用pdfminer.six打开一个PDF，从一个URL中打开。

Posted 2021-04-03

背景：Python 3.7 Python 3.7 & pdfminer.six

使用这里的信息。用Python从PDF导出数据我有以下代码。

import io

from pdfminer.converter import TextConverter
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfpage import PDFPage

def extract_text_from_pdf(pdf_path):
    resource_manager = PDFResourceManager()
    fake_file_handle = io.StringIO()
    converter = TextConverter(resource_manager, fake_file_handle)
    page_interpreter = PDFPageInterpreter(resource_manager, converter)

    with open(pdf_path, 'rb') 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()

    if text:
        return text

if __name__ == '__main__':
    path = '../_pdfs/mypdf.pdf'
    print(extract_text_from_pdf(path))

这可以工作(yay!)，但我真正想做的是通过它的url直接请求pdf，而不是打开一个已经预先保存到本地驱动器的pdf。

我不知道如何修改 "with open "逻辑以从远程url调用，也不确定我最好使用最新版本的Python的哪个请求库 (requests, urllib, urllib2, 等等)。

我是Python的新手，所以请记住这一点 (P.s. 我找到了其他的问题，但是没有一个能让我满意的 - 可能是因为它们都很老了。)

任何帮助都将非常感激! 任何帮助都将非常感激！谢谢

答案

你可以使用 PyPDF2 来解析一个pdf文件。试试这个。

import requests, PyPDF2
# Fill address with your url
try:
    response = requests.get(address)
except:
    print("Error")
my_raw_data = response.content
with open("my_pdf.pdf", 'wb') as my_data:
    my_data.write(my_raw_data)
my_data.close()
open_pdf_file = open("my_pdf.pdf", 'rb')
try:
    read_pdf = PyPDF2.PdfFileReader(open_pdf_file)
except:
    print("Failed to read, Press Enter to continue :")
if read_pdf.isEncrypted:
    read_pdf.decrypt("")
n = read_pdf.getNumPages()
for x in range(0,n):
    try:
        s = read_pdf.getPage(x).extractText()
    except:
        print("Error in",i)
        continue
    print(s)

另一答案

我的解决方法如下。

from io import StringIO, BytesIO
import urllib.request

from pdfminer.converter import TextConverter
from pdfminer.pdfinterp import PDFPageInterpreter, PDFResourceManager
from pdfminer.pdfpage import PDFPage

def extract_text_from_pdf_url(url, user_agent=None):
    resource_manager = PDFResourceManager()
    fake_file_handle = StringIO()
    converter = TextConverter(resource_manager, fake_file_handle)    

    if user_agent == None:
        user_agent = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/83.0.4103.61 Safari/537.36'

    headers = {'User-Agent': user_agent}
    request = urllib.request.Request(url, data=None, headers=headers)

    response = urllib.request.urlopen(request).read()
    fb = BytesIO(response)

    page_interpreter = PDFPageInterpreter(resource_manager, converter)

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


    text = fake_file_handle.getvalue()

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

    if text:
        # If document has instances of \xa0 replace them with spaces.
        # NOTE: \xa0 is non-breaking space in Latin1 (ISO 8859-1) & chr(160)
        text = text.replace(u'\xa0', u' ')

        return text