网易云热评词云
本帖最后由 大马强 于 2022-1-18 11:34 编辑这个程序去年就写好了，但由于学业问题以及一些bug，菜鸡的我到现在放假还没搞好{:5_107:}（用是还能用的）
程序功能实现：歌曲的获取，热评获取，词云生成，界面图形化
程序截图
https://static01.imgkr.com/temp/ebf54af793e14fcd808b21d4722d9a12.jpg
需要完善的地方
[*]歌曲只有20首，我在网页版搜索也是这样
[*]窗口大小改变，但生成的词云就不会按照我期望的大小改变
程序包含三个文件 wyy ,wc以及网易云热评词云
网易云热评词云代码
from tkinter import messagebox
from tkinter import *
from wyy import Wyy
from wc import *
class comment_wordcloud:
def __init__(self, root) -> None:
self.song_list = [] # 歌曲的名字
self.id_list = []
self.wc = None
self.photo = None
self.w = Wyy()
self.root = root
# 主窗口和主框架
self.cv = Canvas(self.root,background="gray")# 右边 词云显示地方
self.lf = LabelFrame(self.root, background="blue")# 左边输入框 按钮 歌曲列表
# 左上方输入框和两个按钮
self.lf1 = LabelFrame(self.lf, height=250, width=200)
self.e1 = Entry(self.lf1, width=27)
self.b1 = Button(self.lf1, text="获取信息", width=13,
command=self.get_song_list, cursor="hand2")# 获取歌曲
self.b2 = Button(self.lf1, text="生成词云", width=13,
command=self.get_hotcomment, cursor="hand2")# 获取歌曲
# 左下显示歌曲列表的地方
self.lf2 = LabelFrame(self.lf, height=250, width=200)
self.sb = Scrollbar(self.lf2)
self.lb = Listbox(self.lf2, yscrollcommand=self.sb,
height=450, width=200)
# 组件的摆放
self.show_widget()
# s刷新词云大小
self.root.bind("<Configure>", self.refresh)
def show_wordcloud(self):
self.cv.delete(ALL)
height_ = self.cv.winfo_height()
width_ = self.cv.winfo_width()
try:
self.wc = WC(width_, height_)
with open("content.txt", "r", encoding="utf-8") as fp:
content = fp.read()
self.photo
self.wc.to_file(content)
self.photo = PhotoImage(file="./wc.png")
self.cv.create_image(width_/2, height_/2,
anchor=CENTER, image=self.photo)
except:
pass
def get_song_list(self):
self.lb.delete(0, END)# 将上一次的数据清除
if(self.e1.get()):
self.song_list[:] = self.w.get_song_list(self.e1.get())
for name in self.song_list:
self.lb.insert(END, name["name"])
self.id_list.append(name["id"])
def get_hotcomment(self):
if (self.lb.curselection()):
# print(id_list)
index = self.lb.curselection()
param = self.id_list
comment_list = self.w.get_hotcomment(param)
if comment_list != -1:
if comment_list:
# 将数据写入一个文本文件中
with open("评论.txt", "w", encoding="utf-8") as fp:
for content in comment_list:
fp.write(content["content"])
self.show_wordcloud()
else:
messagebox.showerror(
title="粗错啦！", message="该歌曲是纯音乐,无歌词!", icon="info")
else:
messagebox.showerror(
title="粗错啦！", message="你被反爬了，休息下吧！", icon="info")
def refresh(self, event):# 窗口大小的改变
# a = event.height
# b = event.width
# print(self.cv.winfo_height(), self.cv.winfo_width())
height_ = self.root.winfo_height()
width_ = self.root.winfo_width()
print("当前", height_, width_)
print("上一次", self.cv_h, self.cv_w)
self.cv.place(x=200, y=0, width=width_-200, height=height_ - 10)
self.lf.place(x=0, y=0, width=200, height=height_)
print(abs(width_ - self.cv_w), abs(height_ - self.cv_h))
# 长宽改变超过一定数值才会改变，要不然太卡了
if self.photo and (abs(width_ - self.cv_w) > 25 or abs(height_ - self.cv_h) > 10):
self.cv_w = width_
self.cv_h = height_
self.show_wordcloud()
def show_widget(self):
self.cv_h = self.lf_h = 500
self.cv_w = 400
self.lf_w = 200
self.cv.place(x=200, y=0, height=self.cv_h, width=self.cv_w)
self.lf.place(x=0, y=0, height=self.cv_h, width=self.lf_w)
self.lf1.pack()
self.lf2.pack()
self.e1.grid(row=0, columnspan=2, pady=5)
self.b1.grid(row=1, column=0, sticky=W)
self.b2.grid(row=1, column=1, sticky=E)
self.sb.pack(side=RIGHT, fill=Y)
self.lb.pack()
if __name__ == "__main__":
root = Tk()
root.geometry("600x500")
cw = comment_wordcloud(root)
root.mainloop()
wyy代码
from Crypto.Cipher import AES
from base64 import b64encode
import requests
import json
class Wyy():
def __init__(self):
# 将加密的变量准备好
self.e = "010001"
self.d = "00e0b509f6259df8642dbc35662901477df22677ec152b5ff68ace615bb7b725152b3ab17a876aea8a5aa76d2e417629ec4ee341f56135fccf695280104e0312ecbda92557c93870114af6c9d05c4f7f0c3685b7a46bee255932575cce10b424d813cfe4875d3e82047b97ddef52741d546b8e289dc6935b3ece0462db0a22b8e7"
self.g = "0CoJUm6Qyw8W8jud"
self.i = "p6xB1rx37AU8O0KO"
self.song_list = ""
def get_encSeckey(self):
return "b742226290709f51abf9ad9a4e9136bd89036078368545a3f9a5ab938068d7a7be4d3f3fc2ea184090def069b85f75e4b443a43b1a872710c22ce983a3785fc074e799bd90d3e22a7a14d8a4864d647a72dc3a0de05a10ac61ef8114b631bf0079708ff79e0c2901ce0db1c26be78503550f65be6490ad08125ebf9744cc41cf"
# 补位
def to_16(self, data):
pd = 16 - len(data) % 16
data += chr(pd) * pd
return data
def enc_param(self, data, key):
iv = "0102030405060708"
# 创建一个AES加密器, 设置密钥，偏移量以及模式,前两者要为字符串格式
# AEs加密的数据格式一定是16的倍数，不到就用chr(x)补齐 格式为 "123456788chr(7)chr(7)"
data = self.to_16(data)
aes = AES.new(key=key.encode("utf-8"),
iv=iv.encode("utf-8"), mode=AES.MODE_CBC)
# 加密后返回结果为字节，但需要的是字符串，并且该返回不能被 utf-8 格式所识别，还需要借助其他的库将其转换
bs = aes.encrypt(data.encode("utf-8"))
return str(b64encode(bs), "utf-8")
def get_param(self, data):# 字典1是加密不了的，需要处理成字符串
# param 是经过两次加密的
first = self.enc_param(data, self.g)
second = self.enc_param(first, self.i)
return second
def requset_data(self, url, data):
req = requests.post(url, data={
"params": self.get_param(json.dumps(data)),
"encSecKey": self.get_encSeckey()
})
res = req
req.close()
return res
def get_hotcomment(self, data):
url = "https://music.163.com/weapi/comment/resource/comments/get?csrf_token="
self.data = {
"cursor": "-1",
"offset": "0",
"orderType": "1",
"pageNo": "1",
"pageSize": "20",
"rid": f"R_SO_4_{data}",
"threadId": f"R_SO_4_{data}"
}
req = self.requset_data(url, self.data)
if req.json()["code"] == -460:
return -1
else:
return req.json()["data"]["hotComments"]
def get_song_list(self, s):
url = "https://music.163.com/weapi/cloudsearch/get/web?csrf_token="
data = {
'csrf_token': "",
"hlposttag": "</span>",
"hlpretag": r'"<span class=\"s-fc7\">"',
"limit": "30",
"offset": "0",
"s": s,
"total": "true",
'type': "1"
}
req = self.requset_data(url, data)
self.song_list = req.json()["result"]["songs"]
return self.song_list
if __name__ == "__main__":
# pass
# 测试代码
w = Wyy()
wc代码
import wordcloud
import jieba
# 创建一个词云对象,并且设置相关属性
class WC():
def __init__(self, width_, height_):
self.wc = wordcloud.WordCloud(width=width_, height=height_,
background_color="white", font_path="msyh.ttc")
def to_file(self, data):
data = str(data)
# 将字符串用jieba处理
text = jieba.lcut(data)
text = " ".join(text)
self.wc.generate(text)
self.wc.to_file("wc.png")
求路过的到大佬看看{:9_220:} {:9_220:}
最后祝鱼油们新年快乐，快快乐乐过大年{:10_298:} {:10_288:}
感谢楼主 hornwong 发表于 2022-1-17 22:18
感谢楼主
{:10_297:} 厉害！ {:10_254:} {:10_254:} 可以的很厉害 {:5_95:} 牛牛牛！{:10_254:} 666
感谢楼主! {:10_254:}{:10_254:}{:10_254:} 666 太强了 {:5_106:}{:5_106:} {:10_254:} 厉害厉害 全世界特效最佳的Python教程 666
厉害
页:
[1]
2