import fitz # PyMuPDF库 import os # 读取PDF文件的内容 def read_pdf(file_path): doc = fitz.open(file_path) content = "" for page in doc: content += page.getText("text") doc.close() return content # 去除字符串中的空格和空行 def remove_spaces(text): return "\n".join([line.strip() for line in text.split("\n") if line.strip()]) # 将字符串按中文句号分割成多个语句 def split_sentences(text): sentences = [] for sentence in text.split("。"): sentence = sentence.strip() if sentence: sentences.append(sentence + "。") return sentences # 读取指定目录下所有PDF文件的内容并合并成一个字符串 def read_all_pdfs(dir_path): all_content = "" for file_name in os.listdir(dir_path): if file_name.endswith(".pdf"): file_path = os.path.join(dir_path, file_name) content = read_pdf(file_path) content = remove_spaces(content) all_content += content return all_content # 将字符串按中文句号分割成多个语句并打印出来 def print_sentences(text): sentences = split_sentences(text) for sentence in sentences: print(sentence) # 测试 dir_path = r"D:\点宽学院" all_content = read_all_pdfs(dir_path) print_sentences(all_content)代码运行显示AttributeError: 'Page' object has no attribute 'getText'我该如何修改

这个错误可能是因为fitz的版本问题，可以尝试更新fitz库。同时，建议在读取PDF文件时，使用try-except语句来捕捉异常，以便更好地处理错误。

以下是更新fitz库和添加try-except语句的修改代码：

import fitz # PyMuPDF库 
import os # 读取PDF文件的内容 

def read_pdf(file_path):     
    doc = fitz.open(file_path)     
    content = ""     
    for page in doc:         
        try:
            content += page.getText("text")         
        except:
            pass
    doc.close()     
    return content  

# 去除字符串中的空格和空行 
def remove_spaces(text):     
    return "\n".join([line.strip() for line in text.split("\n") if line.strip()])  

# 将字符串按中文句号分割成多个语句 
def split_sentences(text):     
    sentences = []     
    for sentence in text.split("。"):         
        sentence = sentence.strip()         
        if sentence:             
            sentences.append(sentence + "。")     
    return sentences  

# 读取指定目录下所有PDF文件的内容并合并成一个字符串 
def read_all_pdfs(dir_path):     
    all_content = ""     
    for file_name in os.listdir(dir_path):         
        if file_name.endswith(".pdf"):             
            file_path = os.path.join(dir_path, file_name)             
            content = read_pdf(file_path)             
            content = remove_spaces(content)             
            all_content += content     
    return all_content  

# 将字符串按中文句号分割成多个语句并打印出来 
def print_sentences(text):     
    sentences = split_sentences(text)     
    for sentence in sentences:         
        print(sentence)  

# 测试 
dir_path = r"D:\点宽学院" 
all_content = read_all_pdfs(dir_path) 
print_sentences(all_content)