Python实现查询一个文件中的pdf文件中的关键字_python查找pdf关键字和总页数

要求，查询一个文件中的pdf文件中的关键字，输出关键字所在PDF文件的文件名及对应的页数。

import os
import PyPDF2
 
def search_pdf_files(folder_path, keywords):
    # 初始化结果字典，以关键字为键，值为包含关键字的页面和文件名列表
    results = {keyword: [] for keyword in keywords}
 
    # 遍历指定文件夹下的所有文件
    for root, dirs, files in os.walk(folder_path):
        for filename in files:
            if filename.endswith(".pdf"):
                # 构建PDF文件的完整路径
                pdf_path = os.path.join(root, filename)
 
                # 打开PDF文件
                with open(pdf_path, "rb") as pdf_file:
                    pdf_reader = PyPDF2.PdfReader(pdf_file)
 
                    # 获取PDF的总页数
                    total_pages = len(pdf_reader.pages)
 
                    # 遍历PDF的每一页
                    for page_num in range(total_pages):
                        # 读取页面内容
                        page = pdf_reader.pages[page_num]
                        page_text = page.extract_text()
 
                        # 检查所有关键字
                        for keyword in keywords:
                            if keyword in page_text:
                                results[keyword].append({
                                    "file_name": filename,
                                    "page_number": page_num + 1  # PDF页码从1开始
                                })
 
    return results
 
# 示例用法
folder_to_search = r"C:\Users\Administrator\Desktop\2"
search_keywords = ["SVD", "线性回归", "XGBoost", "不存在的关键字"]  # 添加多个关键字，包括不存在的关键字
results = search_pdf_files(folder_to_search, search_keywords)
 
# 打印结果
for keyword, keyword_results in results.items():
    if keyword_results:
        print(f"关键字 '{keyword}' 所在的文件及页数：")
        for result in keyword_results:
            print(f"文件 '{result['file_name']}' 的第 {result['page_number']} 页")
    else:
        print(f"没有找到关键字 '{keyword}'。")
    print()  # 输出换行以区分不同关键字的结果

 为了方便且高效看论文。

用了上面那个之后发现不太对劲，找到文件后，就可以ctrl+F了，所以去掉了页数。代码如下：

import os
import PyPDF2
 
def search_pdf_files(folder_path, keywords):
    # Initialize a results dictionary with keywords as keys and lists of files as values
    results = {keyword: [] for keyword in keywords}
 
    # Initialize a set to keep track of processed files for each keyword
    processed_files = {keyword: set() for keyword in keywords}
 
    # Traverse all files in the specified folder
    for root, dirs, files in os.walk(folder_path):
        for filename in files:
            if filename.endswith(".pdf"):
                # Build the full path of the PDF file
                pdf_path = os.path.join(root, filename)
 
                # Open the PDF file
                with open(pdf_path, "rb") as pdf_file:
                    pdf_reader = PyPDF2.PdfReader(pdf_file)
 
                    # Get the total number of pages in the PDF
                    total_pages = len(pdf_reader.pages)
 
                    # Iterate through each page of the PDF
                    for page_num in range(total_pages):
                        # Read the page content
                        page = pdf_reader.pages[page_num]
                        page_text = page.extract_text()
 
                        # Check all keywords
                        for keyword in keywords:
                            if keyword in page_text:
                                # Check if this file has not been processed for this keyword
                                if filename not in processed_files[keyword]:
                                    results[keyword].append({
                                        "file_name": filename,
                                        "page_number": page_num + 1  # PDF page numbers start from 1
                                    })
                                    processed_files[keyword].add(filename)
 
    return results
 
# 示例用法
folder_to_search = r"C:\Users\Administrator\Desktop\优秀论文"
search_keywords = ["ARIMA", "XGBoost", "SVM", "支持向量机","线性回归","决策树","随机森林","模拟退火","粒子群","遗传算法","LSTM","BP神经网络","t-SNE","LightGBM","GMM","距离相关系数","灰色关联分析","互信息","信息熵","递归特征消除","综合评价","熵权法"]  # 添加多个关键字，包括不存在的关键字
results = search_pdf_files(folder_to_search, search_keywords)
 
# 打印结果
for keyword, keyword_results in results.items():
    if keyword_results:
        print(f"关键字 '{keyword}' 所在的文件及页数：")
        for result in keyword_results:
            print(f"文件 '{result['file_name']}'")
    else:
        print(f"没有找到关键字 '{keyword}'。")
    print()  # 输出换行以区分不同关键字的结果