python从列中打开PDF urls并将文本数据加载到新列中

import requests
import io
import subprocess
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfinterp import PDFPageInterpreter, PDFResourceManager
import pandas as pd

# 从URL中打开PDF文件
def open_pdf_from_url(url):
    response = requests.get(url)
    with open('temp.pdf', 'wb') as f:
        f.write(response.content)
    subprocess.Popen(['open', 'temp.pdf'])  # 适用于MacOS，Windows和Linux系统请使用不同的命令

# 将PDF文件中的文本数据加载到新列中
def load_text_from_pdf(file_path, df, new_column):
    with open(file_path, 'rb') as f:
        parser = PDFParser(f)
        document = PDFDocument(parser)
        rsrcmgr = PDFResourceManager()
        device = io.StringIO()
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        for page in PDFPage.create_pages(document):
            interpreter.process_page(page)
            text = device.getvalue()
            df = df.assign(**{new_column: text})
    return df

# 示例代码
df = pd.DataFrame({'URL': ['http://example.com/pdf1.pdf', 'http://example.com/pdf2.pdf']})
open_pdf_from_url(df['URL'][0])
df = load_text_from_pdf('temp.pdf', df, 'Text')
print(df)