《请回答1988》弹幕分析

{
  "code": 0,
  "message": "0",
  "ttl": 1,
  "data": [
    {
      "cid": 166505309,
      "page": 1,
      "from": "vupload",
      "part": "请回答1988 P6修正",
      "duration": 4366,
      "vid": "",
      "weblink": "",
      "dimension": {
        "width": 1280,
        "height": 720,
        "rotate": 0
      }
    }
  ]
}

<i>
    <chatserver>chat.bilibili.com</chatserver>
    <chatid>166505309</chatid>
    <mission>0</mission>
    <maxlimit>8000</maxlimit>
    <state>0</state>
    <real_name>0</real_name>
    <source>e-r</source>
    <d p="3476.34000,1,25,16777215,1584938994,0,3db21a6b,30302178995863555">吸吸吸吸吸</d>
    <d p="1885.60400,1,25,16777215,1584939023,0,571b43d9,30302194189729799">这算什么交往哈哈哈哈</d>
    <d p="1919.24700,1,25,16777215,1584939057,0,571b43d9,30302211817865221">关二哥</d>
    <d p="1936.11400,1,25,16777215,1584939084,0,571b43d9,30302226084265987">化妆了</d>
    <d p="3444.53200,1,25,16777215,1584939135,0,c2a058d,30302253026902021">请务必这样做</d>
    <d p="4342.22900,1,25,16777215,1584939534,0,74eee2ec,30302461728653317">三连催更</d>
</i>

# 实现B站弹幕信息的解析和保存
import requests
import json
import chardet
import re


# 1.根据bvid获取cid
def get_cid():
    url = 'https://api.bilibili.com/x/player/pagelist?bvid=BV1g7411d7v7&jsonp=jsonp'
    # 获取url请求响应结果
    res_text = requests.get(url).text
    json_obj = json.loads(res_text)
    return json_obj['data'][0]['cid']


# 2.根据cid调用api，获取弹幕信息，并保存到txt数据文件中
def save_danm(cid):
    url = 'https://api.bilibili.com/x/v1/dm/list.so?oid=' + str(cid)
    res = requests.get(url)
    # 基于返回结果制定编码，避免乱码
    res.encoding = chardet.detect(res.content)['encoding']
    res_text = res.text
    # *?模式是将*的贪婪匹配修改为惰性匹配，也就按最小匹配模式
    pattern = re.compile('<d.*?>(.*?)</d>')
    dan_mu_list = pattern.findall(res_text)
    with open('../resources/dan_mu.txt', mode='w', encoding='utf-8') as f:
        for d in dan_mu_list:
            # 逐行写入弹幕
            f.write(d + '\n')
    print('dan_mu.txt done')


# 调用方法，获取cid
cid = get_cid()
# 调用方法，保存弹幕
save_danm(cid)

# 实现将弹幕生成为词云图
import pandas as pd
import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
from imageio import imread

# 读取文本文件，并进行分词
with open('resources/dan_mu.txt', encoding='utf-8') as f:
    txt = f.read()
# 将读取的内容，自动按行拆分为列表
txt_list = txt.split()
# 将每句弹幕进行分词
txt_cut = [jieba.lcut(x) for x in txt_list]
# 读取停用词表
with open('resources/stopwords.txt', encoding='utf-8') as f:
    stop_words = f.read()
stop_words = stop_words.split()

# 创建一维数组
s_txt_cut = pd.Series(txt_cut)
# 分词结果中去除停用词
txt_last = s_txt_cut.apply(lambda x: [i for i in x if i not in stop_words])

# 词频统计
txt_stat = []
for i in txt_last:
    txt_stat.extend(i)
txt_count = pd.Series(txt_stat).value_counts()

# 词云图绘制
back_img = imread(r"love.jpg")
wc_obj = WordCloud(font_path='resources/msyh.ttc', background_color='white', max_words=1800, mask=back_img,
                   max_font_size=200,
                   random_state=42)
wc_fit = wc_obj.fit_words(txt_count)

plt.figure(figsize=(16, 9))
plt.imshow(wc_fit)
plt.axis('off')
plt.show()
wc_obj.to_file('word_cloud_1988.png')

python -m ensurepip
python -m pip install -i https://pypi.tuna.tsinghua.edu.cn/simple pip -U