python - "File format is not supported"同时多线程处理 pdf 文件列表

Question

我正在自学 Python 线程的基础知识，但遇到了困难。 我希望脚本将函数应用于 pdf 列表。该函数只是简单地计算每个 pdf 文件中表格的数量，然后返回每个文件有多少表格的组合列表。

现在，我收到一条错误消息，指出我的“文件格式不受支持”。据我所知，列表中的每个路径都是以 .pdf 结尾的完整路径。我不知道我做错了什么？

我已将代码精简到要点，并在下面包含了我的代码

import camelot
from multiprocessing.dummy import Pool as ThreadPool 
import glob
import os


#get a list of all the pdf paths in the directory I am interested in
pdfs = [os.path.abspath(x) for x in os.listdir(r'C:\Users\josiahh\Desktop\threading_learning')]

#format each path to have the r letter in front of it
rpdfs = ["r'" + pdf + "'" for pdf in pdfs]

#function that counts each table in the pdf. THIS IS WHERE SOMETHING IS WRONG...I THINK
listoflengths = []
def len_table5(filepath):    
    tables = camelot.read_pdf(filepath, pages = '1-end',flavor='stream')
    tablelength = len(tables)
    listoflengths.append(tablelength)

#threading code
pool = ThreadPool(5) 
results = pool.map(len_table5, rpdfs)
pool.close() 
pool.join() 

任何帮助将不胜感激。如果我可以澄清任何事情，请告诉我

编辑: 在文件名前面使用 r 时进行回溯

---------------------------------------------------------------------------
NotImplementedError                       Traceback (most recent call last)
<ipython-input-57-d38bdf75c567> in <module>
      1 
      2 pool = ThreadPool(5)
----> 3 results = pool.map(len_table5, rpdfs)
      4 pool.close()
      5 pool.join()

~\AppData\Local\Continuum\anaconda3\lib\multiprocessing\pool.py in map(self, func, iterable, chunksize)
    286         in a list that is returned.
    287         '''
--> 288         return self._map_async(func, iterable, mapstar, chunksize).get()
    289 
    290     def starmap(self, func, iterable, chunksize=None):

~\AppData\Local\Continuum\anaconda3\lib\multiprocessing\pool.py in get(self, timeout)
    668             return self._value
    669         else:
--> 670             raise self._value
    671 
    672     def _set(self, i, obj):

~\AppData\Local\Continuum\anaconda3\lib\multiprocessing\pool.py in worker(inqueue, outqueue, initializer, initargs, maxtasks, wrap_exception)
    117         job, i, func, args, kwds = task
    118         try:
--> 119             result = (True, func(*args, **kwds))
    120         except Exception as e:
    121             if wrap_exception and func is not _helper_reraises_exception:

~\AppData\Local\Continuum\anaconda3\lib\multiprocessing\pool.py in mapstar(args)
     42 
     43 def mapstar(args):
---> 44     return list(map(*args))
     45 
     46 def starmapstar(args):

<ipython-input-54-025080eb0d6f> in len_table5(filepath)
      1 listoflengths = []
      2 def len_table5(filepath):
----> 3     tables = camelot.read_pdf(filepath, pages = '1-end',flavor='stream')
      4     tablelength = len(tables)
      5     listoflengths.append(tablelength)

~\AppData\Local\Continuum\anaconda3\lib\site-packages\camelot\io.py in read_pdf(filepath, pages, password, flavor, suppress_stdout, layout_kwargs, **kwargs)
    101 
    102         validate_input(kwargs, flavor=flavor)
--> 103         p = PDFHandler(filepath, pages=pages, password=password)
    104         kwargs = remove_extra(kwargs, flavor=flavor)
    105         tables = p.parse(flavor=flavor, suppress_stdout=suppress_stdout,

~\AppData\Local\Continuum\anaconda3\lib\site-packages\camelot\handlers.py in __init__(self, filepath, pages, password)
     33         self.filepath = filepath
     34         if not filepath.lower().endswith('.pdf'):
---> 35             raise NotImplementedError("File format not supported")
     36 
     37         if password is None:

NotImplementedError: File format not supported

文件路径中不使用 rs 时的回溯

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
<ipython-input-59-07744a46a83f> in <module>
      1 
      2 pool = ThreadPool(5)
----> 3 results = pool.map(len_table5, pdfs)
      4 pool.close()
      5 pool.join()

~\AppData\Local\Continuum\anaconda3\lib\multiprocessing\pool.py in map(self, func, iterable, chunksize)
    286         in a list that is returned.
    287         '''
--> 288         return self._map_async(func, iterable, mapstar, chunksize).get()
    289 
    290     def starmap(self, func, iterable, chunksize=None):

~\AppData\Local\Continuum\anaconda3\lib\multiprocessing\pool.py in get(self, timeout)
    668             return self._value
    669         else:
--> 670             raise self._value
    671 
    672     def _set(self, i, obj):

~\AppData\Local\Continuum\anaconda3\lib\multiprocessing\pool.py in worker(inqueue, outqueue, initializer, initargs, maxtasks, wrap_exception)
    117         job, i, func, args, kwds = task
    118         try:
--> 119             result = (True, func(*args, **kwds))
    120         except Exception as e:
    121             if wrap_exception and func is not _helper_reraises_exception:

~\AppData\Local\Continuum\anaconda3\lib\multiprocessing\pool.py in mapstar(args)
     42 
     43 def mapstar(args):
---> 44     return list(map(*args))
     45 
     46 def starmapstar(args):

<ipython-input-58-e6499958826d> in len_table5(filepath)
     14 listoflengths = []
     15 def len_table5(filepath):
---> 16     tables = camelot.read_pdf(filepath, pages = '1-end',flavor='stream')
     17     tablelength = len(tables)
     18     listoflengths.append(tablelength)

~\AppData\Local\Continuum\anaconda3\lib\site-packages\camelot\io.py in read_pdf(filepath, pages, password, flavor, suppress_stdout, layout_kwargs, **kwargs)
    101 
    102         validate_input(kwargs, flavor=flavor)
--> 103         p = PDFHandler(filepath, pages=pages, password=password)
    104         kwargs = remove_extra(kwargs, flavor=flavor)
    105         tables = p.parse(flavor=flavor, suppress_stdout=suppress_stdout,

~\AppData\Local\Continuum\anaconda3\lib\site-packages\camelot\handlers.py in __init__(self, filepath, pages, password)
     41             if sys.version_info[0] < 3:
     42                 self.password = self.password.encode('ascii')
---> 43         self.pages = self._get_pages(self.filepath, pages)
     44 
     45     def _get_pages(self, filepath, pages):

~\AppData\Local\Continuum\anaconda3\lib\site-packages\camelot\handlers.py in _get_pages(self, filepath, pages)
     64             page_numbers.append({'start': 1, 'end': 1})
     65         else:
---> 66             infile = PdfFileReader(open(filepath, 'rb'), strict=False)
     67             if infile.isEncrypted:
     68                 infile.decrypt(self.password)

FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\josiahh\\camelot - Copy (2) - Copy.pdf'

Answer 1

有一些事情需要考虑:

1. 不要硬编码路径字符串，它不灵活而且最有可能 无法在不同的机器上运行。
2. os.listdir() 仅返回文件夹中的文件名，因此 os.path.abspath() 不会为您提供正确的结果。
3. 不确定是否要向文件名添加前缀，您真的需要这个吗？

更正后的版本为:

import os
from multiprocessing.dummy import Pool as ThreadPool

import camelot

BASE_PATH = os.path.dirname((os.path.abspath(__file__)))

FOLDER_PATH = os.path.join(BASE_PATH, "threading_learning")

pdfs = [os.path.join(FOLDER_PATH, file_name) for file_name in os.listdir(FOLDER_PATH)]

listoflengths = []


def len_table5(filepath):
    tables = camelot.read_pdf(filepath, pages='1-end', flavor='stream')
    tablelength = len(tables)
    listoflengths.append(tablelength)


# threading code
pool = ThreadPool(5)
results = pool.map(len_table5, pdfs)
pool.close()
pool.join()

print(listoflengths)