# -*- coding:utf-8 -*-

 import re

 '''

 适应新版本

 '''

 year='17A'#用户自定义

 ss='./data/'#根目录

 filename = ss+'EDCD%s.txt'%year#输入文件名

 def trcd_nonote():

     p1 = r"^\s{4}(?:X|\W)\s{2}(C\d\d\d)\s.+\n"

     p2 = r"^\s{4}(?:X|\W)\s{2}C\d\d\d\s(.+)\n"

     p3 = r"^\s{7}Desc:\s(.+\.)\n"

     p4 = r"^\s{7}Desc:\s(.+[^\.])\n"

     p5 = r"^\s{13}(.+[^\.])\n"

     p6 = r"^\s{13}(.+\.)\n"

     pattern1 = re.compile(p1)

     pattern2 = re.compile(p2)

     pattern3 = re.compile(p3)

     pattern4 = re.compile(p4)

     pattern5 = re.compile(p5)

     pattern6 = re.compile(p6)

     fr = open(filename)

     temp = ();

     flag = 0

     for line in fr.readlines():

         matcher1 = re.findall(pattern1,line)

         matcher2 = re.findall(pattern2,line)

         matcher3 = re.findall(pattern3,line)

         matcher4 = re.findall(pattern4,line)

         matcher5 = re.findall(pattern5,line)

         matcher6 = re.findall(pattern6,line)

         #print matcher

         w2 = open(ss+'trcd_nonote%s.txt'%year,'a')#a代表追加 w代表重写

         if matcher1:

             flag = 1

             w2.write("\n")

             for j in matcher1:

                 for k in j:

                     w2.write(k)

                 #for k in g:

                     #w2.write(k)

             #continue;

         if ((matcher2!=[])and(flag ==1)):

             flag = 2

             #print type(tup1)

             #print tup1

             #flag = 2

             w2.write(",")

             for j in matcher2:

                 for k in j:

                     w2.write(k)

         if ((matcher3!=[])and(flag ==2)):

             flag = 3

             w2.write(",\"")

             for j in matcher3:

                 for k in j:

                     w2.write(k)

             w2.write("\"")

         if (matcher4!=[]):

             w2.write(",\"")

             for j in matcher4:

                 for k in j:

                     w2.write(k)

             flag = 4

         if ((matcher5!=[])and(flag ==4)):

             flag = 5

             w2.write(" ")

             for j in matcher5:

                 for k in j:

                     w2.write(k)

         if ((matcher6!=[])and(flag ==4 or 5)):

             flag = 6

             w2.write(" ")

             for j in matcher6:

                 for k in j:

                     w2.write(k)

             w2.write("\"")

     w2.close( )

 def trcd_note():

     p1 = r"^(?:\s{7}|X\s{6}|\W\s{6})([A-Z][0-9]{3})\s[A-Z].+$"#匹配1001

     p2 = r"^\s{7}Note:\s\n"#Note

     p3= r"^\s{13}([^ ].+)\n"#Note内容

     p4= r"^(?:-|컴)+\n"

     pattern1 = re.compile(p1)

     pattern2 = re.compile(p2)

     pattern3 = re.compile(p3)

     pattern4 = re.compile(p4)

     fr = open(filename)

     w2 = open(ss+'trcd_note%s.txt'%year,'a')#a代表追加 w代表重写

     # temp = ();

     flag = 0

     flag1=0

     for line in fr.readlines():

         matcher1 = re.findall(pattern1,line)

         matcher2 = re.findall(pattern2,line)

         matcher3 = re.findall(pattern3,line)

         matcher4 = re.findall(pattern4,line)

         #print matcher

         if matcher1!=[]:

             flag = 1

             w2.write("\n")

             # for j in matcher1:

             #     w2.write(j)

         if ((matcher2!=[])and(flag == 1)):

             flag = 2

             flag1=1

             # w2.write(",")

         if flag1==1:

             if ((matcher3!=[])and(flag ==2 or 3)):

                 flag = 3

                 w2.write(" ")

                 for j in matcher3:

                     w2.write(j)

             # w2.write(")

             if ((matcher4!=[])and(flag == 3)):

                 flag=0

                 flag1=0

     w2.write("\n")

     w2.close( )

     fr.close()

 def join():

     f1= open(ss+'trcd_note%s.txt'%year)

     f2 =open(ss+'trcd_nonote%s.txt'%year) 

     list_note=[]

     for line1 in f1:

         # print(line1)

         if line1.isspace():

             list_note.append('')

         else:

             list_note.append(line1)

     f1.close()

     # print(list_note)

     f2_w= open(ss+'trcd%s.csv'%year,'a')

     # for i in range(len(list_note)):

     i=0

         # f2_r = open(ss+'/new/%s_w.txt'%list_tag[i])

     for line2 in f2:

         str11="%s,\"%s\"\n"%(line2.strip('\n'),list_note[i].strip('\n'))

         i=i+1

         # print(i)

         # print(str11)

         f2_w.write(str11)

     f2_w.close()

     f2.close()

 if __name__ == '__main__':

     trcd_nonote()

     trcd_note()

     join()

trcd_extract_EDCD_new的更多相关文章

随机推荐

  1. PYTHON-进阶-装饰器小结，转载

    本文转载自:http://www.wklken.me/posts/2012/10/27/python-base-decorator.html 基本概念 具体概念自己google 装饰器是一个很著名的设 ...

  2. Mybatis知识(5)

    1. #{} 与${}的区别 #{}解释为 JDBC prepared statement 的一个参数标记,而${}解释为字符串替换.比如:我们不能在表名的位置使用参数标记,也不能在列名的位置使用参数 ...

  3. c:forEach varStatus属性

    转自:https://blog.csdn.net/jzy23682891/article/details/7075904 c:forEach varStatus属性 current当前这次迭代的(集合 ...

  4. Python使用Threading模块创建线程

    使用Threading模块创建线程,直接从threading.Thread继承,然后重写__init__方法和run方法: #!/usr/bin/python # -*- coding: UTF-8 ...

  5. python处理分隔大文件

    4个.sql格式的文件,2G大小,直接插入mysql数据中,文件太大了,导入不进去. 太大的文件用python处理也很麻烦,处理不了,只能先分隔成小文件处理. 文件中数据格式:其中values里面的数 ...

  6. Python3 ssl模块不可用的问题

    编译安装完Python3之后,使用pip来安装python库,发现了如下报错: $ pip install numpy pip is configured with locations that re ...

  7. docker registry2

    https://blog.csdn.net/mideagroup/article/details/52052618

  8. IRanges package

    1)介绍 在分析序列时,我们通常对特定的连续子序列感兴趣. 例如,a矢量可以被认为是按字母顺序排列的小写字母序列. 我们将第一个五个字母(a到e)称为连续的子序列,而仅包含元音的子序列不会是连续的. ...

  9. SpringBoot application.yml logback.xml 多环境

    启动命令为 //开发环境 java -jar app.jar --spring.profiles.active=dev--server.port=8060 //测试环境 java -jar app.j ...

  10. C# split分割多个字符

    string[] myAgent = agentInfo.Split(new string[] { "$#$" }, StringSplitOptions.None);