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('詞')
plt.ylabel('出現次數')
plt.show()

like.append(data["data"]["replies"][i]["like"])
level.append(data["data"]["replies"][i]["member"]["level_info"]["current_level"])
繪圖
plt.bar(level,like)
plt.xlabel('用戶等級')
plt.ylabel('點讚總數')

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:頁數
oid:視頻av號
'''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用來規定返回值是否可以包含非ASCII碼。
中文超過ASCII碼範圍，修改ensure_ascii參數值
'''
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頁
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']
*#用來正常顯示中文標籤
*plt.rcParams['axes.unicode_minus']=False #用來正常顯示負號
#有中文出現的情況，需要u'內容'

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('用戶等級')
plt.ylabel('點讚總數')
plt.show()

import json,csv

comment=[]*#評論列表
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("寫入", comment)#評論的txt文件

import jieba,re
*#去除標點
*def get_text(file_name):
with open(file_name, 'r', encoding='utf-8') as fr:
text = fr.read()
#刪除的標點
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)#調用jieba實現分詞，返回列表

res_dict = {}
#進行詞頻統計
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 = []

#去除單個字的詞
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()
# 遍歷分詞
for word in word_list:
if word not in ignore_words:#排除詞
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']
#用來正常顯示中文標籤
plt.rcParams['axes.unicode_minus']=False #用來正常顯示負號
#有中文出現的情況，需要u'內容'
#文件目錄
file_path="res.csv"
df=pd.read_csv(file_path,encoding="gbk")
#柱狀圖
def _bar():
df.columns = ["word","frequency"]
print(df.head())
plt.bar(df["word"],df["frequency"])
plt.xlabel('詞')
plt.ylabel('出現次數')
plt.show()
_bar()


#詞雲
with open("comment.txt","r",encoding="utf8")as f:
txt=f.read()
stopwords =
["的","了","我","時","在","你","看","到","沒","不","就","是","人","也","有","和","會",
"一個","沒有","時候","彈幕","自己","什麼","時間","知道","就是","現在","真的","已經","還是","這個","看到","可以","因為"
,"你們","才能","不是","但是","那個","最後","每秒","所以","他們","覺得","怎麼樣","一樣","舉報","這部","大家","不能","當時"
,"一直","一次","然後","還有","這樣","評論","如果","那麼","為什麼","第一次","感謝","只是","這些","之後","忘記","一下","雖然","為了"
,"一定","今天","這麼","不會","這裡","去年","兩個","以後","地方","那些","這種","怎麼","其實","起來","應該","---","發生","只有","天氣"
,"今年","很多","好像","所有","一部","出來","找到","之子","一遍","謝謝","告訴","東西","永遠","的話","五塊","一句","之前","過去","一年"
,"一天","終於","選擇","對於","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("詞雲.png")

一個 沒有 沒有 時候 彈幕 自己 什麼 時間 知道 就是 現在 真的 已經 還是 看到 可以 因為 你們 才能 不是 但是 每秒 所以 他們 覺得 怎麼樣 一樣 舉報 這部 大家 不能 當時 一直 一次 然後 還有 這樣 評論 如果 那麼 為什麼 第一次 感謝 只是 這些 之後 忘記 一下 雖然 為了 一定 今天 這麼 不會 這裡 去年 兩個 以後 地方 那些 這種 怎麼 其實 起來 應該 --- 發生 只有 天氣 今年 很多 好像 所有 一部 出來 找到 之子 一遍 謝謝 告訴 東西 永遠 的話 五塊 一句 之前 過去 一年 一天 終於 選擇 對於 非常 突然