使用Python从文本文件中删除x行段落
我有一个很长的文本文件，里面的段落有6行和7行。我需要把所有7行的段落写到一个文件里，把6行的段落写到另一个文件里。或者也可以选择删除6行（或7行）的段落。每个段落之间用空行（或者两个空行）分隔开。
文本文件的例子：
Firs Name Last Name address1 Address2 Note 1 Note 2 Note3 Note 4 First Name LastName add 1 add 2 Note2 Note3 Note4 etc...
我想在Windows上使用Python 3。任何帮助都很欢迎。谢谢！
1 个回答
0
欢迎来到StackOverflow！我看到你可能已经搜索了很多代码，所以我给你推荐以下这段代码。
这段代码的作用是检查段落的行数，确保每个段落的行数在6到7行之间。如果有段落不符合这个要求，它会发出警告。
你可以把所有的打印输出去掉，这样代码会更干净，但保留它们可以帮助你理解算法的过程。
我认为这段代码没有错误，但也不能保证百分之百没有问题。
这并不是唯一的解决方法，我选择了这种适用于所有类型文件的方式：逐行读取。虽然也可以一次性读取整个文件，然后把它分成行的列表，或者用正则表达式处理，但如果文件非常大，一次性读取会消耗很多内存。
with open('source.txt') as fsource,\
open('SIX.txt','w') as six, open('SEVEN.txt','w') as seven:
buf = []
cnt = 0
exceeding7paragraphs = 0
tinyparagraphs = 0
line = 'go'
while line:
line = fsource.readline()
cnt += 1
buf.append(line)
if len(buf)<6 and line.rstrip('\n\r')=='':
tinyparagraphs += 1
print cnt,repr(line),"this line of paragraph < 6 is void,"+\
"\nthe treatment of all this paragraph is skipped\n"+\
'\n# '+str(cnt)+' '+ repr(line)+" skipped line "
buf = []
while line and line.rstrip('\n\r')=='':
line = fsource.readline()
cnt += 1
if line=='':
print "line",cnt,"is '' , EOF -> the program will be stopped"
elif line.rstrip('\n\r')=='':
print '#',cnt,repr(line)
else:
buf.append(line)
print '!',cnt,repr(line),' put in void buf'
else:
print cnt,repr(line),' put in buf'
if len(buf)==6:
line = fsource.readline() # reading a potential seventh line of a paragraph
cnt += 1
if line.rstrip('\n\r'): # means the content of the seventh line isn't void
buf.append(line)
print cnt,repr(line),'seventh line put in buf'
line = fsource.readline()
cnt += 1
if line.rstrip('\n\r'): # means the content of the eighth line isn't void
exceeding7paragraphs += 1
print cnt,repr(line),"the eight line isn't void,"+\
"\nthe treatment of all this paragraph is skipped"+\
"\neighth line skipped"
buf = []
while line and line.rstrip('\n\r'):
line = fsource.readline()
cnt += 1
if line=='':
print "line",cnt,"is '' , EOF -> the program will be stopped"
elif line.rstrip('\n\r')=='':
print '\n#',cnt,repr(line)
else:
print str(cnt) + ' ' + repr(line)+' skipped line'
else:
if line=='':
print cnt,"line is '' , EOF -> the program will be stopped\n"
else: # line.rstrip('\n\r') is ''
print cnt,'eighth line is void',repr(line)
seven.write(''.join(buf) + '\n')
print buf,'\n',len(buf),'lines recorded in file SEVEN\n'
buf = []
else:
print cnt,repr(line),'seventh line: void'
six.write(''.join(buf) + '\n')
print buf,'\n',len(buf),'lines recorded in file SIX'
buf = []
if line=='':
print "line",cnt,"is '' , EOF -> the program will be stopped"
else:
print '\nthe line is',cnt, repr(line)
while line and line.rstrip('\n\r')=='':
line = fsource.readline()
cnt += 1
if line=='':
print "line",cnt,"is '' , EOF -> the program will be stopped"
elif line.rstrip('\n\r')=='':
print '#',cnt,repr(line)
else: # line.rstrip('\n\r') != ''
buf.append(line)
print '!',cnt,repr(line),' put in void buf'
if exceeding7paragraphs>0:
print '\nWARNING :'+\
'\nThere are '+str(exceeding7paragraphs)+' paragraphs whose number of lines exceeds 7.'
if tinyparagraphs>0:
print '\nWARNING :'+\
'\nThere are '+str(tinyparagraphs)+' paragraphs whose number of lines is less than 6.'
print '\n===================================================================='
print 'File SIX\n'
with open('SIX.txt') as six:
print six.read()
print '===================================================================='
print 'File SEVEN\n'
with open('SEVEN.txt') as seven:
print seven.read()
我也给你的问题点了赞，因为这个问题并不像看起来那么简单，另外我不想让你只有一条帖子和一个差评，这对初学者来说会很打击。下次尽量让你的提问更清晰，正如其他人所说的。
.
编辑：
这里有一段简化的代码，适用于只包含6或7行段落的文本，段落之间正好隔着1或2行，正如问题描述中所说的那样。
with open('source2.txt') as fsource,\
open('SIX.txt','w') as six, open('SEVEN.txt','w') as seven:
buf = []
line = fsource.readline()
while not line: # to go to the first non empty line
line = fsource.readline()
while True:
buf.append(line) # this line is the first of a paragraph
print '\n- first line of a paragraph',repr(line)
for i in xrange(5):
buf.append(fsource.readline())
# at this point , 6 lines of a paragraph have been read
print '-- buf 6 : ',buf
line = fsource.readline()
print '--- line seventh',repr(line),id(line)
if line.rstrip('\r\n'):
buf.append(line)
seven.write(''.join(buf) + '\n')
buf = []
line = fsource.readline()
else:
six.write(''.join(buf) + '\n')
buf = []
# at this point, line is the empty line after a paragraph or EOF
print '---- line after',repr(line),id(line)
line = fsource.readline()
print '----- second line after',repr(line)
# at this point, line is an empty line after a paragraph or EOF
# or the first line of a new paragraph
if not line: # it is EOF
break
if not line.rstrip('\r\n'): # it is a second empty line
line = fsource.readline()
# now line is the first of a new paragraph
print '\n===================================================================='
print 'File SIX\n'
with open('SIX.txt') as six:
print six.read()
print '===================================================================='
print 'File SEVEN\n'
with open('SEVEN.txt') as seven:
print seven.read()