python文本提取_python 文本内容提取

展开全部

^#!/usr/bin/python3

# -*- coding: utf-8 -*-

def parse(text):

result = []

import re

r1 = re.compile(r'\s*(/[^636f70793231313335323631343130323136353331333361303637\s]+)\s+FaceTracking\s+\{([^\}]*)\}\s+\(([^\)]*)\)')

r2 = re.compile(r'\s*FD_Face\s+\(([^\)]*)\)')

pos = 0

while True:

m = r1.match(text[pos:])

if not m:

break

data = {}

data['source'] = m.group(1)

keys = m.group(2).split(',')

values = m.group(3).split(',')

attrs = dict(map(lambda x,y:[x,y], keys, values))

data.update(attrs)

pos += m.end()

face = []

for x in range(int(data['FaceNumber'])):

m = r2.match(text[pos:])

if not m:

break

face.append(m.group(1).split(','))

pos += m.end()

data['FD_Face'] = face

result.append(data)

return result

def main(input_file, output_file):

f = open(input_file, 'r')

text = f.read()

f.close()

result = parse(text)

buff = []

for data in result:

buff.append('miFileIndex: {miFileIndex}'.format(**data))

buff.append('source: {source}'.format(**data))

buff.append('FaceNumber: {FaceNumber}'.format(**data))

i = 0

for face in data['FD_Face']:

i += 1

buff.append('Face{0}: ({1})'.format(i, ','.join(face)))

buff.append('')

f = open(output_file, 'w')

f.write("\n".join(buff))

f.flush()

f.close()

if __name__ == '__main__':

import sys

if len(sys.argv) == 3:

main(sys.argv[1], sys.argv[2])