Python flashtext文本搜索和替换操作库功能使用探索

pip install flashtext

from flashtext import KeywordProcessor

keyword_processor = KeywordProcessor()
keyword_processor.add_keyword("Python", "Python3")
keyword_processor.add_keyword("flashtext", "text search")

text = "Python is a popular programming language. flashtext is a fast text search library."
result = keyword_processor.replace_keywords(text)
print(result)

keyword_dict = {"Python": "Python3", "flashtext": "text search"}
keyword_processor.add_keywords_from_dict(keyword_dict)

keyword_processor.add_keyword("book")
keyword_processor.add_keyword("booked")

text = "I booked a book."
result = keyword_processor.replace_keywords(text, whole_word=False)
print(result)

import re
keyword_processor.add_keyword("email", re.compile(r"\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b"))

text = "My email is john@example.com and my phone number is 123-456-7890."
keywords = keyword_processor.extract_keywords(text)
print(keywords)

# 将敏感词汇替换为*
sensitive_words = ["password", "credit card"]
for word in sensitive_words:
    keyword_processor.add_keyword(word, "*")

text = "Please do not share your password or credit card information."
cleaned_text = keyword_processor.replace_keywords(text)
print(cleaned_text)

# 提取文本中的日期
keyword_processor.add_keyword("date", re.compile(r"\d{4}-\d{2}-\d{2}"))

text = "The meeting is scheduled for 2023-01-15. Don't forget the date."
dates = keyword_processor.extract_keywords(text)
print(dates)

# 优化网站内容
seo_keywords = {"Python": "Python programming", "flashtext": "text search tool"}
keyword_processor.add_keywords_from_dict(seo_keywords)

text = "Learn Python with the flashtext library."
optimized_text = keyword_processor.replace_keywords(text)
print(optimized_text)