python Method for Segmenting One Text into Multiple Text
- 2021-07-24 11:11:38
- OfStack
In this paper, we share the example of python dividing one text into multiple texts for your reference. The specific contents are as follows
# load file
# for each row
## if match
## output
def main():
file_source = './reading_questions.txt'
#target_dir = ''
file_in = open(file_source,'r')
template_str = 'TARGET'
outfilename = './head.txt'
output_content = ''
while 1:
line = file_in.readline()
if not line:
break
if line.find(template_str) != -1:
write_file(outfilename,output_content)
outfilename = './'+line+'.txt' # output file tile
output_content = ''
else:
output_content += line # append
write_file(outfilename,output_content) #for the last file
# close file stream
file_in.close()
def write_file(filename, filecontent):
file_out = open(filename,'w') # create file
file_out.write(filename)
file_out.write(filecontent)
file_out.close()
main()
Error reported under cygwin+python3: UnicodeDecodeError: 'gb2312' codec can 't decode byte 0xac in position 25: illegal multibyte sequence
Modify open file parameters
file_in = open(file_source,'r',encoding='UTF-8')
Amend to read as follows
# load file
# for each row
## if match
## output
def main():
print ('hhh')
file_source = 'listening_questions.txt'
#target_dir = ''
file_in = open(file_source,'r',encoding='UTF-8')
template_str = 'ZTPO'
outfilename = 'head' #first file before match target
output_content = ''
while 1:
line = file_in.readline()
if not line:
break
if line.find(template_str) != -1:
write_file(outfilename,output_content)
outfilename = line.strip('\n')
output_content = '' # clear content of output file
else:
output_content += line # append content
write_file(outfilename,output_content) #for the last file
# close file stream
file_in.close()
def write_file(filename, filecontent):
outfilename = './'+filename+'.txt' # output file tile
file_out = open(outfilename,'w',encoding='UTF-8') # create file
file_out.write(filename)
file_out.write(filecontent)
file_out.close()
main()