关于python中PDF文件提取

相关路径：菜鸟pandas
TXT提取关键信息

import os
import time
import pandas
import pdfplumber
import xlwt
import pandas as pd
import re


class OperationPdf:

    def __init__(self):
        self.pdf = pdfplumber.open("./data/ya.pdf")

    def write_txt(self):
        if os.path.exists('./pdf.txt'):
            os.remove('./pdf.txt')
        size = len(self.pdf.pages)
        for i in range(size):
            first_page = self.pdf.pages[i]
            self.table = first_page.extract_text()
            try:
                self.fileobj = open('./pdf.txt', 'a+', encoding='utf-8')
                self.fileobj.write(self.table)
                # print(self.table)
            except IOError:
                print('写入程序中断')
        self.fileobj.close()

    def readtxt(self):
        # 读txt文件把每行数据输出为列表
        fileobj = open("./pdf-.txt", "r", encoding="utf-8")
        dataMat = []
        for line in fileobj.readlines():
            # print(line)
            curLine = line.strip().split(" ")
            #     floatLine=list(map(float,curLine))#这里使用的是map函数直接把数据转化成为float类型
            dataMat.append(curLine[:])
        disct = {}
        print('dataMat:', dataMat)
        return dataMat

    def reade(self):
        file = self.fileobj.read()
        res = re.findall('(Postman)、(Charles)、(Fiddler)、(禅道)、(Testlink)、(Tapd)、(JIRA)', file)
        if res == []:
            pass
        else:
            print(res)

    def saveas(self):
        # 切取想要的txt中的数据另存为一个文件
        fi = open("./pdf.txt", "r", encoding="utf-8")
        fo = open("./pdf-.txt", "w", encoding="utf-8")

        wflag = False
        newline = []
        dataMat = []
        for line in fi:  # 按行读入文件，此时line的type是str
            if "陈 雅" in line:  # 重置写标记
                wflag = False
            if "自我描述" in line:  # 检验是否到了要写入的内容
                wflag = True
                continue
            if "工作经历" in line:  # 检验是否到了要写入的内容
                wflag = False
            if wflag == True:
                K = list(line)
                if len(K) > 1:  # 去除文本中的空行
                    for i in K:  # 写入需要内容
                        newline.append(i)
        strlist = "".join(newline)
        newlines = str(strlist)
        D = '·'
        newlines = newlines.replace(f"{D}", "")  # 删掉句中·
        fo.write(newlines)
        fo.close()
        fi.close()







if __name__ == '__main__':
    count = 0
    j = 0
    OperationPdf().saveas()
    table = OperationPdf().readtxt()
    df = pd.DataFrame(table)
    writer = pd.ExcelWriter('./pdf.xlsx')
    if count == 0:
        df.to_excel(writer, header=False, index=False, startrow=count)
    else:
        df[1:].to_excel(writer, header=False, index=False, startrow=count - j)
        j += 1  # 避免出现空行

    # time.sleep(3)
    # pdfdebug().readtxt()