关于python处理文本的一个有关问题

关于python处理文本的一个问题
比如我现在有一个文本

1|2|3|4|5
11|22|33|44|55
1|3|4|5|6|3
这样的行

我要找出一列里相同的行并去重。

这个咋处理呢


[解决办法]

Python code

#-*- coding: utf-8 -*-import rea = '1|2|3|4|5'b = '11|22|33|44|55'c = '1|3|4|5|6|3'ls = [a, b, c]NUM_PATTERN = r'^(\d+)(.*)'dict = {}def getLines(dict):    p = re.compile(NUM_PATTERN)    for _l in ls:        value = p.findall(_l)        k = value[0][0]        v = value[0][1]        dict[k] = vif __name__ == '__main__':    getLines(dict)    print dict
[解决办法]
Python code
#!/usr/bin/env pythonimport redef getLines(filename):    ldict = {}    pat = re.compile('^(\d+)')    with open(filename) as fd:        for line in fd:            mat = pat.match(line)            if mat:                n = mat.group(1)                if n in ldict:                    continue                else:                    ldict[n] = 1                    print line,        fd.close()if __name__ == '__main__':    getLines('a.txt')
[解决办法]
[code=Python][/code]

#! /usr/bin/env python
# -*- coding: cp936 -*-

'''这种结果是否正确'''

def noreplines(src):
   lines = src.split('\n')
   lnos = [lno for lno in (line.split('|') for line in lines)]
   lefts = set(ln for ln in range(len(lines)))
   for i in range(len(lnos[0])):
       edict = {}
       for j in range(len(lnos)):
           if lnos[j][i] not in edict:
               edict[lnos[j][i]] = j
       lefts &= set(edict[key] for key in edict)
   for ln in lefts:
       print lines[ln]

def main():
   src = '''1|2|3|4
1|2|4|5
2|4|5|5
3|4|6|6
4|5|7|7
5|6|7|8'''
   noreplines(src)

if __name__ == '__main__':
   main()
          
  
      

[解决办法]
Python code
#! /usr/bin/env python# -*- coding: cp936 -*-'''这种结果是否正确'''def noreplines(src):    lines = src.split('\n')    lnos = [lno for lno in (line.split('|') for line in lines)]    lefts = set(ln for ln in range(len(lines)))    for i in range(len(lnos[0])):        edict = {}        for j in range(len(lnos)):            if lnos[j][i] not in edict:                edict[lnos[j][i]] = j        lefts &= set(edict[key] for key in edict)    for ln in lefts:        print lines[ln]def main():    src = '''1|2|3|41|2|4|52|4|5|53|4|6|64|5|7|75|6|7|8'''    noreplines(src)if __name__ == '__main__':    main()
[解决办法]
$cat test.txt
1|2|3|4
1|2|4|5
2|4|5|5
3|4|6|6
4|5|7|7
5|6|7|8
1|2|3|4|5
11|22|33|44|55
1|3|4|5|6|3
Python code
#!/usr/bin/python# encoding: utf-8class Parser:    def __init__(self, spliter):        self.spliter = spliter        self.cached = set()    def __call__(self, stream):        for ln in stream:            k, v = ln.split(self.spliter, 1)            if k in self.cached:                continue            else:                self.cached.add(k)                yield lnparser = Parser('|')for ln in parser(open('test.txt')):    print ln
[解决办法]
Python code
f = open('test.txt', 'r');dls = {};for l in reversed(f.readlines()):   dls[l.split('|')[0]] = [len(dls), l];f.close();for k in sorted(dls, key=lambda x: dls[x][0], reverse=True):   print(dls[k][1]);