Question

我想使用下面的代码使用pdfminer从在线PDF中提取文本，它没有显示错误，但输出没有任何内容

from pdfminer.pdfpage import PDFPage
from urllib import request
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from io import StringIO
from io import open

def readPDF(pdfFile):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, laparams=laparams)
    PDFPage.get_pages(rsrcmgr, device, pdfFile)
    device.close()
    content = retstr.getvalue()
    retstr.close()
    return content

pdfFile = request.urlopen("https://www.jstage.jst.go.jp/article/cancer/9/0/9_KJ00003588219/_pdf/-char/en")
outputString = readPDF(pdfFile)
print(outputString)

Answer 1

我建议您使用pdftotext库提取文本。

import pdftotext
fh = open(document_name, 'rb')
pdf = pdftotext.PDF(fh)
text = ""
for page in pdf:
    text += page
print(text)

Answer 2

以下代码在Python 3.7.4中有效

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.layout import LAParams
from pdfminer.converter import TextConverter
from pdfminer.pdfpage import PDFPage
import io
import urllib.request
import requests


def pdf_to_text(pdf_file):
    text_memory_file = io.StringIO()

    rsrcmgr = PDFResourceManager()
    device = TextConverter(rsrcmgr, text_memory_file, laparams=LAParams())
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    # get first 3 pages of the pdf file
    for page in PDFPage.get_pages(pdf_file, pagenos=(0, 1, 2)):
        interpreter.process_page(page)
    text = text_memory_file.getvalue()
    text_memory_file.close()
    return text

# # online pdf to text by urllib
# online_pdf_file=urllib.request.urlopen('http://www.dabeaz.com/python/UnderstandingGIL.pdf')
# pdf_memory_file=io.BytesIO()
# pdf_memory_file.write(online_pdf_file.read())
# print(pdf_to_text(pdf_memory_file))


# online pdf to text by requests
response = requests.get('http://www.dabeaz.com/python/UnderstandingGIL.pdf')
pdf_memory_file = io.BytesIO()
pdf_memory_file.write(response.content)
print(pdf_to_text(pdf_memory_file))

如何在python中使用pdfminer从在线PDF中提取文本

2 个答案: