python之微信机器人

import itchat
import pandas as pd
itchat.auto_login(hotReload=True)
friends=itchat.get_friends(update=True)

def get_attr(friends,key):
    return list(map(lambda user:user.get(key),friends))

nickname=get_attr(friends,"NickName")
sex=get_attr(friends,"Sex")
province=get_attr(friends,"Province")
city=get_attr(friends,"City")
signature=get_attr(friends,"Signature")
data={'nickname':nickname,'sex':sex,'province':province,'city':city,'signature':signature}
data=pd.DataFrame(data,columns=['nickname','sex','province','city','signature'])

import matplotlib.pyplot as plt
import matplotlib as mpl
import seaborn as sns
from pyecharts import Map
sns.set(font='SimHei')
mpl.rcParams['font.sans-serif']=['SimHei']
sns.set_style('white')
sns.set_context('notebook')

data['sex']=data['sex'].apply(lambda x: 'male' if x==1 else ('female' if x==2 else 'unkknown'))
plt.figure(figsize=(10,10))
sns.countplot(x=data['sex'],palette = "pastel")
plt.show

注意重启服务器，大部分的报错就是服务器失联了！！！！

data['province']=data['province'].apply(lambda x:'unknown' if x=='' else x)
pro=data['province'].value_counts()
pro_map =Map('中国地图',title_color="#fff",title_pos='center',width=1200,height=600,background_color='#404a59')
pro_map.add('',pro.index,pro.values,is_label_show=True,is_visualmap=True,visual_text_color='#000')
pro_map.render('China attribute.html')



柱状图
plt.figure(figsize=(20,10))
sns.barplot(x=pro.index,y=pro.values,palette='Set2')
sns.set_xticklabels(pro.index,rotation=90)
plt.show

sc_data=data.query('province=="湖北"')
sc_data['city']=sc_data['city'].apply(lambda x:'unknown' if not x else x+'市')
sc=sc_data['city'].value_counts()
sc_map=Map('湖北',title_color="#fff",title_pos='center',width=1200,height=600,background_color='#404a59')
sc_map.add('',sc.index,sc.values,maptype='湖北',is_label_show=True,is_visualmap=True,visual_text_color='#000')
sc_map.render('湖北.html')

import jieba
import re
data['signature']=data['signature'].apply(lambda x:re.sub(re.compile(r"<span.*?</span>"),"emoji",x) if '<span' in x else x)
signature=''.join(data['signature'])
wordlist=jieba.cut(signature,cut_all=False)
#stopwords_chinese = [line.strip() for line in open ('stopwords_chinese.txt',encoding='UTF-8').readlines()]
stopwords_chinese = [line.strip() for line in open ('C:/Users/baihua/Desktop/ciyun.txt','r',encoding='utf-8').readlines()]

word_list=[]
for seg in wordlist:
    if seg not in stopwords_chinese:
        word_list.append(seg)

word_list=pd.DataFrame({'signature':word_list})
word_rank = word_list["signature"].value_counts()

from pyecharts import WordCloud
wordcloud_chinese=WordCloud(width=1500,height=820)
wordcloud_chinese.add("",word_rank.index[0:100],word_rank.values[0:100],word_size_range=[20,200],is_more_utils=True)
wordcloud_chinese.render("signature.html")

用python处理文本，处理数据显得特别重要！！！

 

关于词云核心代码和原理：http://python.jobbole.com/87496/

关于python处理txt文本：https://blog.csdn.net/J__Max/article/details/82810144