def read_txt_file_by_line(filepath):
    with open(filepath, 'r', encoding='utf-8') as file:
        for line in file:
            print(line.strip())
# 示例調(diào)用
read_txt_file_by_line('example.txt')

def read_txt_file(filepath):
    with open(filepath, 'r', encoding='utf-8') as file:
        content = file.read()
    return content
# 示例調(diào)用
content = read_txt_file('example.txt')
print(content)

def compare_txt_files(file1, file2):
    with open(file1, 'r', encoding='utf-8') as f1, open(file2, 'r', encoding='utf-8') as f2:
        content1 = f1.readlines()
        content2 = f2.readlines()    
    for line1, line2 in zip(content1, content2):
        if line1 != line2:
            print(f'Difference found:\nFile1: {line1}\nFile2: {line2}')
# 示例調(diào)用
compare_txt_files('file1.txt', 'file2.txt')

import difflib
def highlight_differences(file1, file2):
    with open(file1, 'r', encoding='utf-8') as f1, open(file2, 'r', encoding='utf-8') as f2:
        content1 = f1.readlines()
        content2 = f2.readlines()

    diff = difflib.unified_diff(content1, content2, fromfile='file1', tofile='file2')
    for line in diff:
        print(line)
# 示例調(diào)用
highlight_differences('file1.txt', 'file2.txt')  

def filter_lines_by_keyword(filepath, keyword):
    with open(filepath, 'r', encoding='utf-8') as file:
        lines = file.readlines()
    
    filtered_lines = [line for line in lines if keyword not in line]
    return filtered_lines
# 示例調(diào)用
filtered = filter_lines_by_keyword('example.txt', 'filter_keyword')
for line in filtered:
    print(line.strip())

def filter_empty_and_comment_lines(filepath):
    with open(filepath, 'r', encoding='utf-8') as file:
        lines = file.readlines()
    
    filtered_lines = [line for line in lines if line.strip() and not line.strip().startswith('#')]
    return filtered_lines
# 示例調(diào)用
filtered = filter_empty_and_comment_lines('example.txt')
for line in filtered:
    print(line.strip())

def merge_txt_files(file_list, output_file):
    with open(output_file, 'w', encoding='utf-8') as outfile:
        for file in file_list:
            with open(file, 'r', encoding='utf-8') as infile:
                outfile.write(infile.read())
                outfile.write('\n')
# 示例調(diào)用
merge_txt_files(['file1.txt', 'file2.txt', 'file3.txt'], 'merged.txt')

def merge_files_by_line(file_list, output_file):
    files = [open(file, 'r', encoding='utf-8') for file in file_list]
    with open(output_file, 'w', encoding='utf-8') as outfile:
        while True:
            lines = [file.readline() for file in files]
            if all(line == '' for line in lines):
                break
            for line in lines:
                if line:
                    outfile.write(line.strip() + '\n')
    for file in files:
        file.close()
# 示例調(diào)用
merge_files_by_line(['file1.txt', 'file2.txt', 'file3.txt'], 'merged_by_line.txt')

import csv
def txt_to_csv(txt_file, csv_file):
with open(txt_file, 'r', encoding='utf-8') as infile, open(csv_file, 'w', newline='', encoding='utf-8') 
as outfile:
        writer = csv.writer(outfile)
        for line in infile:
            writer.writerow(line.strip().split())
# 示例調(diào)用
txt_to_csv('example.txt', 'output.csv')

import json
def txt_to_json(txt_file, json_file):
    data = []
    with open(txt_file, 'r', encoding='utf-8') as infile:
        for line in infile:
            data.append(line.strip())

    with open(json_file, 'w', encoding='utf-8') as outfile:
        json.dump(data, outfile, indent=4)
# 示例調(diào)用
txt_to_json('example.txt', 'output.json')

import re
def extract_pattern_from_txt(pattern, txt_file):
    matches = []
    with open(txt_file, 'r', encoding='utf-8') as file:
        content = file.read()
        matches = re.findall(pattern, content)
    return matches
# 示例調(diào)用，提取所有的數(shù)字
pattern = r'\d+'
matches = extract_pattern_from_txt(pattern, 'example.txt')
print("Match found:", matches)

def extract_emails_and_urls(txt_file):
    email_pattern = r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}'
    url_pattern = r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+'    
    with open(txt_file, 'r', encoding='utf-8') as file:
        content = file.read()
        
    emails = re.findall(email_pattern, content)
    urls = re.findall(url_pattern, content)    
    return emails, urls
# 示例調(diào)用
emails, urls = extract_emails_and_urls('example.txt')
print("Emails found:", emails)
print("URLs found:", urls)

from collections import Counter

def count_word_frequency(txt_file):
    with open(txt_file, 'r', encoding='utf-8') as file:
        words = file.read().split()
        word_freq = Counter(words)
    return word_freq
# 示例調(diào)用
word_freq = count_word_frequency('example.txt')
for word, freq in word_freq.most_common():
    print(f'{word}: {freq}')

from wordcloud import WordCloud
import matplotlib.pyplot as plt

def generate_word_cloud(txt_file):
    with open(txt_file, 'r', encoding='utf-8') as file:
        text = file.read()        
    wordcloud = WordCloud(width=800, height=400, background_color='white').generate(text)
    plt.figure(figsize=(10, 5))
    plt.imshow(wordcloud, interpolation='bilinear')
    plt.axis('off')
    plt.show()
# 示例調(diào)用
generate_word_cloud('example.txt')

def generate_report_from_template(template_file, output_file, data):
with open(template_file, 'r', encoding='utf-8') as infile, open(output_file, 'w', encoding='utf-8') 
as outfile:
        content = infile.read()
        for key, value in data.items():
            content = content.replace(f'{{{{ {key} }}}}', str(value))
        outfile.write(content)
# 示例調(diào)用
data = {
    'name': 'Alice',
    'date': '2024-08-17',
    'summary': 'This is a summary of the report.'}
generate_report_from_template('template.txt', 'report.txt', data)

def generate_dynamic_report(output_file, sections):
    with open(output_file, 'w', encoding='utf-8') as outfile:
        for section in sections:
            outfile.write(f'# {section["title"]}\n\n')
            outfile.write(f'{section["content"]}\n\n')
# 示例調(diào)用
sections = [{"title": "Introduction",
        "content": "This is the introduction section of the report."},
    {"title": "Data Analysis",
        "content": "This section contains the analysis of the data."}]
generate_dynamic_report('dynamic_report.txt', sections)