Python代码怎样进行文本处理 Python代码正则表达式的应用实例

text = "  Hello, World!  "
cleaned_text = text.strip()  # 去除首尾空白
words = cleaned_text.split(",")  # 分割成单词列表
print(words) # 输出：['Hello', ' World!']

import re

text = "My email is example@domain.com and another one is test@sub.domain.org"
emails = re.findall(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}", text)
print(emails) # 输出：['example@domain.com', 'test@sub.domain.org']

import re

html_text = "<p>This is a paragraph with <b>bold</b> text.</p>"
clean_text = re.sub(r"<[^>]+>", "", html_text)
print(clean_text) # 输出：This is a paragraph with bold text.

import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords

nltk.download('punkt') # 如果没有下载过punkt分词器，需要先下载
nltk.download('stopwords') # 如果没有下载过停用词列表，需要先下载

text = "This is an example sentence. It contains some words."
tokens = word_tokenize(text) # 分词
stop_words = set(stopwords.words("english")) # 获取英文停用词列表
filtered_tokens = [w for w in tokens if not w.lower() in stop_words] # 去除停用词

print(filtered_tokens) # 输出：['example', 'sentence', '.', 'contains', 'words', '.']

import re

text = "Hello World"
new_text = re.sub(r"(\w+) (\w+)", r"\2 \1", text)
print(new_text) # 输出：World Hello

# 以指定编码方式读取文件
with open("file.txt", "r", encoding="gbk") as f:
    content = f.read()

# 将字符串编码成指定编码方式的字节序列
byte_string = "你好".encode("utf-8")

# 将字节序列解码成字符串
string = byte_string.decode("utf-8")

import chardet

with open("file.txt", "rb") as f:
    raw_data = f.read()
    result = chardet.detect(raw_data)
    encoding = result["encoding"]

print(encoding)

import re

pattern = re.compile(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}")
emails = pattern.findall(text)