问使用io和PyPDF2从PDF url中提取文本没有输出。

EN

import requests
from pdfminer3.layout import LAParams, LTTextBox
from pdfminer3.pdfpage import PDFPage
from pdfminer3.pdfinterp import PDFResourceManager
from pdfminer3.pdfinterp import PDFPageInterpreter
from pdfminer3.converter import PDFPageAggregator
from pdfminer3.converter import TextConverter
import io

resource_manager = PDFResourceManager()
fake_file_handle = io.StringIO()
converter = TextConverter(resource_manager, fake_file_handle, laparams=LAParams())
page_interpreter = PDFPageInterpreter(resource_manager, converter)

url = 'https://www.poderjudicial.es/search/contenidos.action?action=accessToPDF&publicinterface=true&tab=AN&reference=e3ca421447bc6b71&encode=true&optimize=20210216&databasematch=AN'

response = requests.get(url)
f = io.BytesIO(response.content)

with f as fh:

    for page in PDFPage.get_pages(fh,
                                  caching=True,
                                  check_extractable=True):
        page_interpreter.process_page(page)

    text = fake_file_handle.getvalue()

# close open handles
converter.close()
fake_file_handle.close()

print(text)