python爬取b站评论_用python 抓取B站视频评论，制作词云

好的，很高兴回答您的问题！

首先，我们需要安装一些必要的库，如requests、BeautifulSoup、jieba、wordcloud等。你可以使用以下命令进行安装：

pip install requests
pip install BeautifulSoup4
pip install jieba
pip install wordcloud

接下来，我们需要先获取视频的av号（或者BV号），然后通过B站的API接口来获取评论数据。代码如下：

import requests
import json

# 获取B站视频评论
def get_bilibili_comment(aid):
    url = "https://api.bilibili.com/x/v2/reply?pn={}&type=1&oid={}&sort=2"
    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"}
    comments = []
    for i in range(1, 6):  # 抓取前5页评论
        response = requests.get(url.format(i, aid), headers=headers)
        data = json.loads(response.text)
        for comment in data["data"]["replies"]:
            comments.append(comment["content"]["message"])
    return comments

# 获取B站视频的av号
def get_bilibili_av(bv):
    url = "https://api.bilibili.com/x/web-interface/view?bvid={}"
    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"}
    response = requests.get(url.format(bv), headers=headers)
    data = json.loads(response.text)
    return data["data"]["aid"]

接着，我们需要使用jieba库对评论内容进行分词，并将分词结果存储到一个列表中。代码如下：

import jieba

# 分词
def cut_words(comments):
    words = []
    for comment in comments:
        words += jieba.lcut(comment)
    return words

最后，我们可以使用wordcloud库来制作词云图。代码如下：

import matplotlib.pyplot as plt
from wordcloud import WordCloud

# 制作词云图
def make_wordcloud(words):
    text = " ".join(words)
    wc = WordCloud(background_color="white", max_words=200, font_path="msyh.ttc")
    wc.generate(text)
    plt.imshow(wc)
    plt.axis("off")
    plt.show()

完整代码如下：

import requests
import json
import jieba
import matplotlib.pyplot as plt
from wordcloud import WordCloud

# 获取B站视频评论
def get_bilibili_comment(aid):
    url = "https://api.bilibili.com/x/v2/reply?pn={}&type=1&oid={}&sort=2"
    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"}
    comments = []
    for i in range(1, 6):  # 抓取前5页评论
        response = requests.get(url.format(i, aid), headers=headers)
        data = json.loads(response.text)
        for comment in data["data"]["replies"]:
            comments.append(comment["content"]["message"])
    return comments

# 获取B站视频的av号
def get_bilibili_av(bv):
    url = "https://api.bilibili.com/x/web-interface/view?bvid={}"
    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"}
    response = requests.get(url.format(bv), headers=headers)
    data = json.loads(response.text)
    return data["data"]["aid"]

# 分词
def cut_words(comments):
    words = []
    for comment in comments:
        words += jieba.lcut(comment)
    return words

# 制作词云图
def make_wordcloud(words):
    text = " ".join(words)
    wc = WordCloud(background_color="white", max_words=200, font_path="msyh.ttc")
    wc.generate(text)
    plt.imshow(wc)
    plt.axis("off")
    plt.show()

if __name__ == "__main__":
    bv = input("请输入B站视频的BV号：")
    aid = get_bilibili_av(bv)
    comments = get_bilibili_comment(aid)
    words = cut_words(comments)
    make_wordcloud(words)

这样，我们就可以使用Python来抓取B站视频评论，并制作词云图了。