Question

我有一个PDF日期，其中包含以下日期页面。我需要使用python单独使用以下08/30/1941页面。寻找逻辑？

{'05/20/2016': [1, 1, 1, 1, 2, 2, 3, 3, 3, 3, 4, 4, 4, 5, 5, 5, 5, 6, 6],
 '06/20/2016': [4],
 '08/30/1941': [1, 5]}

Answer 1

因此，您需要做的是使用PyPDF2或PDFMiner从PDF中提取文本

<强> PDFMiner

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 convert_pdf_to_txt(path):
  rsrcmgr = PDFResourceManager()
  retstr = StringIO()
  codec = 'utf-8'
  laparams = LAParams()
  device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
  fp = open(path, 'rb')
  interpreter = PDFPageInterpreter(rsrcmgr, device)
  password = ""
  maxpages = 0
  caching = True
  pagenos=set()

  for pageNumber, pages in enumerate(PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True)):
    interpreter.process_page(pages)

#for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
    #interpreter.process_page(0)

 text = retstr.getvalue()

 fp.close()
 device.close()
 retstr.close()
 words = text.split('\n')
 return words

使用上述功能提取文字

a_list = convert_pdf_to_txt(path)

这将返回一个列表，您基本上可以浏览列表中的元素

导入重新

try:
   for index, values in enumerate(a_list):
     date_to_find = re.compile(r"08/30/1941")
     Date_to_find = filter(date_to_find.match, values))
     if Date_to_find == []:
        print("The Date is not available")
     else:
        found = a_list[index]
        Date_to_find = re.match(r"(08/30/1941:)(.*\Z)")
        Date_Found = Date_to_find.group(2)
  print(Date_Found)
except:
   print("There was some error")

逻辑到使用python拍摄奇数日期

1 个答案: