pip install PyPDF2

pip install pypdf

python -c "import PyPDF2; print(PyPDF2.__version__)"
# 輸出類似：3.0.0

# 創(chuàng)建虛擬環(huán)境
python -m venv pdf_env
# 激活虛擬環(huán)境（Windows）
pdf_env\Scripts\activate
# 激活虛擬環(huán)境（Mac/Linux）
source pdf_env/bin/activate
# 在虛擬環(huán)境中安裝
pip install PyPDF2
# 導出依賴清單
pip freeze > requirements.txt

import PyPDF2
with open('example.pdf', 'rb') as file:
    reader = PyPDF2.PdfReader(file)
    print(reader)  # 輸出：<PyPDF2._reader.PdfReader object at 0x...>

import PyPDF2

def extract_text_from_pdf(pdf_path):
    """從PDF文件中提取所有文本并打印"""
    try:
        with open(pdf_path, 'rb') as file:
            reader = PyPDF2.PdfReader(file)
            print(f"文件共 {len(reader.pages)} 頁\n")
            
            for page_num, page in enumerate(reader.pages):
                text = page.extract_text()
                print(f"--- 第 {page_num + 1} 頁 ---")
                print(text if text else "[該頁無文本或提取失敗]")
                print()
                
    except FileNotFoundError:
        print(f"錯誤：文件 '{pdf_path}' 不存在")
    except Exception as e:
        print(f"處理PDF時發(fā)生錯誤：{e}")

# 使用示例
extract_text_from_pdf('example.pdf')

# 只提取第3頁（索引從0開始，所以第3頁的索引是2）
reader = PyPDF2.PdfReader('example.pdf')
third_page_text = reader.pages[2].extract_text()
print(third_page_text)

from PyPDF2 import PdfReader, PdfWriter

def merge_pdfs(pdf_list, output_path):
    writer = PdfWriter()
    
    for pdf_file in pdf_list:
        reader = PdfReader(pdf_file)
        for page in reader.pages:
            writer.add_page(page)
    
    with open(output_path, 'wb') as f:
        writer.write(f)
    
    print(f"合并完成！共 {len(writer.pages)} 頁，保存至 {output_path}")

# 使用示例
merge_pdfs(['file1.pdf', 'file2.pdf', 'file3.pdf'], 'merged.pdf')

from PyPDF2 import PdfReader, PdfWriter

def split_pdf(input_pdf, output_dir):
    reader = PdfReader(input_pdf)
    
    for i, page in enumerate(reader.pages):
        writer = PdfWriter()
        writer.add_page(page)
        
        output_path = f"{output_dir}/page_{i+1}.pdf"
        with open(output_path, 'wb') as f:
            writer.write(f)
    
    print(f"拆分完成！共 {len(reader.pages)} 個文件")

# 只拆分前5頁
def split_first_n_pages(input_pdf, n, output_dir):
    reader = PdfReader(input_pdf)
    writer = PdfWriter()
    
    for page in reader.pages[:n]:
        writer.add_page(page)
    
    with open(f"{output_dir}/first_{n}_pages.pdf", 'wb') as f:
        writer.write(f)

from PyPDF2 import PdfReader

reader = PdfReader('example.pdf')
info = reader.metadata

print("=" * 40)
print("PDF 元信息")
print("=" * 40)
print(f"標題: {info.title}")
print(f"作者: {info.author}")
print(f"主題: {info.subject}")
print(f"創(chuàng)建者: info.creator}")
print(f"生產(chǎn)者: info.producer}")
print(f"頁數(shù): {len(reader.pages)}")
print(f"是否加密: {reader.is_encrypted}")
print("=" * 40)

from PyPDF2 import PdfReader

reader = PdfReader('encrypted.pdf')

if reader.is_encrypted:
    try:
        # 嘗試解密
        reader.decrypt('your_password')
        print("解密成功！")
        
        # 現(xiàn)在可以正常提取文本
        text = reader.pages[0].extract_text()
        print(text)
    except Exception as e:
        print(f"解密失?。簕e}")
else:
    print("文件未加密，直接讀取")

# 原本應該是："這是一份中文PDF文檔"
# 實際輸出：
"??è????????PDF??￡"
# 或者輸出：
"?????????"

from PyPDF2 import PdfReader

def check_pdf_extractability(pdf_path):
    reader = PdfReader(pdf_path)
    
    print(f"文件名: {pdf_path}")
    print(f"頁數(shù): {len(reader.pages)}")
    print(f"是否加密: {reader.is_encrypted}")
    
    # 嘗試提取第一頁的前200個字符
    sample = reader.pages[0].extract_text()[:200]
    print(f"第一頁預覽: {sample}")
    
    # 檢查生產(chǎn)者信息
    producer = reader.metadata.get('/Producer', '未知')
    print(f"生產(chǎn)者: {producer}")
    
    # 初步判斷
    if any(ord(c) > 127 for c in sample if c):
        print(">>> 可能包含非ASCII字符（中文），提取結果可能存在亂碼風險")
    else:
        print(">>> 僅包含ASCII字符，提取相對可靠")

check_pdf_extractability('test.pdf')

# pip install pdfplumber
import pdfplumber

with pdfplumber.open('chinese_doc.pdf') as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

from pypdf import PdfReader

# 添加strict=False忽略部分解析警告
reader = PdfReader('chinese_doc.pdf', strict=False)
text = reader.pages[0].extract_text()

# 圖片型PDF需要先轉換為圖片，再用OCR識別
# pip install pdf2image pytesseract pillow
from pdf2image import convert_from_path
import pytesseract

images = convert_from_path('scanned.pdf')
text = pytesseract.image_to_string(images[0], lang='chi_sim')
print(text)

# 嘗試手動修復編碼（僅適用于特定場景）
def fix_encoding(broken_text):
    # 嘗試不同的編碼方式
    for encoding in ['gbk', 'gb2312', 'big5', 'utf-8']:
        try:
            return broken_text.encode('latin1').decode(encoding)
        except:
            continue
    return broken_text

text = page.extract_text()
fixed_text = fix_encoding(text)

import os
import sys
from pathlib import Path
from PyPDF2 import PdfReader

def extract_text_from_pdf(pdf_path):
    """
    從單個PDF文件提取文本
    返回: (是否成功, 文本內(nèi)容)
    """
    try:
        reader = PdfReader(pdf_path)
        full_text = []
        
        for page_num, page in enumerate(reader.pages, 1):
            text = page.extract_text()
            if text:
                full_text.append(f"[第{page_num}頁]\n{text}\n")
            else:
                full_text.append(f"[第{page_num}頁]\n[無文本或提取失敗]\n")
        
        return True, "\n".join(full_text)
    
    except Exception as e:
        return False, f"處理失?。簕str(e)}"

def batch_extract_pdfs(input_folder, output_folder, extensions=None):
    """
    批量提取文件夾內(nèi)所有PDF的文本
    
    參數(shù):
        input_folder: 存放PDF文件的文件夾路徑
        output_folder: 輸出TXT文件的文件夾路徑
        extensions: 文件擴展名列表，默認為['.pdf']
    """
    if extensions is None:
        extensions = ['.pdf', '.PDF']
    
    # 創(chuàng)建輸出文件夾
    Path(output_folder).mkdir(parents=True, exist_ok=True)
    
    # 收集所有PDF文件
    pdf_files = []
    for ext in extensions:
        pdf_files.extend(Path(input_folder).glob(f"*{ext}"))
    
    if not pdf_files:
        print(f"在文件夾 '{input_folder}' 中未找到PDF文件")
        return
    
    print(f"共找到 {len(pdf_files)} 個PDF文件，開始處理...\n")
    
    success_count = 0
    fail_count = 0
    
    for pdf_file in pdf_files:
        print(f"正在處理: {pdf_file.name} ...")
        
        success, content = extract_text_from_pdf(str(pdf_file))
        
        output_path = Path(output_folder) / f"{pdf_file.stem}.txt"
        
        with open(output_path, 'w', encoding='utf-8') as f:
            f.write(content)
        
        if success:
            success_count += 1
            print(f"  ? 成功，已保存至: {output_path.name}")
        else:
            fail_count += 1
            print(f"  ? 失敗: {content[:100]}")
    
    print(f"\n{'='*50}")
    print(f"處理完成！成功: {success_count}，失敗: {fail_count}")
    print(f"輸出目錄: {output_folder}")
    print(f"{'='*50}")

def extract_with_progress(input_folder, output_folder, show_preview=True):
    """
    帶進度預覽的批量提取功能
    """
    pdf_files = list(Path(input_folder).glob("*.pdf")) + list(Path(input_folder).glob("*.PDF"))
    total = len(pdf_files)
    
    for idx, pdf_file in enumerate(pdf_files, 1):
        print(f"[{idx}/{total}] 處理: {pdf_file.name}")
        
        success, content = extract_text_from_pdf(str(pdf_file))
        
        if show_preview and success:
            preview = content[:200].replace('\n', ' ')
            print(f"  預覽: {preview}...")
        
        output_path = Path(output_folder) / f"{pdf_file.stem}.txt"
        with open(output_path, 'w', encoding='utf-8') as f:
            f.write(content)
        
        print(f"  ? 已保存\n")

if __name__ == "__main__":
    # 方式1：直接運行
    INPUT_DIR = "./pdfs"      # 存放PDF的文件夾
    OUTPUT_DIR = "./output"   # 輸出TXT的文件夾
    
    # 方式2：命令行傳參
    if len(sys.argv) >= 3:
        INPUT_DIR = sys.argv[1]
        OUTPUT_DIR = sys.argv[2]
    
    batch_extract_pdfs(INPUT_DIR, OUTPUT_DIR)
    
    # 如果需要更詳細的處理進度，使用以下函數(shù)
    # extract_with_progress(INPUT_DIR, OUTPUT_DIR, show_preview=True)