Python文本处理之按行处理大文件的方法

  >>> for line in open('chap1.txt'): # Python 2.2+
  ...  # process each line in some manner
  ...  pass
  ...
  >>> linelist = open('chap1.txt').readlines()
  >>> print linelist[1849],
  EXERCISE: Working with lines from a large file
  >>> txt = open('chap1.txt').read()
  >>> from os import linesep
  >>> linelist2 = txt.split(linesep)

  >>> import linecache
  >>> print linecache.getline('chap1.txt',1850),
  PROBLEM: Working with lines from a large file

#------------------ cachedlinelist.py --------------------#
  import linecache, types
  class CachedLineList:
   # Note: in Python 2.2+, it is probably worth including:
   # __slots__ = ('_fname')
   # ...and inheriting from 'object'
   def __init__(self, fname):
    self._fname = fname
   def __getitem__(self, x):
    if type(x) is types.SliceType:
     return [linecache.getline(self._fname, n+1)
       for n in range(x.start, x.stop, x.step)]
    else:
     return linecache.getline(self._fname, x+1)
   def __getslice__(self, beg, end):
    # pass to __getitem__ which does extended slices also
    return self[beg:end:1]

  >>> from cachedlinelist import CachedLineList
  >>> cll = CachedLineList('../chap1.txt')
  >>> cll[1849]
  ' PROBLEM: Working with lines from a large file\r\n'
  >>> for line in cll[1849:1851]: print line,
  ...
  PROBLEM: Working with lines from a large file
  ----------------------------------------------------------
  >>> for line in cll[1853:1857:2]: print line,
  ...
  a matter of using the '.readline()', '.readlines()' and
  simplified syntax for this frequent operation by letting the

 #-------------------- randline.py ------------------------#
  #!/usr/bin/python
  """Iterate over random lines in a file (req Python 2.2+)
  From command-line use: % randline.py <fname> <numlines>
  """
  import sys
  from os import stat, linesep
  from stat import ST_SIZE
  from random import randrange
  MAX_LINE_LEN = 4096
  #-- Iterable class
  class randline(object):
   __slots__ = ('_fp','_size','_limit')
   def __init__(self, fname, limit=sys.maxint):
    self._size = stat(fname)[ST_SIZE]
    self._fp = open(fname,'rb')
    self._limit = limit
   def __iter__(self):
    return self
   def next(self):
    if self._limit <= 0:
     raise StopIteration
    self._limit -= 1
    pos = randrange(self._size)
    priorlen = min(pos, MAX_LINE_LEN) # maybe near start
    self._fp.seek(pos-priorlen)
    # Add extra linesep at beg/end in case pos at beg/end
    prior = linesep + self._fp.read(priorlen)
    post = self._fp.read(MAX_LINE_LEN) + linesep
    begln = prior.rfind(linesep) + len(linesep)
    endln = post.find(linesep)
    return prior[begln:]+post[:endln]
  #-- Use as command-line tool
  if __name__=='__main__':
   fname, numlines = sys.argv[1], int(sys.argv[2])
   for line in randline(fname, numlines):
    print line