我正在尝试使用pdfminer.six从PDF文件中提取数据。我已经从该软件包中下载了示例代码，并使用“ pip install pdfminer.six”进行了安装，并且正在对其进行测试并因该错误而停止
Traceback (most recent call last):
File "pdf2txt.py", line 11, in <module>
import pdfminer.high_level
File "C:\xxx\xxxx\AppData\Local\Programs\Python\Python36-32\lib\site-
packages\pdfminer\high_level.py", line 11, in <module>
from .pdfdocument import PDFDocument
File "C:\xxx\uxxx\AppData\Local\Programs\Python\Python36-32\lib\site-
packages\pdfminer\pdfdocument.py", line 26, in <module>
from .pdftypes import PDFObjectNotFound
ImportError: cannot import name 'PDFObjectNotFound'
和我的代码pdf2txt.py
#!/usr/bin/env python
import sys
import logging
import six
import pdfminer.settings
pdfminer.settings.STRICT = False
import pdfminer.high_level
import pdfminer.layout
from pdfminer.image import ImageWriter
from io import StringIO
def extract_text(files=[], outfile='-',
_py2_no_more_posargs=None, # Bloody Python2 needs a shim
no_laparams=False, all_texts=None, detect_vertical=None,
word_margin=None, char_margin=None, line_margin=None,
boxes_flow=None, # LAParams
output_type='text', codec='utf-8', strip_control=False,
maxpages=0, page_numbers=None, password="", scale=1.0, rotation=0,
layoutmode='normal', output_dir=None, debug=False,
disable_caching=False, **other):
if _py2_no_more_posargs is not None:
raise ValueError("Too many positional arguments passed.")
if not files:
raise ValueError("Must provide files to work upon!")
# If any LAParams group arguments were passed, create an LAParams object and
# populate with given args. Otherwise, set it to None.
if not no_laparams:
laparams = pdfminer.layout.LAParams()
for param in ("all_texts", "detect_vertical", "word_margin", "char_margin", "line_margin", "boxes_flow"):
paramv = locals().get(param, None)
if paramv is not None:
setattr(laparams, param, paramv)
else:
laparams = None
imagewriter = None
if output_dir:
imagewriter = ImageWriter(output_dir)
if output_type == "text" and outfile != "-":
for override, alttype in ( (".htm", "html"),
(".html", "html"),
(".xml", "xml"),
(".tag", "tag") ):
if outfile.endswith(override):
output_type = alttype
if outfile == "-":
outfp = sys.stdout
if outfp.encoding is not None:
codec = 'utf-8'
else:
outfp = open(outfile, "wb")
for fname in files:
with open(fname, "rb") as fp:
pdfminer.high_level.extract_text_to_fp(fp, **locals())
return outfp
def main(args=None):
import argparse
P = argparse.ArgumentParser(description=__doc__)
P.add_argument("files", type=str, default=None, nargs="+", help="Files to
process.")
P.add_argument("-d", "--debug", default=False, action="store_true",
help="Debug output.")
P.add_argument("-p", "--pagenos", type=str, help="Comma-separated list of
page numbers to parse. Included for legacy applications, use -P/--page-
numbers for more idiomatic argument entry.")
P.add_argument("--page-numbers", type=int, default=None, nargs="+",
help="Alternative to --pagenos with space-separated numbers; supercedes -
-pagenos where it is used.")
P.add_argument("-m", "--maxpages", type=int, default=0, help = "Maximum
pages to parse")
P.add_argument("-P", "--password", type=str, default="", help =
"Decryption password for PDF")
P.add_argument("-o", "--outfile", type=str, default="-", help="Output
file (default/'-' is stdout)")
P.add_argument("-t", "--output_type", type=str, default="text", help =
"Output type: text|html|xml|tag (default is text)")
P.add_argument("-c", "--codec", type=str, default="utf-8", help = "Text
encoding")
P.add_argument("-s", "--scale", type=float, default=1.0, help = "Scale")
P.add_argument("-A", "--all-texts", default=None, action="store_true",
help="LAParams all texts")
P.add_argument("-V", "--detect-vertical", default=None,
action="store_true", help="LAParams detect vertical")
P.add_argument("-W", "--word-margin", type=float, default=None, help =
"LAParams word margin")
P.add_argument("-M", "--char-margin", type=float, default=None, help =
"LAParams char margin")
P.add_argument("-L", "--line-margin", type=float, default=None, help =
"LAParams line margin")
P.add_argument("-F", "--boxes-flow", type=float, default=None, help =
"LAParams boxes flow")
P.add_argument("-Y", "--layoutmode", default="normal", type=str,
help="HTML Layout Mode")
P.add_argument("-n", "--no-laparams", default=False, action="store_true",
help = "Pass None as LAParams")
P.add_argument("-R", "--rotation", default=0, type=int, help = "Rotation")
P.add_argument("-O", "--output-dir", default=None, help="Output directory
for images")
P.add_argument("-C", "--disable-caching", default=False,
action="store_true", help="Disable caching")
P.add_argument("-S", "--strip-control", default=False,
action="store_true", help="Strip control in XML mode")
A = P.parse_args(args=args)
if A.page_numbers:
A.page_numbers = set([x-1 for x in A.page_numbers])
if A.pagenos:
A.page_numbers = set([int(x)-1 for x in A.pagenos.split(",")])
imagewriter = None
if A.output_dir:
imagewriter = ImageWriter(A.output_dir)
if six.PY2 and sys.stdin.encoding:
A.password = A.password.decode(sys.stdin.encoding)
if A.output_type == "text" and A.outfile != "-":
for override, alttype in ( (".htm", "html"),
(".html", "html"),
(".xml", "xml" ),
(".tag", "tag" ) ):
if A.outfile.endswith(override):
A.output_type = alttype
if A.outfile == "-":
outfp = sys.stdout
if outfp.encoding is not None:
# Why ignore outfp.encoding? :-/ stupid cathal?
A.codec = 'utf-8'
else:
outfp = open(A.outfile, "wb")
## Test Code
outfp = extract_text(**vars(A))
outfp.close()
return 0
如果 name ==' main '：sys.exit（main（））
请帮助我。 预先感谢