Parsing a PDF via URL with Python using pdfminer

会有一股神秘感。 提交于 2020-07-05 12:35:25

问题


I am trying to parse this file but without downloading it off of the website. I have run this with the file on my hard drive and I am able to parse it without issue but running this script it trips.

if not document.is_extractable:
raise PDFTextExtractionNotAllowed

I think I am integrating the url wrong.

import sys
import getopt
import urllib2
import datetime
import re
from pdfminer.pdfparser import PDFParser
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter, PDFConverter, LTContainer, LTText, LTTextBox, LTImage
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf
from urllib2 import Request


# Define a PDF parser function
def parsePDF(url):

    # Open the url provided as an argument to the function and read the content
    open = urllib2.urlopen(Request(url)).read()

    # Cast to StringIO object
    from StringIO import StringIO
    memory_file = StringIO(open)

    # Create a PDF parser object associated with the StringIO object
    parser = PDFParser(memory_file)

    # Create a PDF document object that stores the document structure
    document = PDFDocument(parser)

    # Check if the document allows text extraction. If not, abort.
    if not document.is_extractable:
    raise PDFTextExtractionNotAllowed

     # Define parameters to the PDF device objet 
     rsrcmgr = PDFResourceManager()
     retstr = StringIO()
     laparams = LAParams()
     codec = 'utf-8'

     Create a PDF device object
     device = PDFDevice(rsrcmgr, retstr, codec = codec, laparams = laparams)
     # Create a PDF interpreter object
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    # Process each page contained in the document
    for page in PDFPage.create_pages(document):
        interpreter.process_page(page)

# Construct the url
    url = 'http://www.city.pittsburgh.pa.us/police/blotter/blotter_monday.pdf'

回答1:


Building on your own answer and the function provided here, this should return a string from a pdf in a url without downloading it:

import urllib2
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO


def pdf_from_url_to_txt(url):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    # Open the url provided as an argument to the function and read the content
    f = urllib2.urlopen(urllib2.Request(url)).read()
    # Cast to StringIO object
    fp = StringIO(f)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos = set()
    for page in PDFPage.get_pages(fp,
                                  pagenos,
                                  maxpages=maxpages,
                                  password=password,
                                  caching=caching,
                                  check_extractable=True):
        interpreter.process_page(page)
    fp.close()
    device.close()
    str = retstr.getvalue()
    retstr.close()
    return str



回答2:


Extending above answer, a little hack work for me like a charm! Here is mine version of function:

def pdf_from_url_to_txt(url):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    f = urllib.request.urlopen(url).read()
    fp = BytesIO(f)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos = set()
    for page in PDFPage.get_pages(fp,
                                  pagenos,
                                  maxpages=maxpages,
                                  password=password,
                                  caching=caching,
                                  check_extractable=True):
        interpreter.process_page(page)
    fp.close()
    device.close()
    str = retstr.getvalue()
    retstr.close()
    return str


来源:https://stackoverflow.com/questions/22800100/parsing-a-pdf-via-url-with-python-using-pdfminer

易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!