本文目录导读：
Python实现（最灵活）
基础文本抽取
import re
import os
def extract_content(file_path, pattern):
"""从文件中抽取符合正则表达式的内容"""
results = []
try:
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
matches = re.findall(pattern, content)
results.extend(matches)
except Exception as e:
print(f"读取文件错误: {e}")
return results
# 示例：抽取所有邮箱地址
emails = extract_content('data.txt', r'[\w\.-]+@[\w\.-]+\.\w+')
print(emails)
结构化文件抽取
import json
import csv
import xml.etree.ElementTree as ET
def extract_json_fields(json_file, fields):
"""从JSON文件抽取指定字段"""
with open(json_file, 'r', encoding='utf-8') as f:
data = json.load(f)
extracted = []
if isinstance(data, list):
for item in data:
extracted.append({field: item.get(field) for field in fields})
return extracted
def extract_csv_columns(csv_file, columns, delimiter=','):
"""从CSV文件抽取指定列"""
with open(csv_file, 'r', encoding='utf-8') as f:
reader = csv.DictReader(f, delimiter=delimiter)
return [{col: row[col] for col in columns if col in row}
for row in reader]
# 示例使用
json_data = extract_json_fields('data.json', ['name', 'email', 'age'])
csv_data = extract_csv_columns('data.csv', ['name', 'phone'])
Shell脚本（Linux/Unix环境）
#!/bin/bash
# 抽取文件中的特定模式
extract_pattern() {
local file=$1
local pattern=$2
grep -oP "$pattern" "$file"
}
# 抽取CSV文件的指定列
extract_csv_column() {
local file=$1
local column=$2
local delimiter=${3:-,}
cut -d"$delimiter" -f"$column" "$file"
}
# 抽取文件的关键字行
extract_keyword_lines() {
local file=$1
local keyword=$2
grep -n "$keyword" "$file"
}
# 使用示例
# extract_pattern "log.txt" "error.*"
# extract_csv_column "data.csv" 1,3,5
PowerShell（Windows环境）
# 抽取文本文件中的匹配行
function Extract-Content {
param(
[string]$FilePath,
[string]$Pattern,
[string]$OutputFile
)
$matches = Select-String -Path $FilePath -Pattern $Pattern
if ($OutputFile) {
$matches | Select-Object -ExpandProperty Line | Out-File -FilePath $OutputFile
}
return $matches
}
# 抽取CSV文件列
function Extract-CsvColumns {
param(
[string]$CsvFile,
[string[]]$Columns
)
Import-Csv $CsvFile | Select-Object $Columns
}
# 示例
# Extract-Content -FilePath "log.txt" -Pattern "ERROR|WARNING"
# Extract-CsvColumns -CsvFile "data.csv" -Columns "Name", "Email"
高级功能实现
批量文件处理
import glob
import os
def batch_extract(directory, file_pattern, extraction_func):
"""批量处理目录中的文件"""
results = {}
for file_path in glob.glob(os.path.join(directory, file_pattern)):
filename = os.path.basename(file_path)
results[filename] = extraction_func(file_path)
return results
# 示例：处理所有.log文件
def extract_errors(file_path):
errors = []
with open(file_path, 'r') as f:
for line in f:
if 'ERROR' in line:
errors.append(line.strip())
return errors
all_errors = batch_extract('./logs', '*.log', extract_errors)
按条件抽取
class ConditionExtractor:
def __init__(self, conditions):
"""
conditions: [(column_index, operator, value), ...]
"""
self.conditions = conditions
def extract_from_csv(self, csv_file, delimiter=','):
result = []
with open(csv_file, 'r', encoding='utf-8') as f:
reader = csv.reader(f)
headers = next(reader)
for row in reader:
if self._check_conditions(row):
result.append(row)
return result
def _check_conditions(self, row):
for col_idx, operator, value in self.conditions:
cell = row[col_idx]
if operator == '>':
if not (float(cell) > float(value)):
return False
elif operator == 'contains':
if value not in cell:
return False
return True
实用工具函数
import re
from collections import Counter
def extract_html_tags(html_file, tag):
"""抽取HTML文件中的特定标签内容"""
pattern = f'<{tag}[^>]*>(.*?)</{tag}>'
with open(html_file, 'r', encoding='utf-8') as f:
return re.findall(pattern, f.read(), re.DOTALL)
def extract_unique_values(file_path, separator=None):
"""抽取文件中唯一的值"""
with open(file_path, 'r') as f:
if separator:
values = f.read().split(separator)
else:
values = [line.strip() for line in f]
return list(set(filter(None, values)))
def extract_word_frequency(file_path):
"""抽取文件中的单词频率"""
with open(file_path, 'r', encoding='utf-8') as f:
words = re.findall(r'\b\w+\b', f.read().lower())
return Counter(words).most_common(10)
使用建议
- 简单文本匹配：使用Shell或PowerShell
- 复杂数据处理：使用Python
- 大文件处理：使用流式处理避免内存溢出
- 正则表达式模式：根据具体需求定制pattern
- 错误处理：添加适当的异常处理
- 编码问题：注意文件编码格式
这些脚本可以根据具体需求进行定制和组合使用。
