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('Word')
plt.ylabel('Frequency')
plt.show()

like.append(data["data"]["replies"][i]["like"])
level.append(data["data"]["replies"][i]["member"]["level_info"]["current_level"])
# Plotting
plt.bar(level,like)
plt.xlabel('User Level')
plt.ylabel('Total Likes')

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: page number
oid: video av number
'''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)
'''
Where ensure_ascii is used to specify whether the return value can contain non-ASCII codes.
Chinese characters exceed the ASCII range, modify the ensure_ascii parameter value.
'''
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 pages
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']
# To display Chinese labels normally
plt.rcParams['axes.unicode_minus']=False # To display negative signs normally
# In cases where Chinese appears, use u'content'

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('User Level')
plt.ylabel('Total Likes')
plt.show()

import json,csv

comment=[] # Comment list
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("Written", comment) # Comments in txt file

import jieba,re
# Remove punctuation
def get_text(file_name):
with open(file_name, 'r', encoding='utf-8') as fr:
text = fr.read()
# Deleted punctuation
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) # Call Jieba for word segmentation, return list

res_dict = {}
# Perform word frequency statistics
for i in vlist:
res_dict[i] = res_dict.get(i,0) + 1
res_list = list(res_dict.items())
#print(res_list)
# Sort in descending order
res_list.sort(key = lambda x:x[1], reverse = True)
fin_res_list = []

# Remove single character words
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()
# Iterate through segmented words
for word in word_list:
if word not in ignore_words: # Exclude words
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']
# To display Chinese labels normally
plt.rcParams['axes.unicode_minus']=False # To display negative signs normally
# In cases where Chinese appears, use u'content'
# File path
file_path="res.csv"
df=pd.read_csv(file_path,encoding="gbk")
# Bar chart
def _bar():
df.columns = ["word","frequency"]
print(df.head())
plt.bar(df["word"],df["frequency"])
plt.xlabel('Word')
plt.ylabel('Frequency')
plt.show()
_bar()

# Word cloud
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("word_cloud.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