Python处理大文件解压与读取：解决编码错误及性能优化

def unzip_to_txt_plus(zipfilename):
  zfile = zipfile.ZipFile(zipfilename, 'r')
  for filename in zfile.namelist():
    data = zfile.read(filename)
    # data = data.decode('gbk').encode('utf-8')
    data = data.decode('gbk', 'ignore').encode('utf-8')
    file = open(filename, 'w+b')
    file.write(data)
    file.close()


if __name__ == '__main__':
  zipfilename = "E:\\share\\python_excel\\zip_to_database\\20171025.zip"
  unzip_to_txt_plus(zipfilename)

# - coding: utf-8 -
import csv
import linecache
import xlrd
import MySQLdb


def txt_todatabase(filename, linenum):
   # with open(filename, "r", encoding="gbk") as csvfile:
   #   Read = csv.reader(csvfile)
   #   count =0
   #   for i in Read:
   #   #   print(i)
   #      count += 1
   #      # print('hello')
   #   print(count)
   count = linecache.getline(filename, linenum)
   print(count)
   # with open("new20171028.csv", "w", newline="") as datacsv:
   #   # dialect为打开csv文件的方式，默认是excel，delimiter="\t"参数指写入的时候的分隔符
   #   csvwriter = csv.writer(datacsv, dialect=("excel"))
   #   # csv文件插入一行数据，把下面列表中的每一项放入一个单元格（可以用循环插入多行）
   #   csvwriter.writerow(["A", "B", "C", "D"])


def bigtxt_read(filename):
  with open(filename, 'r', encoding='utf-8') as data:
    count =0
    while 1:
      count += 1
      line = data.readline()
      if 1000000 == count:
        print(line)
      if not line:
        break
    print(count)


if __name__ == '__main__':
  filename = '20171025.txt'
  txt_todatabase(filename, 1000000)
  bigtxt_read(filename)