python3读取pdf文件

一.安装pdfminer3k模块

python3读取pdf文件_第1张图片

二.读取pdf文件

import sys
import importlib
importlib.reload(sys)

from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LTTextBoxHorizontal, LAParams
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed

def readPDF(path, toPath):
    # 以二进制形式打开pdf文件
    with open(path, "rb") as f:
        # 创建一个pdf文档分析器
        parser = PDFParser(f)
        # 创建pdf文档
        pdfFile = PDFDocument()
        # 链接分析器与文档对象
        parser.set_document(pdfFile)
        pdfFile.set_parser(parser)
        # 提供初始化密码
        pdfFile.initialize()
        # 检测文档是否提供txt转换
    if not pdfFile.is_extractable:
        raise PDFTextExtractionNotAllowed
    else:
        # 解析数据
        # 数据管理
        manager = PDFResourceManager()
        # 创建一个PDF设备对象
        laparams = LAParams()
        device = PDFPageAggregator(manager, laparams=laparams)
        # 解释器对象
        interpreter = PDFPageInterpreter(manager, device)

        # 开始循环处理,每次处理一页
        for page in pdfFile.get_pages():
            interpreter.process_page(page)
            layout = device.get_result()
            for x in layout:
                if(isinstance(x, LTTextBoxHorizontal)):
                    with open(toPath, "a") as f:
                        str = x.get_text()
                        # print(str)
                        f.write(str+"\n")

path = r"G:\program\PycharmProjects\day06\3.读取pdf文件\文档.pdf"
toPath = r"G:\program\PycharmProjects\day06\3.读取pdf文件\a.txt"
readPDF(path, toPath)



你可能感兴趣的:(读取pdf文件)