爬取B站评论并进行词云图显示

1.在首页选取一个视频，检查网页源代码，查看评论所处的位置

这里爬取B站视频下面的用户昵称，性别，签名，内容，发布时间，归属地等信息

import requests
import datetime
import csv

url = 'https://api.bilibili.com/x/v2/reply/wbi/main?oid=919114382&type=1&mode=3&pagination_str=%7B%22offset%22:%22%22%7D&plat=1&seek_rpid=&web_location=1315875&w_rid=662e6cfa6de007f47971504fdd7361fb&wts=1701617200'
if __name__ == '__main__':
    #创建保存文件以及相关配置
    f = open('data.csv',mode='a',encoding='utf-8',newline='')
    csv_writer = csv.DictWriter(f,fieldnames=[
            '昵称',
            '性别',
            '签名',
            '内容',
            '发布时间',
            '归属地',
    ])
    csv_writer.writeheader()

    headers={
        'Cookie':#浏览器中的cookie
        'Referer':'https://www.bilibili.com/video/BV16N411u76v/?spm_id_from=333.1007.top_right_bar_window_history.content.click&vd_source=1702d37bb5ca4b1f33292dd3a16bb428',
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0'
    }

    response = requests.get(url=url,headers=headers)
    json_data = response.json()
    for index in json_data['data']['replies']:
        try:
        #发布时间
            date = str(datetime.datetime.fromtimestamp(index['ctime']))
            dit={
                '昵称':index['member']['uname'],
                '性别':index['member']['sex'],
                '签名':index['member']['sign'],
                '内容': index['content']['message'],
                '发布时间':date,
                '归属地':index['reply_control']['location'].replace('IP属地：',''),
            }
            csv_writer.writerow(dit)
            print(dit)
        except:
            pass

结果保存为csv文件，查看文件内容所示

进行词云图显示，这里只选取评论部分，保存为txt文件

import jieba
import collections
import re
from pyecharts.charts import WordCloud
from pyecharts.globals import SymbolType
from pyecharts import options as opts
from pyecharts.globals import ThemeType, CurrentConfig

#打开爬取的评论数据
with open('data.txt') as f:
    data = f.read()
  # 文本预处理
new_data = re.findall('[\u4e00-\u9fa5]+', data, re.S)  # 只要字符串中的中文
new_data = " ".join(new_data)

# 文本分词--精确模式分词
seg_list_exact = jieba.cut(new_data, cut_all=True)

result_list = []
with open('stop_words.txt', encoding='utf-8') as f:
    con = f.readlines()
    stop_words = set()
    for i in con:
        i = i.replace("\n", "")  # 去掉读取每一行数据的\n
        stop_words.add(i)

for word in seg_list_exact:
    # 设置停用词并去除单个词
    if word not in stop_words and len(word) > 1:
        result_list.append(word)
print(result_list)
# 筛选后统计
word_counts = collections.Counter(result_list)
# 获取前100最高频的词
word_counts_top100 = word_counts.most_common(100)
# 可以打印出来看看统计的词频
print(word_counts_top100)

word1 = WordCloud(init_opts=opts.InitOpts(width='1350px', height='750px', theme=ThemeType.MACARONS))
word1.add('词频', data_pair=word_counts_top100,
          word_size_range=[15, 108], textstyle_opts=opts.TextStyleOpts(font_family='cursive'),
          shape=SymbolType.DIAMOND)
word1.set_global_opts(title_opts=opts.TitleOpts('评论词云图'),
                      toolbox_opts=opts.ToolboxOpts(is_show=True, orient='vertical'),
                      tooltip_opts=opts.TooltipOpts(is_show=True, background_color='red', border_color='yellow'))
word1.render("评论词云图.html")

输出结果