nebula-llm-qa/data/analyze_data/analyze_pdf.py

import pdfplumber
import pandas as pd

def readPdf(path, pageNumber):
    with pdfplumber.open(path) as pdf:
        content = ''
        # 读取PDF文档第i+1页
        page = pdf.pages[pageNumber]

        # page.extract_text()函数即读取文本内容，下面这步是去掉文档最下面的页码
        page_content = '\n'.join(page.extract_text().split('\n')[:-1])
        content = content + page_content
        return content