build_index/parser/pdf_parser.py

# -*-coding:utf-8 -*-
import PyPDF2
from build_index.parser.base import BaseParser


class PDFParser(BaseParser):
    def header_remove(self):
        # 删除研报的页头
        pass

    def footnote_remove(self):
        # 删除研报的页脚
        pass

    def parse_file(self, file):
        # store pages of
        text_list = []

        with open(file, "rb") as fp:
            pdf = PyPDF2.PdfReader(fp)
            num_pages = len(pdf.pages)
            for page in range(num_pages):
                page_text = pdf.pages[page].extract_text()
                text_list.append(page_text)
        text = '\n'.join(text_list)
        metadata = {'source': file, 'pages': num_pages}
        return text, metadata