|
||
if regex.search(r'目\s*录', cleaned_text, regex.MULTILINE):
|
||
toc_page = page_num
|
||
break
|
||
|
||
# 确定截取的页数
|
||
pages_to_extract = toc_page + 1 if toc_page != -1 else start_page
|
||
# 提取页面
|
||
for page_num in range(pages_to_extract):
|
||
before_doc.add_page(pdf_document.pages[page_num])
|
||
print(before_pdf_path)
|
||
with open(before_pdf_path, 'wb') as f_before:
|
||
before_doc.write(f_before)
|
||
|
||
output_doc = PdfWriter()
|
||
for page_num in range(start_page, end_page + 1):
|
||
output_doc.add_page(pdf_document.pages[page_num])
|
||
with open(output_pdf_path, 'wb') as f:
|
||
output_doc.write(f)
|
||
print(f"{output_suffix} 已截取并保存页面从 {start_page} 到 {end_page} 为 {output_pdf_path}")
|
||
return output_pdf_path
|
||
except Exception as e:
|
||
print(f"Error in save_extracted_pages: {e}")
|
||
return "" # 返回空字符串
|
||
|
||
def is_pdf_or_doc(filename):
|
||
# 判断文件是否为PDF或Word文档
|
||
return filename.lower().endswith(('.pdf', '.doc', '.docx'))
|
||
|
||
|
||
def convert_to_pdf(file_path):
|
||
# 假设 docx2pdf 函数已经被定义，这里仅根据文件扩展名来决定是否需要转换
|
||
if file_path.lower().endswith(('.doc', '.docx')):
|
||
return docx2pdf(file_path)
|
||
return file_path
|
||
|
||
|
||
def get_invalid_file(file_path, output_folder, common_header,begin_page):
|
||
"""
|
||
从指定的PDF文件中提取无效部分并保存到输出文件夹中。
|
||
begin_pattern从前往后匹配 end_pattern从后往前
|
||
页数小于100不进行begin_pattern，默认start_page=0
|
||
页数大于200时end_pattern从前往后匹配
|
||
|
||
|
||
Args:
|
||
file_path (str): 输入的PDF文件路径。
|
||
output_folder (str): 提取后文件的输出文件夹路径。
|
||
common_header (str): 公共头部文本，用于清理每页的内容。
|
||
|
||
Returns:
|
||
list: 包含保存的文件路径的列表，如果提取失败则返回包含空字符串的列表。
|
||
"""
|
||
# 定义开始模式
|
||
begin_patterns = [
|
||
regex.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:公告|邀请书|邀请函|邀请).*|^第一卷|^投标邀请书|^投标邀请函|^投标邀请',
|
||
regex.MULTILINE
|
||
),
|
||
regex.compile(
|
||
r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:招标公告|磋商公告|谈判公告|邀请书|邀请函|投标邀请|磋商邀请|谈判邀请)[\)）]?\s*$',
|
||
regex.MULTILINE
|
||
)
|
||
]
|
||
|
||
# 定义结束模式
|
||
end_patterns = [
|
||
regex.compile(
|
||
r'第[一二三四五六七八九十]+(?:章|部分).*?合同|[：:]清标报告',
|
||
regex.MULTILINE
|
||
),
|
||
regex.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:响应|投标|应答).*?(?:格式|文件(?:的)?组成|文件(?:的)?构成|文件(?:的)?编制).*',
|
||
regex.MULTILINE
|
||
),
|
||
regex.compile(
|
||
r"\s*(投标文件|响应文件|响应性文件|应答文件)(?:的)?格式\s*",
|
||
regex.MULTILINE
|
||
)
|
||
]
|
||
|
||
# 定义排除模式
|
||
exclusion_pattern = regex.compile(
|
||
r'文件的构成|文件的组成|文件组成|文件构成|文件的编制|文件编制',
|
||
regex.MULTILINE
|
||
)
|
||
|
||
try:
|
||
# 打开PDF文件
|
||
pdf_document = PdfReader(file_path)
|
||
total_pages = len(pdf_document.pages)
|
||
# 新增逻辑：如果总页数 <= 50，直接返回 file_path
|
||
if total_pages <= 50:
|
||
print(f"PDF页数({total_pages}) <= 50，直接返回文件路径:{file_path}")
|
||
return file_path,0
|
||
# 提取并清理每页的文本内容
|
||
page_texts = []
|
||
for i in range(total_pages):
|
||
page = pdf_document.pages[i]
|
||
text = page.extract_text()
|
||
cleaned_text = clean_page_content(text, common_header) if text else ""
|
||
page_texts.append(cleaned_text)
|
||
|
||
# 定义查找起始页的函数
|
||
def find_start_page(begin_page):
|
||
for pattern in begin_patterns:
|
||
for i in range(begin_page, min(begin_page + 30, total_pages)):
|
||
text = page_texts[i]
|
||
if regex.search(exclusion_pattern, text):
|
||
continue
|
||
if regex.search(pattern, text):
|
||
# print(f"起始模式在第 {i + 1} 页匹配: {pattern.pattern}")
|
||
return i
|
||
# print(f"未在前30页找到模式: {pattern.pattern}")
|
||
return 0 # 默认从第一页开始
|
||
|
||
# 定义查找结束页的函数
|
||
def find_end_page():
|
||
if total_pages > 200:
|
||
# print("总页数大于200页，结束页从前往后查找，跳过前30页。") #防止匹配到目录这块
|
||
for pattern in end_patterns:
|
||
for i in range(30, total_pages):
|
||
text = page_texts[i]
|
||
if regex.search(pattern, text):
|
||
# print(f"结束模式在第 {i + 1} 页匹配: {pattern.pattern}")
|
||
return i
|
||
else:
|
||
# print("结束页从后往前查找，确保只剩前30页时停止。")
|
||
for pattern in end_patterns:
|
||
for i in range(total_pages - 1, 29, -1):
|
||
text = page_texts[i]
|
||
if regex.search(pattern, text):
|
||
# print(f"结束模式在第 {i + 1} 页匹配: {pattern.pattern}")
|
||
return i
|
||
|
||
# 如果没有匹配到，设置end_page逻辑
|
||
if total_pages > 100:
|
||
print("未找到结束模式，总页数大于100，设置结束页为前100页。"+file_path)
|
||
return max(100, int(total_pages * 2 / 3))
|
||
else:
|
||
print("未找到结束模式，设置结束页为最后一页。"+file_path)
|
||
return total_pages - 1
|
||
|
||
# 根据总页数决定是否查找起始页
|
||
if total_pages < 100:
|
||
# print("总页数少于100页，默认起始页为第一页。")
|
||
start_page = 0
|
||
with concurrent.futures.ThreadPoolExecutor() as executor:
|
||
future_end = executor.submit(find_end_page)
|
||
end_page = future_end.result()
|
||
else:
|
||
with concurrent.futures.ThreadPoolExecutor() as executor:
|
||
future_start = executor.submit(find_start_page,begin_page)
|
||
future_end = executor.submit(find_end_page)
|
||
start_page = future_start.result()
|
||
end_page = future_end.result()
|
||
|
||
# print(f"起始页: {start_page + 1}, 结束页: {end_page + 1}")
|
||
|
||
# 验证页码范围
|
||
if start_page > end_page:
|
||
print(f"无效的页码范围: 起始页 ({start_page + 1}) > 结束页 ({end_page + 1})")
|
||
return "",0
|
||
|
||
# 调用已实现的保存函数
|
||
output_path = save_extracted_pages(
|
||
pdf_path=file_path,
|
||
output_folder=output_folder,
|
||
start_page=start_page,
|
||
end_page=end_page,
|
||
output_suffix="invalid",
|
||
common_header=common_header
|
||
)
|
||
|
||
# print(f"提取的页面 {start_page} 到 {end_page} 已保存至 {output_path}")
|
||
return output_path,end_page
|
||
|
||
except Exception as e:
|
||
print(f"处理文件 {file_path} 时发生错误: {e}")
|
||
return "",0
|
||
|
||
def extract_pages_generic(pdf_document, begin_pattern, end_pattern, begin_page, common_header, exclusion_pattern=None,
|
||
output_suffix="normal",invalid_endpage=-1):
|
||
start_page = None
|
||
end_page = None
|
||
flag=True
|
||
# 确定遍历范围
|
||
total_pages = len(pdf_document.pages)
|
||
end_limit = total_pages if invalid_endpage == -1 else min(invalid_endpage, total_pages)
|
||
for i, page in enumerate(pdf_document.pages[begin_page:end_limit], start=begin_page):
|
||
text = page.extract_text() or ""
|
||
cleaned_text = clean_page_content(text, common_header)
|
||
if output_suffix == "tobidders_notice" or output_suffix=="notice":
|
||
catalog_pattern = regex.compile(r'\s*目\s*录\s*$', regex.MULTILINE)
|
||
if exclusion_pattern and flag and (start_page is not None) and regex.search(exclusion_pattern, cleaned_text):
|
||
flag=False
|
||
continue
|
||
if begin_page==0 and catalog_pattern.search(cleaned_text):
|
||
continue # 如果存在目录，跳过当前页面
|
||
else:
|
||
#一般投标文件的编制、组成在'投标人须知前附表/正文'中，需要防止begin_pattern匹配到这部分内容，所以在start_page is None的时候使用该exclusion_pattern
|
||
if exclusion_pattern and flag and (start_page is None) and regex.search(exclusion_pattern, cleaned_text):
|
||
flag=False
|
||
continue
|
||
if start_page is None and regex.search(begin_pattern, cleaned_text):
|
||
if (output_suffix == "notice" and i >= begin_page) or (output_suffix != "notice" and i > begin_page):
|
||
start_page = i
|
||
continue
|
||
if start_page is not None:
|
||
if output_suffix == "tobidders_notice":
|
||
if regex.search(end_pattern, cleaned_text) and i > start_page:
|
||
end_page = i
|
||
break
|
||
else:
|
||
if regex.search(end_pattern, cleaned_text) and (i > start_page) and not regex.search(begin_pattern, cleaned_text):
|
||
end_page = i
|
||
break
|
||
return start_page, end_page
|
||
|
||
|
||
def generate_mid_pattern(chapter_type=None):
|
||
"""
|
||
根据章节类型动态生成 mid_pattern。
|
||
|
||
参数:
|
||
chapter_type (str, optional): 章节类型，如 '章' 或 '部分'。
|
||
|
||
返回:
|
||
regex.Pattern: 编译后的正则表达式模式。
|
||
"""
|
||
# 定义基础的 mid_pattern
|
||
base_mid_pattern = (
|
||
r'^\s*(?:[（(]\s*[一二12]?\s*[)）]\s*[、．.]*|'
|
||
r'[一二12][、．.]+|[、．.]+)\s*(说\s*明|总\s*则|名\s*词\s*解\s*释)|'
|
||
r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|应答人).*须知正文\s*$'
|
||
)
|
||
|
||
additional_mid_pattern = ''
|
||
if chapter_type:
|
||
if chapter_type == '章':
|
||
additional_mid_pattern = r'^第[一二三四五六七八九十百千]+?(?:部分)'
|
||
elif chapter_type == '部分':
|
||
additional_mid_pattern = r'^第[一二三四五六七八九十百千]+?(?:章)'
|
||
|
||
if additional_mid_pattern:
|
||
combined_pattern = rf'(?:{base_mid_pattern})|(?:{additional_mid_pattern})'
|
||
else:
|
||
combined_pattern = base_mid_pattern
|
||
|
||
return regex.compile(combined_pattern, regex.MULTILINE)
|
||
|
||
def generate_end_pattern(extraction_stage, chapter_type=None):
|
||
"""
|
||
根据提取阶段和章节类型动态生成 end_pattern。
|
||
|
||
参数:
|
||
extraction_stage (str): 提取阶段标记，如 'first' 表示第一次，'third' 表示第三次。
|
||
chapter_type (str, optional): 章节类型，如 '章' 或 '部分'。
|
||
|
||
返回:
|
||
regex.Pattern: 编译后的正则表达式模式。
|
||
"""
|
||
# 定义公共匹配模式
|
||
common_patterns = (
|
||
r'^(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)附录(?:一)?[：:]|'
|
||
r'^(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)附件(?:一)?[：:]|'
|
||
r'^(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)附表(?:一)?[：:]'
|
||
)
|
||
|
||
# 定义 end_pattern 模板
|
||
end_pattern_template_first = (
|
||
r'^(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九十百千]+(?:{chapter_type})\s*[\u4e00-\u9fff]+'
|
||
r'|' + common_patterns
|
||
)
|
||
|
||
end_pattern_template_third = (
|
||
r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)第[一二三四五六七八九十百千]+(?:{chapter_type})\s*[\u4e00-\u9fff、()（）/]+\s*$'
|
||
r'|' + common_patterns
|
||
)
|
||
|
||
# 选择模板并替换 {chapter_type}
|
||
if extraction_stage == 'third':
|
||
template = end_pattern_template_third
|
||
else:
|
||
template = end_pattern_template_first
|
||
|
||
if chapter_type:
|
||
pattern_str = template.format(chapter_type=chapter_type)
|
||
else:
|
||
pattern_str = template.format(chapter_type='章|部分')
|
||
|
||
return regex.compile(pattern_str, regex.MULTILINE)
|
||
|
||
def extract_pages_tobidders_notice(pdf_path, output_folder, begin_page, common_header, invalid_endpage=-1):
|
||
"""
|
||
从PDF文档中提取起始页、中间页和结束页。
|
||
如果第一次提取失败，则使用新的 begin_pattern 和 end_pattern 重新提取。
|
||
"""
|
||
exclusion_pattern = regex.compile(r'文件的构成|文件的组成|文件构成|文件组成|文件的编制|文件编制')
|
||
pdf_document = PdfReader(pdf_path)
|
||
def run_extraction(begin_pattern, extraction_stage='first'):
|
||
"""
|
||
使用提供的 begin_pattern 运行提取过程。
|
||
根据 extraction_stage 判断是“第一次提取”还是“第三次提取”，
|
||
从而选择对应的默认 end_pattern（动态生成）。
|
||
|
||
参数:
|
||
begin_pattern (regex.Pattern): 用于识别起始的正则表达式模式。
|
||
extraction_stage (str): 提取阶段标记，如 'first' 表示第一次，'third' 表示第三次。
|
||
|
||
返回:
|
||
tuple: (start_page, mid_page, end_page)
|
||
"""
|
||
|
||
# ===== 函数内部变量 =====
|
||
start_page = None
|
||
mid_page = None
|
||
end_page = None
|
||
combined_mid_pattern = None # 中间页的组合模式
|
||
catalog_pattern = regex.compile(r'\s*目\s*录\s*$', regex.MULTILINE)
|
||
total_pages = len(pdf_document.pages)
|
||
end_limit = total_pages if invalid_endpage == -1 else min(invalid_endpage, total_pages)
|
||
# ===== 遍历每一页，执行提取逻辑 =====
|
||
for i, page in enumerate(pdf_document.pages[:end_limit]):
|
||
text = page.extract_text() or ""
|
||
cleaned_text = clean_page_content(text, common_header)
|
||
|
||
# 如果已经找到中间页，且当前页匹配排除模式，则跳过
|
||
if exclusion_pattern and regex.search(exclusion_pattern, cleaned_text) and mid_page is not None:
|
||
continue
|
||
|
||
# 如果为第 0 页之后的目录，直接跳过
|
||
if begin_page == 0 and catalog_pattern.search(cleaned_text):
|
||
continue
|
||
|
||
# ========== 识别起始页 ==========
|
||
if start_page is None:
|
||
match = regex.search(begin_pattern, cleaned_text)
|
||
if match and i > begin_page:
|
||
start_page = i
|
||
matched_text = match.group(0) # 获取整个匹配的文本
|
||
# 根据匹配到的内容识别是“章”还是“部分”，用于后续组合 mid_pattern
|
||
if '章' in matched_text:
|
||
chapter_type = '章'
|
||
elif '部分' in matched_text:
|
||
chapter_type = '部分'
|
||
else:
|
||
chapter_type = None # 未匹配到“章”或“部分”
|
||
|
||
# ===== 动态生成 end_pattern_dynamic =====
|
||
end_pattern_dynamic = generate_end_pattern(extraction_stage, chapter_type)
|
||
# ========== 动态生成 mid_pattern ==========
|
||
combined_mid_pattern = generate_mid_pattern(chapter_type)
|
||
# 找到 start_page 后，继续循环，进入下一页
|
||
continue
|
||
|
||
# ========== 识别中间页 ==========
|
||
if start_page is not None and mid_page is None and combined_mid_pattern:
|
||
if regex.search(combined_mid_pattern, cleaned_text):
|
||
mid_page = i
|
||
|
||
# ========== 识别结束页 ==========
|
||
if start_page is not None and mid_page is not None:
|
||
# 当前使用的 end_pattern（上面根据 extraction_stage 和 chapter_type 选择好了）
|
||
if regex.search(end_pattern_dynamic, cleaned_text):
|
||
if i > mid_page:
|
||
end_page = i
|
||
break
|
||
|
||
return start_page, mid_page, end_page
|
||
|
||
def perform_extraction_and_save(start_page, mid_page, end_page):
|
||
path1 = save_extracted_pages(pdf_path,output_folder,start_page,mid_page,"tobidders_notice_part1",common_header)
|
||
if mid_page != end_page:
|
||
path2 = save_extracted_pages(pdf_path,output_folder,mid_page,end_page,"tobidders_notice_part2",common_header)
|
||
else:
|
||
path2 = path1
|
||
return path1, path2
|
||
|
||
# 第一次提取尝试，使用初始的 begin_pattern
|
||
begin_pattern = regex.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:投标人?|磋商|谈判|供应商|应答人|比选申请人).*须知+|'
|
||
r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!"\s*)(?<!"\s*)(?:投标人?|磋商|谈判|供应商|应答人|比选申请人).*须知前附表\s*$',
|
||
regex.MULTILINE
|
||
)
|
||
start_page, mid_page, end_page = run_extraction(begin_pattern, extraction_stage='first')
|
||
# 如果第一次提取成功，保存并返回路径
|
||
if start_page is not None and mid_page is not None and end_page is not None:
|
||
return perform_extraction_and_save(start_page, mid_page, end_page)
|
||
|
||
print(f"第一次提取tobidders_notice失败，尝试第二次提取: {pdf_path}")
|
||
start_page, mid_page, end_page = extract_pages_twice_tobidders_notice(pdf_document, common_header, begin_page)
|
||
|
||
if start_page is not None and mid_page is not None and end_page is not None:
|
||
return perform_extraction_and_save(start_page, mid_page, end_page)
|
||
|
||
print("第二次提取tobidders_notice失败，尝试第三次提取!")
|
||
new_begin_pattern = regex.compile(
|
||
r'.*(?:投标人|磋商|谈判|供应商|应答人|比选申请人).*须知\s*$|'
|
||
r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!"\s*)(?<!"\s*)(?:投标人?|磋商|谈判|供应商|应答人|比选申请人).*须知前附表\s*$',
|
||
regex.MULTILINE
|
||
)
|
||
start_page, mid_page, end_page = run_extraction(new_begin_pattern, extraction_stage='third')
|
||
if start_page is not None and mid_page is not None and end_page is not None:
|
||
return perform_extraction_and_save(start_page, mid_page, end_page)
|
||
else:
|
||
# 所有提取尝试均失败
|
||
print(f"三次提取tobidders_notice均失败!! {pdf_path}")
|
||
return "", ""
|
||
|
||
|
||
def extract_pages_twice_tobidders_notice(pdf_document, common_header, begin_page):
|
||
#投标须知前附表占一章、投标须知正文占一章
|
||
output_suffix = "tobidders_notice"
|
||
begin_pattern = regex.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:(?:投标人?|磋商|谈判|供应商|应答人|比选申请人).*须知)+',
|
||
regex.MULTILINE
|
||
)
|
||
end_pattern = regex.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*([\u4e00-\u9fff]+)', regex.MULTILINE # 捕获中文部分
|
||
)
|
||
exclusion_words = ["合同", "评标", "开标", "评审", "采购", "资格"] # 在这里添加需要排除的关键词
|
||
|
||
exclusion_pattern = regex.compile(r'文件的构成|文件的组成|文件构成|文件组成|文件的编制|文件编制')
|
||
|
||
# 提取第一部分
|
||
start_page1, end_page1 = extract_pages_generic(pdf_document, begin_pattern, end_pattern, begin_page, common_header,exclusion_pattern,output_suffix)
|
||
if start_page1 is None or end_page1 is None:
|
||
return None, None,None
|
||
|
||
# 提取第二部分
|
||
start_page2 = end_page1
|
||
|
||
# 检查end_page1页面的内容
|
||
text = pdf_document.pages[end_page1].extract_text() or ""
|
||
cleaned_text = clean_page_content(text, common_header)
|
||
match = end_pattern.search(cleaned_text)
|
||
|
||
if match:
|
||
# 获取匹配到的中文部分
|
||
chapter_title = match.group(1)
|
||
# 检查是否包含排除关键词
|
||
if any(word in chapter_title for word in exclusion_words):
|
||
# 如果包含排除关键词，直接返回相同的路径
|
||
return start_page1, end_page1, end_page1
|
||
|
||
# 如果不包含排除关键词，继续提取第二部分
|
||
_, end_page2 = extract_pages_generic(pdf_document, end_pattern, end_pattern, start_page2 - 1, common_header,
|
||
exclusion_pattern, output_suffix)
|
||
|
||
if end_page2 is None:
|
||
return start_page1, end_page1, None
|
||
|
||
return start_page1, end_page1, end_page2
|
||
|
||
if __name__ == "__main__":
|
||
file_path=r'D:\flask_project\flask_app\static\output\output1\2c4be864-bdab-405d-95cb-9d945d8627b3\ztbfile.pdf'
|
||
output_folder=r'D:\flask_project\flask_app\static\output\output1\2c4be864-bdab-405d-95cb-9d945d8627b3\tmp'
|
||
# res=get_invalid_file(file_path,output_folder,"",0)
|
||
|