成都核酸系统崩了，东软被市民连夜骂上了热榜第一，我用Python爬取了评论区，发现...

# 爬取一页评论内容
def get_one_page(url):
    headers = {
        'User-agent' : 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3880.4 Safari/537.36',
        'Host' : 'weibo.cn',
        'Accept' : 'application/json, text/plain, */*',
        'Accept-Language' : 'zh-CN,zh;q=0.9',
        'Accept-Encoding' : 'gzip, deflate, br',
        'Cookie' : '自己的Cookie',
        'DNT' : '1',
        'Connection' : 'keep-alive'
    }
    # 获取网页 html
    response = requests.get(url, headers = headers, verify=False)
    # 爬取成功
    if response.status_code == 200:
        # 返回值为 html 文档，传入到解析函数当中
        return response.text
    return None

# 解析保存评论信息
def save_one_page(html):
    comments = re.findall('<span class="ctt">(.*?)</span>', html)
    for comment in comments[1:]:
        result = re.sub('<.*?>', '', comment)
        if '回复@' not in result:
            with open('comments.txt', 'a+', encoding='utf-8') as fp:
                fp.write(result)

def jieba_():
    stop_words = []
    with open('stop_words.txt', 'r', encoding='utf-8') as f:
        lines = f.readlines()
        for line in lines:
            stop_words.append(line.strip())
    content = open('comments.txt', 'rb').read()
    # jieba 分词
    word_list = jieba.cut(content)
    words = []
    for word in word_list:
        if word not in stop_words:
            words.append(word)
    global word_cloud
    # 用逗号隔开词语
    word_cloud = '，'.join(words)

def cloud():
    # 打开词云背景图
    cloud_mask = np.array(Image.open('bg.png'))
    # 定义词云的一些属性
    wc = WordCloud(
        # 背景图分割颜色为白色
        background_color='white',
        # 背景图样
        mask=cloud_mask,
        # 显示最大词数
        max_words=200,
        # 显示中文
        font_path='./fonts/simhei.ttf',
        # 最大尺寸
        max_font_size=100
    )
    global word_cloud
    # 词云函数
    x = wc.generate(word_cloud)
    # 生成词云图片
    image = x.to_image()
    # 展示词云图片
    image.show()
    # 保存词云图片
    wc.to_file('melon.png')