2

我正在尝试解析这个文件,但没有从网站上下载它。我已经用我硬盘上的文件运行了这个,我可以毫无问题地解析它,但是运行这个脚本它会跳闸。

if not document.is_extractable:
raise PDFTextExtractionNotAllowed

我想我把网址整合错了。

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'
4

2 回答 2

2

基于您自己的答案和此处提供的功能,这应该从 url 中的 pdf 返回一个字符串,而无需下载它:

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
于 2014-05-24T01:16:47.223 回答
2

扩展上面的答案,对我来说有点黑客工作就像一个魅力!这是我的功能版本:

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
于 2018-11-17T18:03:51.793 回答