Python如何匹配文本并在其上一行追加文本

Valarie ·

更新时间:2024-11-15

· 1668 次阅读

匹配文本并在其上一行追加文本

问题描述

对比

遇到的坑

用正则表达式匹配文本(Python经典编程案例)

匹配文本并在其上一行追加文本 问题描述

Python匹配文本并在其上一行追加文本

test.txt

a
b
c
d
e

1.读进列表后覆盖原文件

def match_then_insert(filename, match, content):
    """匹配后在该行追加
    :param filename: 要操作的文件
    :param match: 匹配内容
    :param content: 追加内容
    """
    lines = open(filename).read().splitlines()
    index = lines.index(match)
    lines.insert(index, content)
    open(filename, mode='w').write('\n'.join(lines))
match_then_insert('test.txt', match='c', content='123')

效果

a
b
123
c
d
e

2.FileInput类

from fileinput import FileInput
def match_then_insert(filename, match, content):
    """匹配后在该行追加
    :param filename: 要操作的文件
    :param match: 匹配内容
    :param content: 追加内容
    """
    for line in FileInput(filename, inplace=True):  # 原地过滤
        if match in line:
            line = content + '\n' + line
        print(line, end='')  # 输出重定向到原文件
match_then_insert('test.txt', match='c', content='123')

3.seek

def match_then_insert(filename, match, content):
    """匹配后在该行追加
    :param filename: 要操作的文件
    :param match: 匹配内容
    :param content: 追加内容
    """
    with open(filename, mode='rb+') as f:
        while True:
            try:
                line = f.readline()  # 逐行读取
            except IndexError:  # 超出范围则退出
                break
            line_str = line.decode().splitlines()[0]
            if line_str == match:
                f.seek(-len(line), 1)  # 光标移动到上一行
                rest = f.read()  # 读取余下内容
                f.seek(-len(rest), 1)  # 光标移动回原位置
                f.truncate()  # 删除余下内容
                content = content + '\n'
                f.write(content.encode())  # 插入指定内容
                f.write(rest)  # 还原余下内容
                break
match_then_insert('test.txt', match='c', content='123')

对比方案耗时/s

读进列表后覆盖原文件	54.42
FileInput类	121.59
seek	3.53

from timeit import timeit
from fileinput import FileInput
def init_txt():
    open('test.txt', mode='w').write('\n'.join(['a', 'b', 'c', 'd', 'e']))
def f1(filename='test.txt', match='c', content='123'):
    lines = open(filename).read().splitlines()
    index = lines.index(match)
    lines.insert(index, content)
    open(filename, mode='w').write('\n'.join(lines))
def f2(filename='test.txt', match='c', content='123'):
    for line in FileInput(filename, inplace=True):
        if match in line:
            line = content + '\n' + line
        print(line, end='')
def f3(filename='test.txt', match='c', content='123'):
    with open(filename, mode='rb+') as f:
        while True:
            try:
                line = f.readline()
            except IndexError:
                break
            line_str = line.decode().splitlines()[0]
            if line_str == match:
                f.seek(-len(line), 1)
                rest = f.read()
                f.seek(-len(rest), 1)
                f.truncate()
                content = content + '\n'
                f.write(content.encode())
                f.write(rest)
                break
init_txt()
print(timeit(f1, number=1000))
init_txt()
print(timeit(f2, number=1000))
init_txt()
print(timeit(f3, number=1000))

遇到的坑

报错可试试在文件头部添加

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

或指定 encoding='utf-8'

用正则表达式匹配文本(Python经典编程案例)

ceshi.txt文本如下：第一行为空行


爬虫任务报警
01:45:21
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-1
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: ah_sina_com_cn,job: 28395818dbcb11e998a3f632d94e247c,pid: 88971,log: data/logs/chinabond_fast_spider/ah_sina_com_cn/28395818dbcb11e998a3f632d94e247c.log,items: None
error_data:
爬虫任务报警
01:45:21
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-6
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: shupeidian_bjx_com_cn,job: 04738a5cdbcb11e9803172286b76aa73,pid: 34246,log: data/logs/chinabond_fast_spider/shupeidian_bjx_com_cn/04738a5cdbcb11e9803172286b76aa73.log,items: None
error_data:
爬虫任务报警
01:45:21
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-6
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: news_sdchina_com,job: 28e8db4edbcb11e9803172286b76aa73,pid: 34324,log: data/logs/chinabond_fast_spider/news_sdchina_com/28e8db4edbcb11e9803172286b76aa73.log,items: None
error_data:
爬虫任务报警
01:47:20
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-0
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: hq_smm_cn,job: 4bdc3af6dbcb11e9a45522b8c8b2a9e4,pid: 111593,log: data/logs/chinabond_fast_spider/hq_smm_cn/4bdc3af6dbcb11e9a45522b8c8b2a9e4.log,items: None
error_data:
爬虫任务报警
01:47:21
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-6
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: sichuan_scol_com_cn,job: 71321c4edbcb11e9803172286b76aa73,pid: 34461,log: data/logs/chinabond_fast_spider/sichuan_scol_com_cn/71321c4edbcb11e9803172286b76aa73.log,items: None
error_data:
爬虫任务报警
01:47:21
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-2
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: www_mof_gov_cn,job: 7418dacedbcb11e9b15e02034af50b6e,pid: 65326,log: data/logs/chinabond_fast_spider/www_mof_gov_cn/7418dacedbcb11e9b15e02034af50b6e.log,items: None
error_data:
爬虫任务报警
01:47:21
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-5
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: www_funxun_com,job: 4dcda7a0dbcb11e980a8862f09ca6d70,pid: 27785,log: data/logs/chinabond_fast_spider/www_funxun_com/4dcda7a0dbcb11e980a8862f09ca6d70.log,items: None
error_data:
爬虫任务报警
01:49:21
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-4
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: shuidian_bjx_com_cn,job: 95090682dbcb11e9a0fade28e59e3773,pid: 106424,log: data/logs/chinabond_fast_spider/shuidian_bjx_com_cn/95090682dbcb11e9a0fade28e59e3773.log,items: None
error_data:
爬虫任务报警
01:51:20
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-0
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: tech_sina_com_cn,job: de4bdf72dbcb11e9a45522b8c8b2a9e4,pid: 111685,log: data/logs/chinabond_fast_spider/tech_sina_com_cn/de4bdf72dbcb11e9a45522b8c8b2a9e4.log,items: None
error_data:
爬虫任务报警
01:51:21
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-6
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: ee_ofweek_com,job: ff6bd5b8dbcb11e9803172286b76aa73,pid: 34626,log: data/logs/chinabond_fast_spider/ee_ofweek_com/ff6bd5b8dbcb11e9803172286b76aa73.log,items: None
error_data:
爬虫任务报警
01:51:21
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-6
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: house_hexun_com,job: ff6dfdacdbcb11e9803172286b76aa73,pid: 34633,log: data/logs/chinabond_fast_spider/house_hexun_com/ff6dfdacdbcb11e9803172286b76aa73.log,items: None
error_data:
爬虫任务报警
01:51:21
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-2
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: www_sjfzxm_com,job: 018e7d78dbcc11e9b15e02034af50b6e,pid: 65492,log: data/logs/chinabond_fast_spider/www_sjfzxm_com/018e7d78dbcc11e9b15e02034af50b6e.log,items: None
error_data:
爬虫任务报警
01:53:21
scrapyd==》爬虫任务异常死亡报警
hostname: scrapyd-chinabond-4
error_count: Process died: exitstatus=None ,project: chinabond_fast_spider,spider: news_xianzhaiwang_cn,job: 48d835e8dbcc11e9a0fade28e59e3773,pid: 106476,log: data/logs/chinabond_fast_spider/news_xianzhaiwang_cn/48d835e8dbcc11e9a0fade28e59e3773.log,items: None
error_data:

代码如下：

import os
import re
import json
from collections import namedtuple
alert = namedtuple('Spider_Alert', 'alert_time, alert_hostname, alert_project, alert_spider')
path = r'D:\data\ceshi.txt'
g_path = r'D:\data\\'
file_name = r'result.txt'
file_path = g_path + file_name
alerts_list = list()
with open(path, encoding="utf-8") as file:
    lines = file.readlines()  # 读取每一行
    count = 0
    time = None
    hostname = None
    project = None
    for line in lines:
        if re.search(r'^\d{2}:\d{2}:\d{2}\s*$', line):
            time = re.search(r'^(\d{2}:\d{2}:\d{2})\s*$', line).group(1)
        if re.search(r'^hostname:\s*(.+)', line):
            hostname = re.search(r'^hostname:\s*(.+)', line).group(1)
        if re.search(r'project:\s*([^,]+),', line):
            project = re.search(r'project:\s*([^,]+),', line).group(1)
        if re.search(r'spider:\s*([^,]+),', line):
            spider = re.search(r'spider:\s*([^,]+),', line).group(1)
        if re.search(r'^error_data', line):
            spider_alert = None
            spider_alert = alert(alert_time=time, alert_hostname=hostname, alert_project=project, alert_spider=spider)
            alerts_list.append(spider_alert)
for element in alerts_list:
    print(element[0], element[1], element[3])
    with open(file_path, 'a', encoding="utf-8") as file:
        file.write(element[0] + "\t" + element[1] + "\t" + element[3])
        file.write(' \n')

执行结果如下图：