pip install pymupdf

import fitz  # pymupdf的導(dǎo)入名稱是fitz

def extract_text_from_pdf(pdf_path):
    """從PDF文件中提取所有文本內(nèi)容"""
    # 打開PDF文件
    doc = fitz.open(pdf_path)
    
    # 創(chuàng)建一個空字符串用于存儲文本內(nèi)容
    text = ""
    
    # 遍歷每一頁
    for page_num in range(len(doc)):
        # 獲取當前頁面
        page = doc[page_num]
        
        # 提取文本
        page_text = page.get_text()
        
        # 添加頁碼信息和頁面文本
        text += f"\n--- 第 {page_num + 1} 頁 ---\n"
        text += page_text
    
    # 關(guān)閉文檔
    doc.close()
    
    return text

# 使用示例
pdf_path = "example.pdf"  # 替換為實際的PDF文件路徑
try:
    extracted_text = extract_text_from_pdf(pdf_path)
    print("提取的文本內(nèi)容:")
    print(extracted_text[:500] + "..." if len(extracted_text) > 500 else extracted_text)
    
    # 將提取的文本保存到文件
    with open("extracted_text.txt", "w", encoding="utf-8") as f:
        f.write(extracted_text)
    print("文本已保存到 extracted_text.txt")
    
except Exception as e:
    print(f"提取文本時出錯: {e}")

import fitz
import os

def extract_images_from_pdf(pdf_path, output_folder="extracted_images"):
    """從PDF文件中提取所有圖像"""
    # 確保輸出文件夾存在
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)
    
    # 打開PDF文件
    doc = fitz.open(pdf_path)
    
    # 用于記錄提取的圖像數(shù)量
    image_count = 0
    
    # 遍歷每一頁
    for page_num in range(len(doc)):
        # 獲取當前頁面
        page = doc[page_num]
        
        # 獲取頁面上的圖像列表
        image_list = page.get_images()
        
        # 遍歷圖像列表
        for img_index, img in enumerate(image_list):
            # 獲取圖像的xref
            xref = img[0]
            
            # 獲取圖像信息
            base_image = doc.extract_image(xref)
            image_bytes = base_image["image"]
            image_ext = base_image["ext"]
            
            # 生成輸出文件名
            output_filename = f"{output_folder}/page{page_num + 1}_img{img_index + 1}.{image_ext}"
            
            # 保存圖像
            with open(output_filename, "wb") as f:
                f.write(image_bytes)
            
            image_count += 1
    
    # 關(guān)閉文檔
    doc.close()
    
    return image_count

# 使用示例
pdf_path = "example.pdf"  # 替換為實際的PDF文件路徑
try:
    num_images = extract_images_from_pdf(pdf_path)
    print(f"成功提取了 {num_images} 張圖像到 'extracted_images' 文件夾")
except Exception as e:
    print(f"提取圖像時出錯: {e}")

import fitz

def add_watermark_to_pdf(input_pdf, output_pdf, watermark_text):
    """為PDF文件添加文字水印"""
    # 打開PDF文件
    doc = fitz.open(input_pdf)
    
    # 遍歷每一頁
    for page_num in range(len(doc)):
        # 獲取當前頁面
        page = doc[page_num]
        
        # 獲取頁面尺寸
        rect = page.rect
        
        # 創(chuàng)建一個透明的水印文本
        # 設(shè)置字體大小、顏色和透明度
        text_color = (0.5, 0.5, 0.5)  # 灰色
        alpha = 0.3  # 透明度
        fontsize = 24
        
        # 在頁面中心添加水印
        tw = fitz.TextWriter(rect)
        tw.append((rect.width/2, rect.height/2), watermark_text, fontsize=fontsize, color=text_color)
        tw.write_text(page, opacity=alpha)
    
    # 保存修改后的PDF
    doc.save(output_pdf)
    doc.close()
    
    return output_pdf

# 使用示例
input_pdf = "example.pdf"  # 替換為實際的PDF文件路徑
output_pdf = "watermarked.pdf"
watermark_text = "機密文件 - 請勿外傳"

try:
    result_pdf = add_watermark_to_pdf(input_pdf, output_pdf, watermark_text)
    print(f"已成功添加水印并保存為: {result_pdf}")
except Exception as e:
    print(f"添加水印時出錯: {e}")

pip install pdfplumber

import pdfplumber
import pandas as pd

def extract_tables_from_pdf(pdf_path):
    """從PDF文件中提取所有表格"""
    # 打開PDF文件
    with pdfplumber.open(pdf_path) as pdf:
        all_tables = []
        
        # 遍歷每一頁
        for page_num, page in enumerate(pdf.pages):
            # 提取表格
            tables = page.extract_tables()
            
            if tables:
                print(f"在第 {page_num + 1} 頁找到 {len(tables)} 個表格")
                
                # 處理每個表格
                for table_num, table in enumerate(tables):
                    # 創(chuàng)建DataFrame
                    df = pd.DataFrame(table[1:], columns=table[0])
                    
                    # 添加頁碼和表格編號信息
                    df['頁碼'] = page_num + 1
                    df['表格編號'] = table_num + 1
                    
                    all_tables.append(df)
            else:
                print(f"在第 {page_num + 1} 頁沒有找到表格")
        
        # 如果找到了表格，合并所有表格
        if all_tables:
            combined_df = pd.concat(all_tables, ignore_index=True)
            return combined_df
        else:
            return None

# 使用示例
pdf_path = "example_with_tables.pdf"  # 替換為包含表格的PDF文件路徑
try:
    tables_df = extract_tables_from_pdf(pdf_path)
    
    if tables_df is not None:
        print("\n提取的表格數(shù)據(jù):")
        print(tables_df.head())
        
        # 將表格數(shù)據(jù)保存到Excel文件
        excel_path = "extracted_tables.xlsx"
        tables_df.to_excel(excel_path, index=False)
        print(f"表格數(shù)據(jù)已保存到: {excel_path}")
    else:
        print("未在PDF中找到任何表格")
        
except Exception as e:
    print(f"提取表格時出錯: {e}")

pip install PyPDF2

from PyPDF2 import PdfMerger

def merge_pdfs(pdf_files, output_path):
    """合并多個PDF文件"""
    merger = PdfMerger()
    
    # 添加每個PDF文件
    for pdf in pdf_files:
        try:
            merger.append(pdf)
            print(f"已添加: {pdf}")
        except Exception as e:
            print(f"添加 {pdf} 時出錯: {e}")
    
    # 保存合并后的PDF
    merger.write(output_path)
    merger.close()
    
    return output_path

# 使用示例
pdf_files = ["document1.pdf", "document2.pdf", "document3.pdf"]  # 替換為實際的PDF文件路徑
output_path = "merged_document.pdf"

try:
    result_path = merge_pdfs(pdf_files, output_path)
    print(f"已成功合并PDF文件并保存為: {result_path}")
except Exception as e:
    print(f"合并PDF文件時出錯: {e}")

from PyPDF2 import PdfReader, PdfWriter
import os

def split_pdf(input_pdf, output_folder="split_pages"):
    """將PDF文件拆分為單頁文件"""
    # 確保輸出文件夾存在
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)
    
    # 打開PDF文件
    reader = PdfReader(input_pdf)
    total_pages = len(reader.pages)
    
    # 獲取文件名（不含擴展名）
    base_name = os.path.splitext(os.path.basename(input_pdf))[0]
    
    # 拆分每一頁
    for page_num in range(total_pages):
        writer = PdfWriter()
        writer.add_page(reader.pages[page_num])
        
        # 生成輸出文件名
        output_filename = f"{output_folder}/{base_name}_page_{page_num + 1}.pdf"
        
        # 保存單頁PDF
        with open(output_filename, "wb") as output_file:
            writer.write(output_file)
        
        print(f"已保存第 {page_num + 1} 頁到: {output_filename}")
    
    return total_pages

# 使用示例
input_pdf = "example.pdf"  # 替換為實際的PDF文件路徑
try:
    num_pages = split_pdf(input_pdf)
    print(f"已成功將 {input_pdf} 拆分為 {num_pages} 個單頁PDF文件")
except Exception as e:
    print(f"拆分PDF文件時出錯: {e}")

from PyPDF2 import PdfReader, PdfWriter

def encrypt_pdf(input_pdf, output_pdf, password):
    """加密PDF文件"""
    reader = PdfReader(input_pdf)
    writer = PdfWriter()
    
    # 復(fù)制所有頁面
    for page in reader.pages:
        writer.add_page(page)
    
    # 設(shè)置密碼和加密選項
    writer.encrypt(password)
    
    # 保存加密后的PDF
    with open(output_pdf, "wb") as output_file:
        writer.write(output_file)
    
    return output_pdf

def decrypt_pdf(input_pdf, output_pdf, password):
    """解密PDF文件"""
    reader = PdfReader(input_pdf)
    
    # 檢查PDF是否加密
    if reader.is_encrypted:
        # 嘗試使用密碼解密
        if reader.decrypt(password) != 1:
            raise ValueError("密碼不正確")
    else:
        print("警告: 輸入的PDF文件未加密")
    
    writer = PdfWriter()
    
    # 復(fù)制所有頁面
    for page in reader.pages:
        writer.add_page(page)
    
    # 保存解密后的PDF
    with open(output_pdf, "wb") as output_file:
        writer.write(output_file)
    
    return output_pdf

# 使用示例 - 加密
input_pdf = "example.pdf"  # 替換為實際的PDF文件路徑
encrypted_pdf = "encrypted_document.pdf"
password = "secure123"  # 設(shè)置密碼

try:
    result_path = encrypt_pdf(input_pdf, encrypted_pdf, password)
    print(f"已成功加密PDF文件并保存為: {result_path}")
except Exception as e:
    print(f"加密PDF文件時出錯: {e}")

# 使用示例 - 解密
decrypted_pdf = "decrypted_document.pdf"

try:
    result_path = decrypt_pdf(encrypted_pdf, decrypted_pdf, password)
    print(f"已成功解密PDF文件并保存為: {result_path}")
except Exception as e:
    print(f"解密PDF文件時出錯: {e}")

pip install pdfkit

import pdfkit

def url_to_pdf(url, output_pdf):
    """將URL指向的網(wǎng)頁轉(zhuǎn)換為PDF"""
    try:
        # 配置wkhtmltopdf路徑（如果不在系統(tǒng)PATH中）
        # config = pdfkit.configuration(wkhtmltopdf='/path/to/wkhtmltopdf')
        # pdfkit.from_url(url, output_pdf, configuration=config)
        
        # 如果wkhtmltopdf在系統(tǒng)PATH中
        pdfkit.from_url(url, output_pdf)
        print(f"已成功將 {url} 轉(zhuǎn)換為PDF: {output_pdf}")
        return output_pdf
    except Exception as e:
        print(f"轉(zhuǎn)換網(wǎng)頁到PDF時出錯: {e}")
        return None

def html_to_pdf(html_file, output_pdf):
    """將HTML文件轉(zhuǎn)換為PDF"""
    try:
        pdfkit.from_file(html_file, output_pdf)
        print(f"已成功將 {html_file} 轉(zhuǎn)換為PDF: {output_pdf}")
        return output_pdf
    except Exception as e:
        print(f"轉(zhuǎn)換HTML文件到PDF時出錯: {e}")
        return None

def html_string_to_pdf(html_content, output_pdf):
    """將HTML字符串轉(zhuǎn)換為PDF"""
    try:
        pdfkit.from_string(html_content, output_pdf)
        print(f"已成功將HTML內(nèi)容轉(zhuǎn)換為PDF: {output_pdf}")
        return output_pdf
    except Exception as e:
        print(f"轉(zhuǎn)換HTML字符串到PDF時出錯: {e}")
        return None

# 使用示例 - 從URL創(chuàng)建PDF
url = "https://www.example.com"  # 替換為實際的URL
output_pdf = "webpage.pdf"
url_to_pdf(url, output_pdf)

# 使用示例 - 從HTML文件創(chuàng)建PDF
html_file = "example.html"  # 替換為實際的HTML文件路徑
output_pdf = "from_html_file.pdf"
html_to_pdf(html_file, output_pdf)

# 使用示例 - 從HTML字符串創(chuàng)建PDF
html_content = """<!DOCTYPE html>
<html>
<head>
    <title>測試頁面</title>
</head>
<body>
    <h1>Hello, World!</h1>
    <p>這是一個由HTML字符串生成的PDF文檔。</p>
</body>
</html>"""
output_pdf = "from_html_string.pdf"
html_string_to_pdf(html_content, output_pdf)

import subprocess

def url_to_image(url, output_image):
    """將URL指向的網(wǎng)頁轉(zhuǎn)換為圖片"""
    try:
        # 執(zhí)行wkhtmltoimage命令
        command = ["wkhtmltoimage", url, output_image]
        subprocess.run(command, check=True)
        print(f"已成功將 {url} 轉(zhuǎn)換為圖片: {output_image}")
        return output_image
    except subprocess.CalledProcessError as e:
        print(f"轉(zhuǎn)換網(wǎng)頁到圖片時出錯: {e}")
        return None
    except Exception as e:
        print(f"發(fā)生錯誤: {e}")
        return None

# 使用示例
url = "https://www.example.com"  # 替換為實際的URL
output_image = "webpage.jpg"
url_to_image(url, output_image)

from docx2pdf import convert

def word_to_pdf(input_docx, output_pdf=None):
    """將Word文檔轉(zhuǎn)換為PDF"""
    try:
        # 如果未指定輸出PDF路徑，則使用相同的文件名但擴展名為.pdf
        if output_pdf is None:
            output_pdf = input_docx.replace(".docx", ".pdf")
        
        # 轉(zhuǎn)換Word文檔為PDF
        convert(input_docx, output_pdf)
        print(f"已成功將 {input_docx} 轉(zhuǎn)換為PDF: {output_pdf}")
        return output_pdf
    except Exception as e:
        print(f"轉(zhuǎn)換Word到PDF時出錯: {e}")
        return None

# 使用示例
input_docx = "example.docx"  # 替換為實際的Word文檔路徑
word_to_pdf(input_docx)

import win32com.client
import os

def excel_to_pdf(input_excel, output_pdf=None):
    """將Excel文件轉(zhuǎn)換為PDF（僅適用于Windows系統(tǒng)）"""
    try:
        # 如果未指定輸出PDF路徑，則使用相同的文件名但擴展名為.pdf
        if output_pdf is None:
            output_pdf = input_excel.replace(".xlsx", ".pdf").replace(".xls", ".pdf")
        
        # 獲取絕對路徑
        input_excel = os.path.abspath(input_excel)
        output_pdf = os.path.abspath(output_pdf)
        
        # 創(chuàng)建Excel應(yīng)用程序?qū)嵗?
        excel = win32com.client.Dispatch("Excel.Application")
        excel.Visible = False
        
        # 打開Excel文件
        workbook = excel.Workbooks.Open(input_excel)
        
        # 將工作簿導(dǎo)出為PDF
        workbook.ExportAsFixedFormat(0, output_pdf)
        
        # 關(guān)閉工作簿和Excel應(yīng)用程序
        workbook.Close()
        excel.Quit()
        
        print(f"已成功將 {input_excel} 轉(zhuǎn)換為PDF: {output_pdf}")
        return output_pdf
    except Exception as e:
        print(f"轉(zhuǎn)換Excel到PDF時出錯: {e}")
        return None

# 使用示例（僅適用于Windows系統(tǒng)）
# input_excel = "example.xlsx"  # 替換為實際的Excel文件路徑
# excel_to_pdf(input_excel)

import os
import fitz
import re
from datetime import datetime
import pandas as pd

def process_invoice_pdfs(invoice_folder, output_excel):
    """批量處理發(fā)票PDF，提取關(guān)鍵信息并生成匯總表"""
    # 存儲提取的發(fā)票信息
    invoices_data = []
    
    # 獲取文件夾中的所有PDF文件
    pdf_files = [f for f in os.listdir(invoice_folder) if f.lower().endswith('.pdf')]
    
    for pdf_file in pdf_files:
        pdf_path = os.path.join(invoice_folder, pdf_file)
        print(f"處理: {pdf_path}")
        
        try:
            # 打開PDF文件
            doc = fitz.open(pdf_path)
            
            # 提取第一頁文本（假設(shè)發(fā)票信息在第一頁）
            text = doc[0].get_text()
            
            # 使用正則表達式提取關(guān)鍵信息
            # 注意：以下正則表達式需要根據(jù)實際發(fā)票格式進行調(diào)整
            invoice_number = re.search(r'發(fā)票號碼[：:](\s*\d+)', text)
            invoice_number = invoice_number.group(1).strip() if invoice_number else "未知"
            
            invoice_date = re.search(r'開票日期[：:](\s*\d{4}[年/-]\d{1,2}[月/-]\d{1,2})', text)
            invoice_date = invoice_date.group(1).strip() if invoice_date else "未知"
            
            amount = re.search(r'金額[：:]\s*￥?\s*(\d+\.\d{2})', text)
            amount = amount.group(1).strip() if amount else "0.00"
            
            # 將信息添加到列表
            invoices_data.append({
                '文件名': pdf_file,
                '發(fā)票號碼': invoice_number,
                '開票日期': invoice_date,
                '金額': float(amount),
            })
            
            # 關(guān)閉文檔
            doc.close()
            
        except Exception as e:
            print(f"處理 {pdf_file} 時出錯: {e}")
    
    # 創(chuàng)建DataFrame并保存為Excel
    if invoices_data:
        df = pd.DataFrame(invoices_data)
        
        # 添加總計行
        total_amount = df['金額'].sum()
        df.loc[len(df)] = ['總計', '', '', total_amount]
        
        # 保存為Excel
        df.to_excel(output_excel, index=False)
        print(f"已成功處理 {len(invoices_data)} 個發(fā)票PDF并保存匯總表到: {output_excel}")
        return output_excel
    else:
        print("未找到有效的發(fā)票PDF文件")
        return None

# 使用示例
invoice_folder = "invoices"  # 替換為實際的發(fā)票PDF文件夾路徑
output_excel = "invoice_summary.xlsx"

# process_invoice_pdfs(invoice_folder, output_excel)

import pandas as pd
import matplotlib.pyplot as plt
import fitz
import os
from datetime import datetime

def generate_sales_report_pdf(sales_data_excel, output_pdf):
    """根據(jù)銷售數(shù)據(jù)生成PDF報告"""
    # 讀取銷售數(shù)據(jù)
    df = pd.read_excel(sales_data_excel)
    
    # 創(chuàng)建臨時HTML文件
    html_path = "temp_report.html"
    
    # 生成圖表
    plt.figure(figsize=(10, 6))
    df.groupby('產(chǎn)品')['銷售額'].sum().plot(kind='bar')
    plt.title('各產(chǎn)品銷售額對比')
    plt.ylabel('銷售額')
    plt.tight_layout()
    chart_path = "sales_chart.png"
    plt.savefig(chart_path)
    
    # 計算匯總數(shù)據(jù)
    total_sales = df['銷售額'].sum()
    avg_sales = df['銷售額'].mean()
    max_product = df.loc[df['銷售額'].idxmax()]['產(chǎn)品']
    max_sales = df['銷售額'].max()
    
    # 生成HTML報告
    html_content = f"""
    <!DOCTYPE html>
    <html>
    <head>
        <title>銷售數(shù)據(jù)報告</title>
        <style>
            body {{ font-family: Arial, sans-serif; margin: 40px; }}
            h1 {{ color: #2c3e50; text-align: center; }}
            .report-date {{ text-align: right; color: #7f8c8d; }}
            .summary {{ background-color: #f8f9fa; padding: 20px; border-radius: 5px; margin: 20px 0; }}
            table {{ width: 100%; border-collapse: collapse; margin: 20px 0; }}
            th, td {{ padding: 12px; text-align: left; border-bottom: 1px solid #ddd; }}
            th {{ background-color: #3498db; color: white; }}
            tr:hover {{ background-color: #f5f5f5; }}
            .chart {{ text-align: center; margin: 30px 0; }}
            .footer {{ text-align: center; margin-top: 50px; font-size: 12px; color: #7f8c8d; }}
        </style>
    </head>
    <body>
        <div class="report-date">生成日期: {datetime.now().strftime('%Y年%m月%d日')}</div>
        <h1>銷售數(shù)據(jù)報告</h1>
        
        <div class="summary">
            <h2>銷售摘要</h2>
            <p>總銷售額: ￥{total_sales:,.2f}</p>
            <p>平均銷售額: ￥{avg_sales:,.2f}</p>
            <p>最暢銷產(chǎn)品: {max_product} (￥{max_sales:,.2f})</p>
        </div>
        
        <h2>銷售數(shù)據(jù)明細</h2>
        <table>
            <tr>
                <th>產(chǎn)品</th>
                <th>銷售量</th>
                <th>銷售額</th>
                <th>日期</th>
            </tr>
    """
    
    # 添加表格數(shù)據(jù)
    for _, row in df.iterrows():
        html_content += f"""
            <tr>
                <td>{row['產(chǎn)品']}</td>
                <td>{row['銷售量']}</td>
                <td>￥{row['銷售額']:,.2f}</td>
                <td>{row['日期']}</td>
            </tr>
        """
    
    # 添加圖表和頁腳
    html_content += f"""
        </table>
        
        <div class="chart">
            <h2>銷售圖表</h2>
            <img src="{chart_path}" alt="銷售數(shù)據(jù)圖表" style="max-width: 100%;">
        </div>
        
        <div class="footer">
            <p>此報告由Python自動生成 | 僅供內(nèi)部使用</p>
        </div>
    </body>
    </html>
    """
    
    # 保存HTML文件
    with open(html_path, "w", encoding="utf-8") as f:
        f.write(html_content)
    
    # 將HTML轉(zhuǎn)換為PDF
    import pdfkit
    try:
        pdfkit.from_file(html_path, output_pdf)
        print(f"已成功生成銷售報告PDF: {output_pdf}")
        
        # 清理臨時文件
        os.remove(html_path)
        os.remove(chart_path)
        
        return output_pdf
    except Exception as e:
        print(f"生成PDF報告時出錯: {e}")
        return None

# 使用示例
sales_data_excel = "sales_data.xlsx"  # 替換為實際的銷售數(shù)據(jù)Excel文件路徑
output_pdf = "sales_report.pdf"

# generate_sales_report_pdf(sales_data_excel, output_pdf)