Python从PDF中提取文本的方法效率总结

pip install pdfplumber

import pdfplumber
def pdf2txt(pdf_path):
    txt = ''
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            txt = txt + page.extract_text()
    return txt

pip install pdfminer

from pdfminer.converter import TextConverter
from pdfminer.pdfdocument import PDFTextExtractionNotAllowed
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
def parsePDF(PDF_path):
    resource_manager = PDFResourceManager()
    fake_file_handle = io.StringIO()
    converter = TextConverter(resource_manager,fake_file_handle)
    page_interpreter = PDFPageInterpreter(resource_manager,converter)
    with open(PDF_path,'rb') as fh:
        for page in PDFPage.get_pages(fh,caching=True,check_extractable=True):
            page_interpreter.process_page(page)
        text = fake_file_handle.getvalue()
    converter.close()
    fake_file_handle.close()
    if text:
        return text

pip install pymupdf

import fitz
def parsePDF(filePath):
    with fitz.open(filePath) as doc:
        text = ""
        for page in doc.pages():
            text += page.get_text()
        if text:
            return text