python3用PyPDF2解析pdf文件,用正则匹配数据方式

 import PyPDF2
 import re
 
 pdf_file = open('xxx.pdf', mode='rb')
 read_pdf = PyPDF2.PdfFileReader(pdf_file)
 # 获取pdf文件的所有页数
 number_of_pages = read_pdf.getNumPages()
 # print('total_page: ', number_of_pages)
 line_list = []
 # 循环遍历每一页
 for i in range(0, number_of_pages):
  # 读取每一页的内容
  page = read_pdf.getPage(i)
  page_content = page.extractText()
  # 将这一页的内容分割为列表，，并相加所有的页面内容
  line_list += page_content.split()
 # 关闭pdf文件
 pdf_file.close()
 line_buf = ''
 for buf in line_list:
  line_buf = line_buf+' '+buf
 # 匹配数据：第一列和第二列 如：000069.sz 和 100
 # print(line_buf)
 a = re.findall('([0-9]+[0-9]+[0-9]+[0-9]+[0-9]+[0-9]+.[a-z]+[a-z])', line_buf)
 b = re.findall('[0-9]+[0-9]+[0-9]+[0-9]+[0-9]+[0-9]+.[a-z]+[a-z].([0-9,]+)', line_buf)
 # print(b)
 for i in range(0, len(a)):
  a[i] = a[i].upper()
 for i in range(0, len(b)):
  b[i] = int(b[i].replace(',', ''))
 # print(b)
 # 组成字典
 results = dict(zip(a, b))

fp = open(filename,"w")
fp.write(re.search('(StockDescription:)([a-zA-Z]+-[a-zA-Z]+)',line_buf).group(2) +',')
fp.write(time.strftime('%Y%m%d',time.strptime(re.search('(TradeDate:)([0-9]+[a-zA-Z]+[0-9]+)',line_buf).group(2),'%d%B%Y')) +',')
fp.write(re.search('(Price:[A-Z]+)([0-9.,]+)',line_buf).group(2).replace(',','')+',')
fp.close()