自然语言处理python进阶（二）

python字符串的简单使用

namesList = ['Tuffy','Ali','Nysha','Tim' ]
sentence = 'My dog sleeps on sofa'

names = ';'.join(namesList)
print(type(names), ':', names)
wordList = sentence.split(' ')
print((type(wordList)), ':', wordList)
additionExample = 'ganehsa' + 'ganesha' + 'ganesha'
multiplicationExample = 'ganesha' * 2
print('Text Additions :', additionExample)
print('Text Multiplication :', multiplicationExample)
str = 'Python NLTK'
print(str[1])
print(str[-3])

使用python读取pdf

from PyPDF2 import PdfFileReader

def getTextPDF(pdfFileName, password = ''):
    # 打开
    pdf_file = open(pdfFileName, 'rb')
    # 读取
    read_pdf = PdfFileReader(pdf_file)
    if password != '':
        read_pdf.decrypt(password)
    text = []
    for i in range(0,read_pdf.getNumPages()):
        # 转化为文本
        text.append(read_pdf.getPage(i).extractText())
    return '\n'.join(text)
pdfFile = 'sample-one-line.pdf'
pdfFi