0

这可能只是由于PyPdf2's提取文本功能，但是当我运行下面的代码以重命名文件时，会出现很多最常见的词，例如“Nthe”、“Nfrom”和“Ncommunications”。我不确定我能做些什么来阻止这种情况的发生，或者如何解决它。

是什么导致了这样的问题？

N从哪里来？

其他 PDF 完全符合我的要求，所以我不知道从哪里开始。

import PyPDF2
import re
from collections import Counter
import os.path

files = [f for f in os.listdir('.') if os.path.isfile(f)]
files = filter(lambda f: f.endswith(('.pdf','.PDF')), files)

for file in files:
    pdfFileObj = open('{0}'.format(file), 'rb') #Open the File
    pdfReader = PyPDF2.PdfFileReader(pdfFileObj) #Read the file
    frequency = {} #Create dict
    ignore = {'the','a','if','in','it','of','or','and','for','can','that','are','this','your','you','will','not','have','its','with','need','has','from','more'} #Ignore dese ones

    print "Number of Pages %s " % pdfReader.numPages #Print Num Pages
    word_list = []
    for i in range(pdfReader.numPages): 
        pageObj = pdfReader.getPage(i) # Get the first page
        word_list.append(pageObj.extractText()) #Add the pages together

    match_pattern = re.findall(r'\b[a-z]{3,15}\b', str(word_list)) #Find the text
    cnt = Counter()
    for words in match_pattern: #Start counting the frequency
        words.lower() # Lower Case Words
        if words not in ignore: #Ignore common words
            count = frequency.get(words,0) #Start the count?
            frequency[words] = count + 1 #Add one
    fl = sorted(frequency, key=frequency.__getitem__, reverse = True)[:3] #Sort according to frequency

    pdfFileObj.close() #Close the PDF
    newtitle = ' '.join(map(str,fl, )).title() #Join the title list together

    try:
        print newtitle #Print the title
        os.rename('{0}'.format(file), '{0}.pdf'.format(newtitle))#Rename the file
    except:
        print "Unable to Rename File"
4

0 回答 0