PDF 文本搜索

search_text_in_pdf.py

#!/usr/bin/env python3
'''
pip install pdfminer3k
'''
from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed
from pdfminer.layout import LAParams, LTTextContainer
from pdfminer.converter import PDFPageAggregator
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter


def search(pdf_path, key):
    fp = open(pdf_path, 'rb')
    parser = PDFParser(fp)
    doc = PDFDocument()
    parser.set_document(doc)
    doc.set_parser(parser)
    doc.initialize()

    if not doc.is_extractable:
        raise PDFTextExtractionNotAllowed
    else:
        rsrcmgr = PDFResourceManager()
        laparams = LAParams()
        device = PDFPageAggregator(rsrcmgr, laparams=laparams)
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        text = ''
        for page in doc.get_pages():
            interpreter.process_page(page)
            layout = device.get_result()
            for x in layout:
                if isinstance(x, LTTextContainer):
                    text += x.get_text().strip()
                    if key in text:
                        return True
    return False