如何在 Python 中使用 pdfplumber 打开多个 pdf 文件？

Question

我有一个装满 pdf 文件的文件夹。我需要根据给定的条件遍历每个 pdf 文件。使用熊猫是不可能的。有没有什么方法可以使用 pdfplumber 遍历每个文件？

import os
import glob
import shutil
import pandas as pd
import plotly.express as px
import xlrd
import matplotlib.pyplot as plt
%matplotlib inline
import time
from datetime import datetime
from pytz import timezone
import numpy as np
from tabula import read_pdf
import tabula
import requests
import pdfplumber
from tabula import read_pdf

glob.glob("C:/Users/Dreamer/Desktop/test_run/machine/*.pdf")



#THIS IS THE CONDITION I WANT TO IMPLEMENT IN EACH FILE

with pdfplumber.open(path) as pdf:
    page = pdf.pages[0]
    text = page.extract_text()

for row in text.split('\n'):
    if row.startswith('Raumtemperatur '):
        jobstart = row.split()[-2]
        jobend   = row.split()[-1]
print("jobstart", jobstart) 
print("jobstart", jobend)

期待解决方案或替代方案:)

Answer 1

IIUC，

import glob
from tqdm.auto import tqdm
for current_pdf_file in tqdm(glob.glob("C:/Users/Dreamer/Desktop/test_run/machine/*.pdf")):
    with pdfplumber.open(current_pdf_file) as my_pdf:
         # do other things here?