python批量替代

import re
import jieba.analyse
import codecs
import pandas as pd
def word_replace(xianbingshi,hospital1):
    """替换词表"""
    data = []
    hospital = []
    """去重"""
    with codecs.open(hospital1,'r','utf8') as f:
        for line in f:
            line = line.strip()
            if line not in hospital:
                hospital.append(line)
            else:
                continue
    hospital.sort(key=len, reverse=True)
    with codecs.open(xianbingshi,'r','utf8') as f:
        """优先级：医院、手术、检查、症状、疾病、部位、时间"""
        for line in f:
            for ho in hospital:
                if ho in hospital:
                    line = line.replace(ho,'[hospital]')
            line = line.strip()
            data.append(line)
            print(line)
    with codecs.open(r'C:UsersAdministrator.SC-201812211013PycharmProjects词表工作代码yiwoqucodexianbingshi_write_sub.txt','w','utf8') as f:
        for line in data:
            f.write(line + '
')
        f.close()

def word_replace3(xianbingshi2, operation1):
    data = []
    operation = []
    with codecs.open(operation1,'r','utf8') as f:
        for line in f:
            line = line.strip()
            if line not in operation:
                operation.append(line)
            else:
                continue
    """排序"""
    operation.sort(key=len, reverse=True)
    with codecs.open(xianbingshi2,'r','utf8') as f:
        """优先级：医院、手术、检查、症状、疾病、部位、时间"""
        for line in f:
            for op in operation:
                if op in line:
                    line = line.replace(op, '[operation]')
            line = line.strip()
            data.append(line)
            print(line)
    with codecs.open(xianbingshi2, 'w','utf8') as f:
        for line in data:
            f.write(line + '
')
        f.close()
def word_replace1(xianbingshi2,disease1):
    data = []
    disease = []
    with codecs.open(disease1,'r','utf8') as f:
        for line in f:
            line = line.strip()
            if line not in disease:
                disease.append(line)
            else:
                continue
    disease.sort(key=len, reverse=True)
    with codecs.open(xianbingshi2,'r','utf8') as f:
        """优先级：医院、手术、检查、症状、疾病、部位、时间"""
        for line in f:
            for di in disease:
                if di in line and len(di)>1:
                    line = line.replace(di, '[disease]')
            line = line.strip()
            data.append(line)
            print(line)
    with codecs.open(xianbingshi2,'w', 'utf8') as f:
        for line in data:
            f.write(line + '
')
        f.close()
def word_replace2(xianbingshi2, symptom1):
    data = []
    symptom = []
    with codecs.open(symptom1,'r','utf8') as f:
        for line in f:
            line = line.strip()
            if line not in symptom:
                symptom.append(line)
            else:
                continue
    """排序"""
    symptom.sort(key=len, reverse=True)
    with codecs.open(xianbingshi2,'r','utf8') as f:
        """优先级：医院、手术、检查、症状、疾病、部位、时间"""
        for line in f:
            for sy in symptom:
                if sy in line and len(sy) > 1:
                    line = line.replace(sy, '[symptom]')
            line = line.strip()
            data.append(line)
            print(line)
    with codecs.open(xianbingshi2,'w', 'utf8') as f:
        for line in data:
            f.write(line + '
')
        f.close()

def word_replace4(xianbingshi2, test1):
    data = []
    test = []
    with codecs.open(test1,'r','utf8') as f:
        for line in f:
            line = line.strip()
            if line not in test:
                test.append(line)
            else:
                continue
    """排序"""
    test.sort(key=len, reverse=True)
    with codecs.open(xianbingshi2,'r','utf8') as f:
        """优先级：医院、手术、检查、症状、疾病、部位、时间"""
        for line in f:
            for te in test:
                if te in line:
                    line = line.replace(te, '[test]')
            line = line.strip()
            data.append(line)
            print(line)
    with codecs.open(xianbingshi2, 'w','utf8') as f:
        for line in data:
            f.write(line + '
')
        f.close()
def word_replace5(xianbingshi2, time1):
    data = []
    time = []
    with codecs.open(time1,'r','utf8') as f:
        for line in f:
            line = line.strip()
            if line not in time:
                time.append(line)
            else:
                continue
    """排序"""
    time.sort(key=len, reverse=True)
    with codecs.open(xianbingshi2,'r','utf8') as f:
        """优先级：医院、手术、检查、症状、疾病、部位、时间"""
        for line in f:
            for t in time:
                if t in line:
                    line = line.replace(t,'[time]')
            line = line.strip()
            data.append(line)
            print(line)
    with codecs.open(xianbingshi2,'w', 'utf8') as f:
        for line in data:
            f.write(line + '
')
        f.close()
def word_replace6(xianbingshi2, organ1):
    data = []
    organ = []
    with codecs.open(organ1,'r','utf8') as f:
        for line in f:
            line = line.strip()
            if line not in organ:
                organ.append(line)
            else:
                continue
    """排序"""
    organ.sort(key=len, reverse=True)
    with codecs.open(xianbingshi2,'r','utf8') as f:
        """优先级：医院、手术、检查、症状、疾病、部位、时间"""
        for line in f:
            for o in organ:
                if o in line and len(o) > 1:
                    line = line.replace(o, '[organ]')
            line = line.strip()
            data.append(line)
            print(line)
    with codecs.open(xianbingshi2,'w', 'utf8') as f:
        for line in data:
            f.write(line + '
')
        f.close()
def word_replace7(xianbingshi2, symptom1):
    data = []
    symptom = []
    with codecs.open(symptom1,'r','utf8') as f:
        for line in f:
            line = line.strip()
            if line not in symptom and len(line) == 1:
                symptom.append(line)
                print(line)
            else:
                continue
    """排序"""
    symptom.sort(key=len, reverse=True)
    with codecs.open(xianbingshi2,'r','utf8') as f:
        """优先级：医院、手术、检查、症状、疾病、部位、时间"""
        for line in f:
            for sy in symptom:
                line = line.replace(sy, '[symptom]')
            line = line.strip()
            data.append(line)
            print(line)
    with codecs.open(xianbingshi2,'w', 'utf8') as f:
        for line in data:
            f.write(line + '
')
        f.close()
def word_replace8(xianbingshi2, disease1):
    data = []
    disease = []
    with codecs.open(disease1,'r','utf8') as f:
        for line in f:
            line = line.strip()
            if line not in disease and line == 1:
                disease.append(line)
            else:
                continue
    """排序"""
    disease.sort(key=len, reverse=True)
    with codecs.open(xianbingshi2,'r','utf8') as f:
        """优先级：医院、手术、检查、症状、疾病、部位、时间"""
        for line in f:
            for di in disease:
                line = line.replace(di, '[disease]')
            line = line.strip()
            data.append(line)
            print(line)
    with codecs.open(xianbingshi2,'w', 'utf8') as f:
        for line in data:
            f.write(line + '
')
        f.close()
def word_replace9(xianbingshi2, organ1):
    data = []
    organ = []
    with codecs.open(organ1,'r','utf8') as f:
        for line in f:
            line = line.strip()
            if line not in organ and line == 1:
                organ.append(line)
            else:
                continue
    """排序"""
    organ.sort(key=len, reverse=True)
    with codecs.open(xianbingshi2,'r','utf8') as f:
        """优先级：医院、手术、检查、症状、疾病、部位、时间"""
        for line in f:
            for o in organ:
                 line = line.replace(o, '[organ]')
            line = line.strip()
            data.append(line)
            print(line)
    with codecs.open(xianbingshi2,'w', 'utf8') as f:
        for line in data:
            f.write(line + '
')
        f.close()
if __name__ == '__main__':
    disease1 =r'C:UsersAdministrator.SC-201812211013PycharmProjects词表工作代码yiwoquTXTdisease_0903.txt'
    organ1 = r"C:UsersAdministrator.SC-201812211013PycharmProjects词表工作代码yiwoquTXTorgan_0903.txt"
    test1 = r"C:UsersAdministrator.SC-201812211013PycharmProjects词表工作代码yiwoquTXT	est_0903.txt"
    time1 = r"C:UsersAdministrator.SC-201812211013PycharmProjects词表工作代码yiwoqu	ime1.txt"
    operation1 = r"C:UsersAdministrator.SC-201812211013PycharmProjects词表工作代码yiwoquTXToperation_0903.txt"
    symptom1 = r"C:UsersAdministrator.SC-201812211013PycharmProjects词表工作代码yiwoqucode症状.txt"
    xianbingshi = r'C:UsersAdministrator.SC-201812211013PycharmProjects词表工作代码yiwoqucodexianbingshi_write.txt'
    xianbingshi2 =r'C:UsersAdministrator.SC-201812211013PycharmProjects词表工作代码yiwoqucodexianbingshi_write_sub.txt'
    hospital1 = r'C:UsersAdministrator.SC-201812211013PycharmProjects词表工作代码yiwoquTXThospital_0903.txt'
    word_replace(xianbingshi, hospital1)
    word_replace3(xianbingshi2, operation1)
    word_replace1(xianbingshi2, disease1)
    word_replace2(xianbingshi2, symptom1)
    word_replace4(xianbingshi2, test1)
    # word_replace5(xianbingshi2, time1)
    word_replace6(xianbingshi2, organ1)
    word_replace7(xianbingshi2, symptom1)
    word_replace8(xianbingshi2, disease1)
    word_replace9(xianbingshi2, organ1)