阿珏酱

import os
import re
import time
import requests
from bs4 import BeautifulSoup
from urllib.parse import urlparse, parse_qs

# 指定文件路径
file_path = "C:\\Users\\Administrator\\Desktop\\blog\\content.txt"
save_folder = "C:\\Users\\Administrator\\Desktop\\blog\\content\\"

def save_to_file(data, file_name):
    try:
        file_path = os.path.join(save_folder, file_name + ".txt")
        with open(file_path, 'a', encoding='utf-8') as file:
            file.write(data)
        print("数据已成功保存到文件:", file_path)
    except Exception as e:
        print("保存文件时出错:", e)


def remove_html_tags(text):
    soup = BeautifulSoup(text, 'html.parser')
    return soup.get_text()


def comment(html_content):
    comment_matches = re.findall(r'<div class="comment (.*?)" id="comment-\d+">[\s\S]*?<img .*?inal=".*?202.*?/([^"]+)"/>[\s\S]*?<div ' +
                                 'class="comment-content">(.*?)</div>[\s\S]*?itle=".*?">(.*?)</span>[\s\S]*?<span class="comment-time">(.*?)</span>',
                                 html_content, re.DOTALL)
    article_comments = ''
    if comment_matches:
        i = 0
        for comment_match in comment_matches:
            if 'comment-children' in comment_match[0]:
                i += 1
                is_reply_comment = '>' * i
            else:
                is_reply_comment = '>'
                i = 1

            #头像 大小控制在40
            # 兼容gravatar头像 https://secure.gravatar.com/avatar/ 
            if 'gravatar.com' in comment_match[1]:
                avatar_url = '![](' + str(re.sub(r'(\?|&)s=\d+', '\\1s=40', str(comment_match[1]))) + ')    ' 
            else: 
                parsed_url = urlparse(comment_match[1])
                query_params = parse_qs(parsed_url.query)
                dst_uin = query_params.get('dst_uin', ['1638211921'])
                avatar_url = '![]('+'https://q1.qlogo.cn/g?b=qq&nk='+str(dst_uin[0])+'&s=40'+')    '   

            comment_content = comment_match[2].strip()  
            nickname = comment_match[3].strip()  
            comment_time = comment_match[4].strip()  
            link_url = re.search(r'030.*?/(.*?)" .*? rel', nickname)  

            # 构造评论的markdown格式
            comment_content = is_reply_comment + comment_content.replace('\n', '>')
            comment_content = comment_content.replace('##这篇评论是私密评论##', '[#这篇评论是私密评论#]')

            # 替换表情图片
            soup = BeautifulSoup(comment_content, 'html.parser')
            for img in soup.find_all('img'):
                title_text = img.get('title', '')
                img.replace_with('[#'+title_text+']')

            comment_content = soup.get_text()

            # 保存评论用户的URL地址
            if link_url:
                nickname = '['+remove_html_tags(nickname)+']'
                link_url = '(' + link_url[1] + ')   '
            else:
                link_url = ''
                nickname = remove_html_tags(nickname) + '   '

            if i == 1:
                article_comments += '\n'

            article_comments += is_reply_comment + avatar_url + nickname + link_url + comment_time + '\n' + comment_content + '\n'

        return article_comments
    else:
        return ''


def process_article(url):
    print("当前执行===="+url)
    response = requests.get(url)

    if response.status_code == 200:
        html_content = response.text
        soup = BeautifulSoup(html_content, 'html.parser')
        article_title = soup.find('h1', class_='article-title') 
        article_mate = soup.find('div', class_='article-meta') 
        article_article = soup.find('article', class_='article-content') 

        soup_content = BeautifulSoup(article_article.prettify(), 'html.parser')
        img_tags = soup_content.find_all('img')
        pattern = r"https://web.*?_/"
        
        for img_tag in img_tags:
            if 'data-original' in img_tag.attrs:
                original_url = img_tag['data-original']
            else:
                original_url = img_tag['src']

            cleaned_url = re.sub(pattern, '', original_url)
            new_url = 'https://image.baidu.com/search/down?url=' + cleaned_url
            img_tag['src'] = new_url
            del img_tag['data-original']

        article_comment = soup.find('div', class_='article_comment_list') 
        data = "###### `当你看到这个提示的时候，说明当前的文章是由原emlog博客系统搬迁至此的，文章发布时间已过于久远，编排和内容不一定完整，还请谅解`\n\n" + '###' + article_title.text.strip()+'\n\n'+article_mate.text.strip().replace('\n', '').replace('\r', '').replace('\t', '')+'\n' + soup_content.prettify().replace('<article class="article-content">', '').replace('</article>', '')

        save_to_file(data + '\n网友评论：\n\n', article_title.text.strip())

        data = comment(html_content)

        if not data:
            return

        save_to_file(data, article_title.text.strip())

        if article_comment:
            comment_links = re.findall(r'<a\s+href="(.*?)nts"', str(article_comment))

            if comment_links:
                print('有分页评论数据')
                for link in comment_links:
                    url = link +"nts"
                    print(url)
                    response = requests.get(url)

                    if response.status_code == 200:
                        html_content = response.text
                        data = comment(html_content)
                        if not data:
                            return
                        save_to_file(data, article_title.text.strip())
                        print("写分页评论数据中")
    else:
        print("Failed to retrieve the webpage.")


def main():
    with open(file_path, 'r', encoding='utf-8') as file:
        for line in file:
            segments = line.strip().split("----")

            if len(segments) > 0:
                url = segments[0]  
                process_article(url)
            else:
                print("No URL found in the line.")
            print('开启下一篇文章')
            time.sleep(4)

if __name__ == "__main__":
    main()