not404

data["data"]["replies"][i=0-19]["content"]["message"]

file_path="res.csv"
df=pd.read_csv(file_path,encoding="gbk")

df.columns = ["word","frequency"]
print(df.head())
plt.bar(df["word"],df["frequency"])
plt.xlabel('词')
plt.ylabel('出现次数')
plt.show()

like.append(data["data"]["replies"][i]["like"])
level.append(data["data"]["replies"][i]["member"]["level_info"]["current_level"])
绘图
plt.bar(level,like)
plt.xlabel('用户等级')
plt.ylabel('点赞总数')

import requests,json
headerbili={
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)
AppleWebKit/537.36 
(KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36
Edg/100.0.1185.50",
"referer":"https://www.bilibili.com"
}

'''
next:页数
oid:视频av号
'''python
def get_json(page):
url="https://api.bilibili.com/x/v2/reply/main?jsonp=jsonp&next=%d&type=1&oid=13662970"
data = requests.get(url % page,
headers=headerbili).text.encode("utf8")
comm=json.loads(data)
print(comm)
'''
其中ensure_ascii用来规定返回值是否可以包含非ASCII码。
中文超过ASCII码范围，修改ensure_ascii参数值
'''
with open("./json/{}.json".format(page),"w" ,encoding='utf-8') as
f:
f.write(json.dumps(comm, ensure_ascii=False))

for i in range(100):#100页
get_json(i)
print(i,'n')


# vedioreg = 'class="tap-router">(.*?)</a>'
# aurllist = re.findall(vedioreg, rank, re.S | re.M)
# print(aurllist)

import json
import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif']=['SimHei']
*#用来正常显示中文标签
*plt.rcParams['axes.unicode_minus']=False #用来正常显示负号
#有中文出现的情况，需要u'内容'

like= []
level=[]
for e in range(100):
with open("./json/{}.json".format(e),"r",encoding="utf8") as f:
data=json.load(f)
for i in range(20):
like.append(data["data"]["replies"][i]["like"])
level.append(data["data"]["replies"][i]["member"]["level_info"]["current_level"])
print(like,level)
plt.bar(level,like)
plt.xlabel('用户等级')
plt.ylabel('点赞总数')
plt.show()

import json,csv

comment=[]*#评论列表
for e in range(100):
with open("./json/{}.json".format(e),"r",encoding="utf8") as f:
data=json.load(f)
for i in range(20):
comment.append(data["data"]["replies"][i]["content"]["message"])
with open("comment.txt","w",encoding="utf8") as fp:
writer = csv.writer(fp)
writer.writerow(comment)
print("写入", comment)#评论的txt文件

import jieba,re
*#去除标点
*def get_text(file_name):
with open(file_name, 'r', encoding='utf-8') as fr:
text = fr.read()
#删除的标点
del_ch = ['《','，','》','n','。','、','；','"',
'：',',','！','？',' ']
for ch in del_ch:
text = text.replace(ch,'')
return text


file_name = 'comment.txt'
text = get_text(file_name)
vlist = jieba.lcut(text)#调用jieba实现分词，返回列表

res_dict = {}
#进行词频统计
for i in vlist:
res_dict[i] = res_dict.get(i,0) + 1
res_list = list(res_dict.items())
#print(res_list)
#降序排序
res_list.sort(key = lambda x:x[1], reverse = True)
fin_res_list = []

#去除单个字的词
for item in res_list:
if(len(item[0])>=2):
fin_res_list.append(item)
word_list=[]
words=[]
for i in range(1000):
word,count = fin_res_list[i]
pstr = str(i+1) + ':'
word_list.append(word)
with open('ignore_dict.txt', 'r', encoding='utf-8') as f:
ignore_words = f.read().splitlines()
# 遍历分词
for word in word_list:
if word not in ignore_words:#排除词
word = re.sub(r'[n ]', '', word)
if len(word) < 1:
continue
words.append(word)
# print(pstr, end=' ')
# print(words[i], count)
with open("res.csv","a+")as fa:
fa.write(str(words[i])+","+str(count)+"n")

import pandas as pd
import matplotlib.pyplot as plt
import wordcloud,jieba

plt.rcParams['font.sans-serif']=['SimHei']
#用来正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #用来正常显示负号
#有中文出现的情况，需要u'内容'
#文件目录
file_path="res.csv"
df=pd.read_csv(file_path,encoding="gbk")
#柱状图
def _bar():
df.columns = ["word","frequency"]
print(df.head())
plt.bar(df["word"],df["frequency"])
plt.xlabel('词')
plt.ylabel('出现次数')
plt.show()
_bar()


#词云
with open("comment.txt","r",encoding="utf8")as f:
txt=f.read()
stopwords =
["的","了","我","时","在","你","看","到","没","不","就","是","人","也","有","和","会",
"一个","没有","时候","弹幕","自己","什么","时间","知道","就是","现在","真的","已经","还是","这个","看到","可以","因为"
,"你们","才能","不是","但是","那个","最后","每秒","所以","他们","觉得","怎么样","一样","可能","举报","这部","大家","不能","当时"
,"一直","一次","然后","还有","这样","评论","如果","那么","为什么","第一次","感谢","只是","这些","之后","忘记","一下","虽然","为了"
,"一定","今天","这么","不会","这里","去年","两个","以后","地方","那些","这种","怎么","其实","起来","应该","---","发生","只有","天气"
,"今年","很多","好像","所有","一部","出来","找到","之子","一遍","谢谢","告诉","东西","永远","的话","五块","一句","之前","过去","一年"
,"一天","终于","选择","对于","非常","突然"
]

w=wordcloud.WordCloud(background_color="white",font_path="msyh.ttc",height=600,width=800,stopwords=stopwords)
w.generate(" ".join(jieba.lcut(txt)))
w.to_file("词云.png")

一个 没有 没有 时候 弹幕 自己 什么 时间 知道 就是 现在 真的 已经 还是 看到 可以 因为 你们 才能 不是 但是 每秒 所以 他们 觉得 怎么样 一样 举报 这部 大家 不能 当时 一直 一次 然后 还有 这样 评论 如果 那么 为什么 第一次 感谢 只是 这些 之后 忘记 一下 虽然 为了 一定 今天 这么 不会 这里 去年 两个 以后 地方 那些 这种 怎么 其实 起来 应该 --- 发生 只有 天气 今年 很多 好像 所有 一部 出来 找到 之子 一遍 谢谢 告诉 东西 永远 的话 五块 一句 之前 过去 一年 一天 终于 选择 对于 非常 突然