Python作业8

Python作业8

实现一个动态排行榜和词云

import requests
from bs4 import BeautifulSoup
import json
import re
import time
import jieba
from _collections import OrderedDict
import matplotlib.pyplot as plt
import matplotlib.animation as animation
import numpy
import wordcloud


USER_AGENT={'user-agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1'}


def GetData():
    print("正在爬取 https://www.tiobe.com/tiobe-index/")
    #发送请求，获取数据
    text = requests.get('https://www.tiobe.com/tiobe-index/',headers=USER_AGENT).text
    #获取总的全部数据
    total_content = ''.join(re.findall(r'series:(.*?)\}\);',text,re.DOTALL))
    #获取每种编程语言的数据
    total_content = re.findall(r'({.*?})',total_content,re.DOTALL)
    print(total_content)
    datas=[]
    for k,content in enumerate(total_content):
        #print(content)
        name = ''.join(re.findall(r"{name : '(.*?)'",content,re.DOTALL))
        if name=='Assembly language':
            name='R'
        if name=='Visual Basic':
            name='VB'
        if name=='JavaScript':
            name='JS'
        #print(name)
        data = re.findall(r"\[Date.UTC(.*?)\]",content,re.DOTALL)
        #print(data)
        for i in data:
            i = i.replace(' ','')
            i = re.sub(r'[()]','',i)
            value = i.split(',')[-1]
            #print("value"+value)
            data_list= i.split(',')[:3]
            time = ''
            for  index,j in enumerate(data_list):
                if index!=0:
                    if len(j)==1:
                        j = '0' + j

            datas.append({
                'name':name,
                'data':data_list,
                'value':value
            })
    print("爬取成功，数据处理成功")
    return datas

def sort_key(old_dict,reverse=False):
    keys = sorted(old_dict.keys(),reverse=reverse)
    new_dict = OrderedDict()
    for key in keys:
        new_dict[key] = old_dict
    return new_dict

if __name__ == "__main__":
    datas = []
    month_list = []
    datas = GetData()
    names=['Java','C++','SQL','PHP','R','JS','VB','C','Python','C#']
    for i in datas:
        i['data'] = i['data'][0] + '.' + i['data'][1] + '.' + i['data'][2]
    for i in datas:
        if(i['name']=='Java'):
            #print(i['data'])
            month_list.append(i['data'])

    #print(month_list)
    per_month_lan_dict={i:{j:0 for j in names} for i in month_list}
    #print(per_month_lan_dict)
    for month in month_list:
        for lan in names:
            for i in datas:
                if i['name']==lan and i['data']==month:
                    per_month_lan_dict[month][lan]=i['value']
    #print(per_month_lan_dict)

    colors = ['plum','darkorange','lightgreen','yellow','salmon','aqiamarine','dodgerblue','pink','b','darkviolet']
    color_dict = {'C#':'plum','Python':'darkorange','C++':'lightgreen','C':'yellow','Java':'salmon','VB':'aquamarine','JS':'dodgerblue','R':'pink','PHP':'b','SQL':'darkviolet'}

    plt.gca()
    for data_item in per_month_lan_dict:
        plt.cla()
        temp = sorted(per_month_lan_dict[data_item].items(), key=lambda item: float(item[1]))
        #print(temp)
        x = [item[0] for item in temp]
        #print(x)
        color = [color_dict[i] for i in x]
        y = [float(item[1]) for item in temp]
        #print(y)

        plt.barh(range(1, 11), y, color=color)
        plt.title(data_item, fontsize=24)

        plt.yticks(range(1, 11), list(x), fontproperties='simhei', fontsize=16)
        plt.xticks(range(0, 30, 100))
        for x, y in zip(range(1, 11), y):
            plt.text(y + 0.1, x - 0.1, str(y))
        plt.pause(0.001)
    plt.show()

    # 词云
    plt.figure()
    text = ''
    for i in per_month_lan_dict['2021.4.2'].items():
        for k in range(1,round(float(i[1]))):
            text=text+' '+i[0]
    #print(text)
    w=wordcloud.WordCloud()
    w.generate(text)
    plt.imshow(w)
    plt.show()