在Python中，你可以使用`os`, `re`, 和 `pdfplumber` 这些库来查找指定文件夹下的PDF文件中包含特定关键字，并提取前后10个字符的信息。以下是一个基本示例：

```python import os import re from pdfplumber import PDF # 定义要搜索的关键字和要保存结果的路径 keyword = "your_keyword" output_folder = "https://blog.csdn.net/weixin_33800593/article/details/output" def extract_text_from_pdf(pdf_path): with PDF(pdf_path) as pdf: text = "" for page in pdf.pages: text += page.extract_text() return text def search_and_extract(pdf_text, keyword, n_chars=10): matches = [m.start() - n_chars for m in re.finditer(keyword, pdf_text)] return [(match, pdf_text[match : match + (n_chars * 2)]) for match in matches] # 遍历文件夹 for root, dirs, files in os.walk(".", topdown=True): if ".pdf" in files: file_path = os.path.join(root, files[0]) pdf_text = extract_text_from_pdf(file_path) if keyword in pdf_text: matched_results = search_and_extract(pdf_text, keyword) # 保存匹配到的结果 save_results(matched_results, output_folder) def save_results(results, folder): os.makedirs(folder, exist_ok=True) for index, match_info in enumerate(results): start, context = match_info with open(f"{folder}/result_{index}.txt", 'w') as f: f.write(f"Keyword found at position {start}, context: {context}") # 调用函数开始处理 search_and_extract(keyword=keyword, n_chars=10) ```