如何通过 python re 或其他方式按特定规则开始和结束段落？
How to split paragraphs by specific starts and ends with specific rules by python re or something?
如何通过特定的开始和结束来分割段落？使用 python re 什么的？
Original_texts_with_paragraphs= """
0 zzzzz zzzz zzzzzzzz zzz GG G GGG
1 zzz AA zzz AAA zzzz zzz zzz zzzz zzzz zzzz zzz
2 zzzzz AA zzz zzz AAA zzzz zzzzz zzzzz zzzzz zzzz
3 zzz zzzz zzz zzz zzzz zzzz zzz zzzz EE zzz EEE
4 zzz zzzz zzz zzz zzz zzzz zzz zzzz zzz zzzz zzz zzz
5 zz zzz zzz zzz zzz zzz zz zzz zzzzzz zzzz zzzz zzz
6 BBBB BB zzzz BBB zz B zzzzzz zzzz zzzz zzzz zzzz zz
7 zzz zzz zzzz zzzz zzz zzzzz zzzz zzzzz zzzzz FF FFF zzz
8 CCCC zzz CCC zzzz zz zzzz zzzz zzz zzz GG G GGG
9 zzz AA zz AAA zzzz zzz zzz zzz FF zz FFF
10 AA zzzz AAA zzzz zzzz zzzz zzzzz zzzzz
11 zz CCCC zzz CCC zzzz zzzz zzzz zzzz zzzz zz
12 zzzz zzz zzzzz zzzzz zzzzz zzzzz zzzz zzzz EE zz EEE
13 zz zzz zzzz zzz zzz zzz
14 zzz AA AAA zzz zzz zzzz zzzz GG zz GGG
15 BBBB BB BBB zz B zzzz zz GG zz G GGG
16 zzz zzzz
17 zzzz zzz zzz zzz
18 zz AA zzz AAA zzzz zzzz zzzz zzz
19 zzzz zzz zzz zzz zzzz zzzz zzzz GG G GGG
20 zzzz zzzzz zzzzzzzz zzz
21 zzzzz zzzz zzzzzzzz zzz GG G GGG
22 zzzzzz zzz zz zzzz
23 zzzzz AA zzz zzz AAA zzzz zzzzz zzzzz zzzzz zzzz
24 zzz zzzz zzz zzz zzzz zzzz zzz zzzz EE zzz EEE
"""
开始：
Starts_with = """
AA AAA
BBBB BB BBB B
CCCC CCC
"""
结束：
Ends_with = """
EE EEE
FF FFF
GG G GGG
"""
期望输出：
desired_output = """
1 zzz AA zzz AAA zzzz zzz zzz zzzz zzzz zzzz zzz
2 zzzzz AA zzz zzz AAA zzzz zzzzz zzzzz zzzzz zzzz
3 zzz zzzz zzz zzz zzzz zzzz zzz zzzz EE zzz EEE
6 BBBB BB zzzz BBB zz B zzzzzz zzzz zzzz zzzz zzzz zz
7 zzz zzz zzzz zzzz zzz zzzzz zzzz zzzzz zzzzz FF FFF zzz
8 CCCC zzz CCC zzzz zz zzzz zzzz zzz zzz GG G GGG
9 zzz AA zz AAA zzzz zzz zzz zzz FF zz FFF
10 AA zzzz AAA zzzz zzzz zzzz zzzzz zzzzz
11 zz CCCC zzz CCC zzzz zzzz zzzz zzzz zzzz zz
12 zzzz zzz zzzzz zzzzz zzzzz zzzzz zzzz zzzz EE zz EEE
14 zzz AA AAA zzz zzz zzzz zzzz GG zz GGG
15 BBBB BB BBB zz B zzzz zz GG zz G GGG
18 zz AA zzz AAA zzzz zzzz zzzz zzz
19 zzzz zzz zzz zzz zzzz zzzz zzzz GG G GGG
23 zzzzz AA zzz zzz AAA zzzz zzzzz zzzzz zzzzz zzzz
24 zzz zzzz zzz zzz zzzz zzzz zzz zzzz EE zzz EEE
"""
怎么做？
我试过这段代码，但效果不佳
import re
original = 'Original.txt'
new = 'Padded.txt'
Starts = (
r'.*AA.*AAA.*',
r'.*BBBB.*BB.*BBB.*B.*',
r'.*CCCC.*CCC.*',
)
Ends = (
r'.*EE.*EEE',
r'.*FF.*FFF',
r'.*GG.*G.*GGG'
)
desired_output = []
with open( original, 'r' ) as f:
output = open( new, 'a+' )
start = False
for line in f:
end = False
for pattern in Starts:
start_chars = line[:30]
if re .search( pattern, start_chars ) != None:
start = True
for pattern in Ends:
end_chars = line[-20:]
if re .search( pattern, end_chars ) != None:
start = False
end = True
if end:
output .write( line +'\n\n' )
desired_output .append(line +'\n\n')
elif start:
output .write( line )
desired_output .append(line)
print(desired_output)
我试了很多，但我还是把段落拆分搞糊涂了。我的主要目的是按特定的开头和结尾拆分段落。我有开始和结束的列表。
I also need to store rest of lines into other list. for use it
later.
请帮帮我？
它遵循与 answered moments ago. https://docs.python.org/3/library/re.html
非常相似的逻辑
#! /usr/bin/env python3
import re
original = 'Original.txt'
new = 'Padded.txt'
Starts = (
r'AA .+',
r'BBBB BB.+BBB.+B',
r'CCCC .+ CCC',
)
Ends = (
r'EE .+ EEE',
r'FF.+FFF',
r'.+ GGG'
)
with open( original, 'r' ) as f:
output = open( new, 'a+' )
start = False
for line in f:
end = False
for pattern in Starts:
start_chars = line[:25]
if re .search( pattern, start_chars ) != None:
start = True
for pattern in Ends:
end_chars = line[-15:]
if re .search( pattern, end_chars ) != None:
start = False
end = True
if end: output .write( line +'\n' )
elif start: output .write( line )
1 zzz AA zzz AAA zzzz zzz zzz zzzz zzzz zzzz zzz
2 zzzzz AA zzz zzz AAA zzzz zzzzz zzzzz zzzzz zzzz
3 zzz zzzz zzz zzz zzzz zzzz zzz zzzz EE zzz EEE
6 BBBB BB zzzz BBB zz B zzzzzz zzzz zzzz zzzz zzzz zz
7 zzz zzz zzzz zzzz zzz zzzzz zzzz zzzzz zzzzz FF FFF zzz
8 CCCC zzz CCC zzzz zz zzzz zzzz zzz zzz GG G GGG
9 zzz AA zz AAA zzzz zzz zzz zzz FF zz FFF
10 AA zzzz AAA zzzz zzzz zzzz zzzzz zzzzz
11 zz CCCC zzz CCC zzzz zzzz zzzz zzzz zzzz zz
12 zzzz zzz zzzzz zzzzz zzzzz zzzzz zzzz zzzz EE zz EEE
13 zz AA zzz
14 AAA zzz zzz zzzz zzzz GG zz GGG
15 BBBB BB BBB zz B GG zz G
16 zzz GGG
谢谢@Doyousketch2。
我编辑了你的代码然后它工作得更好。
try:
file = open("Padded1.txt","r+")
file.truncate(0)
file.close()
except:
pass
import re
original = 'Original1.txt'
new = 'Padded1.txt'
result = []
with open( original, 'r' ) as f:
output = open( new, 'a+' )
start = False
for line in f:
end = False
for pattern in Starts:
start_chars = line[:30]
if re .search( pattern, start_chars ) != None:
start = True
for pattern in Ends:
end_chars = line[-20:]
if re .search( pattern, end_chars ) != None:
#####start = False
end = True
if end and start:
output .write( line +'\n\n\n' )
result.append(line +'\n\n\n')
start = False
end = False
elif start:
output .write( line )
result.append(line)
end = False
output.close()
if start == True and end == False:
#remove last line from a text line in python
fd=open("Padded1.txt","r")
d=fd.read()
fd.close()
sep = "\n\n\n\n"
s=sep.join(d.split(sep)[:-1])
fd=open("Padded1.txt","w+")
for i in range(len(s)):
fd.write(s[i])
fd.close()
elif start == False and end == True:
#remove last line from a text line in python
fd=open("Padded1.txt","r")
d=fd.read()
fd.close()
sep = "\n\n\n\n"
s=sep.join(d.split(sep)[:-1])
fd=open("Padded1.txt","w+")
for i in range(len(s)):
fd.write(s[i])
fd.close()
# Comparing Two Text Files, Removing the duplicate lines, and Writing results to a new text file
small_file = open('Original1.txt','r')
long_file = open('Padded1.txt','r')
output_file = open('output_file.txt','w')
try:
small_lines = small_file.readlines()
small_lines_cleaned = [line.rstrip().lower() for line in small_lines]
long_file_lines = long_file.readlines()
long_lines_cleaned = [line.rstrip().lower() for line in long_file_lines]
for line in small_lines_cleaned:
if line not in long_lines_cleaned:
output_file.writelines(line + '\n')
finally:
small_file.close()
long_file.close()
output_file.close()
print('Done')
如何通过特定的开始和结束来分割段落？使用 python re 什么的？
Original_texts_with_paragraphs= """
0 zzzzz zzzz zzzzzzzz zzz GG G GGG
1 zzz AA zzz AAA zzzz zzz zzz zzzz zzzz zzzz zzz
2 zzzzz AA zzz zzz AAA zzzz zzzzz zzzzz zzzzz zzzz
3 zzz zzzz zzz zzz zzzz zzzz zzz zzzz EE zzz EEE
4 zzz zzzz zzz zzz zzz zzzz zzz zzzz zzz zzzz zzz zzz
5 zz zzz zzz zzz zzz zzz zz zzz zzzzzz zzzz zzzz zzz
6 BBBB BB zzzz BBB zz B zzzzzz zzzz zzzz zzzz zzzz zz
7 zzz zzz zzzz zzzz zzz zzzzz zzzz zzzzz zzzzz FF FFF zzz
8 CCCC zzz CCC zzzz zz zzzz zzzz zzz zzz GG G GGG
9 zzz AA zz AAA zzzz zzz zzz zzz FF zz FFF
10 AA zzzz AAA zzzz zzzz zzzz zzzzz zzzzz
11 zz CCCC zzz CCC zzzz zzzz zzzz zzzz zzzz zz
12 zzzz zzz zzzzz zzzzz zzzzz zzzzz zzzz zzzz EE zz EEE
13 zz zzz zzzz zzz zzz zzz
14 zzz AA AAA zzz zzz zzzz zzzz GG zz GGG
15 BBBB BB BBB zz B zzzz zz GG zz G GGG
16 zzz zzzz
17 zzzz zzz zzz zzz
18 zz AA zzz AAA zzzz zzzz zzzz zzz
19 zzzz zzz zzz zzz zzzz zzzz zzzz GG G GGG
20 zzzz zzzzz zzzzzzzz zzz
21 zzzzz zzzz zzzzzzzz zzz GG G GGG
22 zzzzzz zzz zz zzzz
23 zzzzz AA zzz zzz AAA zzzz zzzzz zzzzz zzzzz zzzz
24 zzz zzzz zzz zzz zzzz zzzz zzz zzzz EE zzz EEE
"""
开始：
Starts_with = """
AA AAA
BBBB BB BBB B
CCCC CCC
"""
结束：
Ends_with = """
EE EEE
FF FFF
GG G GGG
"""
期望输出：
desired_output = """
1 zzz AA zzz AAA zzzz zzz zzz zzzz zzzz zzzz zzz
2 zzzzz AA zzz zzz AAA zzzz zzzzz zzzzz zzzzz zzzz
3 zzz zzzz zzz zzz zzzz zzzz zzz zzzz EE zzz EEE
6 BBBB BB zzzz BBB zz B zzzzzz zzzz zzzz zzzz zzzz zz
7 zzz zzz zzzz zzzz zzz zzzzz zzzz zzzzz zzzzz FF FFF zzz
8 CCCC zzz CCC zzzz zz zzzz zzzz zzz zzz GG G GGG
9 zzz AA zz AAA zzzz zzz zzz zzz FF zz FFF
10 AA zzzz AAA zzzz zzzz zzzz zzzzz zzzzz
11 zz CCCC zzz CCC zzzz zzzz zzzz zzzz zzzz zz
12 zzzz zzz zzzzz zzzzz zzzzz zzzzz zzzz zzzz EE zz EEE
14 zzz AA AAA zzz zzz zzzz zzzz GG zz GGG
15 BBBB BB BBB zz B zzzz zz GG zz G GGG
18 zz AA zzz AAA zzzz zzzz zzzz zzz
19 zzzz zzz zzz zzz zzzz zzzz zzzz GG G GGG
23 zzzzz AA zzz zzz AAA zzzz zzzzz zzzzz zzzzz zzzz
24 zzz zzzz zzz zzz zzzz zzzz zzz zzzz EE zzz EEE
"""
怎么做？
我试过这段代码，但效果不佳
import re
original = 'Original.txt'
new = 'Padded.txt'
Starts = (
r'.*AA.*AAA.*',
r'.*BBBB.*BB.*BBB.*B.*',
r'.*CCCC.*CCC.*',
)
Ends = (
r'.*EE.*EEE',
r'.*FF.*FFF',
r'.*GG.*G.*GGG'
)
desired_output = []
with open( original, 'r' ) as f:
output = open( new, 'a+' )
start = False
for line in f:
end = False
for pattern in Starts:
start_chars = line[:30]
if re .search( pattern, start_chars ) != None:
start = True
for pattern in Ends:
end_chars = line[-20:]
if re .search( pattern, end_chars ) != None:
start = False
end = True
if end:
output .write( line +'\n\n' )
desired_output .append(line +'\n\n')
elif start:
output .write( line )
desired_output .append(line)
print(desired_output)
我试了很多，但我还是把段落拆分搞糊涂了。我的主要目的是按特定的开头和结尾拆分段落。我有开始和结束的列表。
I also need to store rest of lines into other list. for use it later.
请帮帮我？
它遵循与
#! /usr/bin/env python3
import re
original = 'Original.txt'
new = 'Padded.txt'
Starts = (
r'AA .+',
r'BBBB BB.+BBB.+B',
r'CCCC .+ CCC',
)
Ends = (
r'EE .+ EEE',
r'FF.+FFF',
r'.+ GGG'
)
with open( original, 'r' ) as f:
output = open( new, 'a+' )
start = False
for line in f:
end = False
for pattern in Starts:
start_chars = line[:25]
if re .search( pattern, start_chars ) != None:
start = True
for pattern in Ends:
end_chars = line[-15:]
if re .search( pattern, end_chars ) != None:
start = False
end = True
if end: output .write( line +'\n' )
elif start: output .write( line )
1 zzz AA zzz AAA zzzz zzz zzz zzzz zzzz zzzz zzz
2 zzzzz AA zzz zzz AAA zzzz zzzzz zzzzz zzzzz zzzz
3 zzz zzzz zzz zzz zzzz zzzz zzz zzzz EE zzz EEE6 BBBB BB zzzz BBB zz B zzzzzz zzzz zzzz zzzz zzzz zz
7 zzz zzz zzzz zzzz zzz zzzzz zzzz zzzzz zzzzz FF FFF zzz8 CCCC zzz CCC zzzz zz zzzz zzzz zzz zzz GG G GGG
9 zzz AA zz AAA zzzz zzz zzz zzz FF zz FFF
10 AA zzzz AAA zzzz zzzz zzzz zzzzz zzzzz
11 zz CCCC zzz CCC zzzz zzzz zzzz zzzz zzzz zz
12 zzzz zzz zzzzz zzzzz zzzzz zzzzz zzzz zzzz EE zz EEE13 zz AA zzz
14 AAA zzz zzz zzzz zzzz GG zz GGG15 BBBB BB BBB zz B GG zz G
16 zzz GGG
谢谢@Doyousketch2。 我编辑了你的代码然后它工作得更好。
try:
file = open("Padded1.txt","r+")
file.truncate(0)
file.close()
except:
pass
import re
original = 'Original1.txt'
new = 'Padded1.txt'
result = []
with open( original, 'r' ) as f:
output = open( new, 'a+' )
start = False
for line in f:
end = False
for pattern in Starts:
start_chars = line[:30]
if re .search( pattern, start_chars ) != None:
start = True
for pattern in Ends:
end_chars = line[-20:]
if re .search( pattern, end_chars ) != None:
#####start = False
end = True
if end and start:
output .write( line +'\n\n\n' )
result.append(line +'\n\n\n')
start = False
end = False
elif start:
output .write( line )
result.append(line)
end = False
output.close()
if start == True and end == False:
#remove last line from a text line in python
fd=open("Padded1.txt","r")
d=fd.read()
fd.close()
sep = "\n\n\n\n"
s=sep.join(d.split(sep)[:-1])
fd=open("Padded1.txt","w+")
for i in range(len(s)):
fd.write(s[i])
fd.close()
elif start == False and end == True:
#remove last line from a text line in python
fd=open("Padded1.txt","r")
d=fd.read()
fd.close()
sep = "\n\n\n\n"
s=sep.join(d.split(sep)[:-1])
fd=open("Padded1.txt","w+")
for i in range(len(s)):
fd.write(s[i])
fd.close()
# Comparing Two Text Files, Removing the duplicate lines, and Writing results to a new text file
small_file = open('Original1.txt','r')
long_file = open('Padded1.txt','r')
output_file = open('output_file.txt','w')
try:
small_lines = small_file.readlines()
small_lines_cleaned = [line.rstrip().lower() for line in small_lines]
long_file_lines = long_file.readlines()
long_lines_cleaned = [line.rstrip().lower() for line in long_file_lines]
for line in small_lines_cleaned:
if line not in long_lines_cleaned:
output_file.writelines(line + '\n')
finally:
small_file.close()
long_file.close()
output_file.close()
print('Done')