使用 PyPDF2 从 PDF 中提取阿拉伯语数据

Question

我想用python3编写一个函数，从有235页、大小为13.6mb的阿拉伯语pdf文件中提取数据，重点是从第51页到第67页（含）提取数据，然后根据特定输入过滤提取的数据，然后导出最终过滤后的数据数据卓越。

现在的问题是 Excel 文件是空的，当我尝试调查时，我发现“df”没有以阿拉伯语形式正确打印，而是以相反的相当混乱的形状打印。

这是我迄今为止编写的代码...

from PyPDF2 import PdfReader
import pandas as pd
from pandas import ExcelWriter
from io import StringIO
from pdfminer.high_level import extract_text
from pathlib import Path
import fitz
import arabic_reshaper
from bidi.algorithm import get_display

def reshape_text(text):
    reshaped_text = arabic_reshaper.reshape(text)
    bidi_text = get_display(reshaped_text)
    return bidi_text

def flat_filter():
    # try:
        print("Starting PDF processing...")
        pdf_path = Path(r"C:\Users\Documents\Personal\Python\pd\char.pdf")

        if not pdf_path.exists():
            raise FileNotFoundError(f"Error: PDF file not found at path: {pdf_path}")
        start_page = 51
        end_page = 67
        
        with open(pdf_path, "rb") as pdf_file:
            chunks = [] #store the upcoming dfs
            for page_num in range(start_page, end_page + 1):
                # page = doc.load_page(page_num)
                # text = page.get_text("text")
                # page = pdf_reader.pages[page_num]
                # text = page.extract_text()
                text = extract_text(pdf_path, page_numbers=[page_num], maxpages=1, password="")
                # print(text)
                filtered_text = [line for line in text.splitlines() if
                                 not any(word.lower() in line.lower() for word in ["a", "130", "الأرضي"])]
                # print(filtered_text)
                chunk_df = pd.DataFrame([line.split() for line in filtered_text])
                chunks.append(chunk_df)
            df = pd.concat(chunks, ignore_index=True)
            # print("DataFrame shape:", df.shape)
            # print("DataFrame columns:", df.columns)
            #print(df)

        columns_to_filter = [2, 4, 5, 7]  #(0-based)
        filter_conditions = []  #store the filter conditions

        while True:
            condition = input("Enter a filter condition for column {}:..".format(columns_to_filter[len(filter_conditions)]+1))
            filter_conditions.append(condition)
            choice = input("Do you want to add another filter condition? (yes/no): ")
            if choice.lower() == 'no':
                for col_index, condition in zip(columns_to_filter, filter_conditions):
                    filter_combined = " & ".join(filter_conditions)
                    df = df[(df.iloc[:, columns_to_filter].fillna('').apply(lambda x: x.str.contains(filter_combined)).all(axis=1))]

                print("Exporting DataFrame to Excel...")
                # Export DataFrame to Excel file
                writer = pd.ExcelWriter("FLAT.xlsx", engine='openpyxl')
                df = df.map(reshape_text)
                df.to_excel(writer, sheet_name="Data", index=True)
                writer.close()
                print("Successfully exported filtered data to FLAT.xlsx!")
                break

    # except Exception as e:
        # print(e)

flat_filter()

我需要提取的数据图像：

Answer 1

这应该可以帮助您开始。它将：-

• 提取表格数据
• 放入DF
• 整理标题
• 给出新索引但保留page_index

接下来，您可以根据需要对数据进行排序/过滤。

阿拉伯文本的标题存在一些问题，因此您可能需要单独处理这些问题。您可以使用 df.rename() 方法来更新它们。我的假设是标题在提取的所有页面上都相同。

import pandas as pd
import fitz

pdf_file = r'arabic_doc.pdf'

list_of_list = []
doc = fitz.open(pdf_file)
for page in doc.pages(51, 67):
    tabs = page.find_tables()
    if tabs.tables:
        list_of_list.append(tabs[0].extract())
       

df = pd.concat([pd.DataFrame(d) for d in list_of_list])
df.columns = df.iloc[0]
df = df.drop([0], axis=0)
df = df.rename_axis('page_index').reset_index()
df.head()