提取全部文本 #460

New Issue

goodboychen · 2025-01-03T16:46:53+08:00

goodboychen commented

2025-01-03 16:46:53 +08:00

def extract_text_from_pdf(filename, page_numbers=None, min_line_length=1):
'''从 PDF 文件中（按指定页码）提取文字'''
paragraphs = []
buffer = ''
full_text = ''
# 提取全部文本
for i, page_layout in enumerate(extract_pages(filename)):
# 如果指定了页码范围，跳过范围外的页
if page_numbers is not None and i not in page_numbers:
continue
for element in page_layout:
if isinstance(element, LTTextContainer):
full_text += element.get_text() + '\n'
# 按空行分隔，将文本重新组织成段落
lines = full_text.split('\n')
for text in lines:
if len(text) >= min_line_length:
buffer += (' ' + text) if not text.endswith('-') else text.strip('-')
elif buffer:
paragraphs.append(buffer)
buffer = ''
if buffer:
paragraphs.append(buffer)
return paragraphs

paragraphs = extract_text_from_pdf("oracle_dba.pdf", page_numbers=[2, 3,4,5,6,7,8,9,10,11,100,101,102], min_line_length=10)

如何提取整个文档的内容？

def extract_text_from_pdf(filename, page_numbers=None, min_line_length=1): '''从 PDF 文件中（按指定页码）提取文字''' paragraphs = [] buffer = '' full_text = '' # 提取全部文本 for i, page_layout in enumerate(extract_pages(filename)): # 如果指定了页码范围，跳过范围外的页 if page_numbers is not None and i not in page_numbers: continue for element in page_layout: if isinstance(element, LTTextContainer): full_text += element.get_text() + '\n' # 按空行分隔，将文本重新组织成段落 lines = full_text.split('\n') for text in lines: if len(text) >= min_line_length: buffer += (' ' + text) if not text.endswith('-') else text.strip('-') elif buffer: paragraphs.append(buffer) buffer = '' if buffer: paragraphs.append(buffer) return paragraphs paragraphs = extract_text_from_pdf("oracle_dba.pdf", page_numbers=[2, 3,4,5,6,7,8,9,10,11,100,101,102], min_line_length=10) 如何提取整个文档的内容？

12019701659cs commented

2025-01-03 19:29:22 +08:00

如果这个代码可以提取的话，就一页一页提取，然后放到一个向量数据库里面就行

Sign in to join this conversation.