如何使用python爬取天天基金网001475基金评论并计算情绪指标

下面是一个大致的代码示例，供您参考：

import requests
from bs4 import BeautifulSoup
import jieba
import jieba.analyse
import pandas as pd

# 设置请求头信息
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'}

# 爬取评论信息
def crawl_comments():
    comments = []
    for i in range(1, 11):  # 爬取前10页评论
        url = 'http://fund.eastmoney.com/comments/001475_p{}.html'.format(i)
        response = requests.get(url, headers=headers)
        soup = BeautifulSoup(response.text, 'html.parser')
        comment_list = soup.select('.cmntslist li')
        for comment in comment_list:
            content = comment.select_one('.cont').text.strip()  # 获取评论内容
            comments.append(content)
    return comments

# 计算情绪指标
def calculate_sentiment(comments):
    jieba.load_userdict("userdict.txt")  # 加载自定义词典
    sentiments = []
    for comment in comments:
        words = jieba.lcut(comment)
        score = 0
        for word in words:
            if word in ['估值', '业绩', '收益', '涨幅', '跌幅', '风险']:  # 自定义情感词
                score += 1
        sentiments.append(score)
    return sentiments

# 绘制情绪指标图表
def plot_sentiment(sentiments):
    df = pd.DataFrame({'sentiment': sentiments})
    ax = df.plot(kind='bar', color='blue')
    ax.set_xlabel('Comment Index')
    ax.set_ylabel('Sentiment Score')
    ax.set_title('Sentiment Analysis of Fund 001475 Comments')
    plt.show()

if __name__ == '__main__':
    comments = crawl_comments()
    sentiments = calculate_sentiment(comments)
    plot_sentiment(sentiments)

在这个示例代码中，crawl_comments()函数使用requests和BeautifulSoup库爬取天天基金网001475基金评论，calculate_sentiment()函数使用jieba库计算每个评论的情绪指标得分，plot_sentiment()函数使用pandas和matplotlib库将情绪指标绘制成图表。需要注意的是，为了提高分词准确率，我们在代码中使用了自定义词典。

希望这个示例代码能够对您有所帮助，如果有任何疑问，请随时向我提问。