1、导入工具包
import itchat
import re
import jieba
import matplotlib.pyplot as plt
from wordcloud import WordCloud
from wordcloud import ImageColorGenerator
import numpy as np
import pandas as pd
import PIL.Image as Image
from os import path
import os
import random
from pyecharts import Pie
import csv
from pyecharts import Geo
from collections import Counter
from pyecharts import Line, Bar, Pie, EffectScatter
import PIL.Image as Image
from pyecharts import Map, Geo
from snownlp import SnowNLP
2、微信登录
itchat.auto_login(hotReload=True)#三行代码实现登录,为了避免频繁扫描二维码登录，加入hotReload=True
itchat.dump_login_status()
friends = itchat.get_friends(update=True)[:]#好友信息获取
3、处理数据，获取所需字段
def get_info():
nickNames = []
remarkNames = []
sexs = []
signatures = []
provinces = []
citys = []
usernames = []
for i in friends:
nickName = i['NickName'].strip().replace('span', '').replace('class', '').replace('emoji', '').replace('\n', '').replace('\"', '').replace('🤣', '') # 去除无用字符
remarkName = i['RemarkName'].strip().replace('span', '').replace('class', '').replace('emoji', '').replace('\n', '').replace('\"', '').replace('🤣', '') # 去除无用字符
sex = i['Sex']
signature = i['Signature'].strip().replace('span', '').replace('class', '').replace('emoji', '').replace('\n', '').replace('\"', '').replace('\t', '').replace('', '').replace("1f60a", " ").replace("1f497", " ").replace("1f31f", " ") # 去除无用字符
rep = re.compile("1f\d+\w*|[<>/=]")
signature = rep.sub('', signature)
province = i['Province']
city = i['City']
userName=i['UserName']
nickNames.append(nickName)
remarkNames.append(remarkName)
sexs.append(sex)
signatures.append(signature)
provinces.append(province)
citys.append(city)
usernames.append(userName)
return zip(nickNames, remarkNames, sexs, signatures, provinces, citys ,usernames)
def get_data():
datas =[]
data = get_info()
for a,b,c,d,e,f,g in data:
info = {}
info['昵称'] = a
info['备注名称'] = b
info['性别'] = c
info['个性签名'] = d
info['省份'] = e
info['城市'] = f
info['用户名']= g
datas.append(info)
return datas
4、存储数据到csv文件
def write2csv(datas):
print('正在保存数据')
with open('wechat-zyh.csv', 'a', newline='', encoding='utf-8-sig') as f: # 文件默认保存在项目所在的目录
fieldnames = ['昵称', '备注名称', '性别', '个性签名', '省份', '城市','用户名'] # 控制列的顺序
writer = csv.DictWriter(f, fieldnames=fieldnames)
writer.writeheader()
writer.writerows(datas)
print("微信好友信息保存成功")
datas = get_data()
write2csv(datas) # 调用函数保存 csv 文件
5、微信好友性别分析
male = female = other = 0
for i in datas:
sex = i['性别']
if sex == 1:
male += 1
elif sex == 2:
female += 1
else:
other += 1
gender = ['男', '女', '其他']
value = [male, female, other]
pie = Pie('微信好友性别比例饼图', '好友总人数：%d' % len(datas), title_pos='center')
pie.add('', gender, value, radius=[30, 75], rosetype='area', is_label_show=True ,is_legend_show=True, legend_top='bottom')
pie.render('./result/gender.html') # 在指定目录下生成一个 gender.html 的文件
#pie.show_config()
print('性别分析图完成')
微信好友性别比例饼图-2.png
6、微信好友头像获取
- 获取用户头像图片，并将头像图片依次存入img文件夹下
num = 0
for i in datas: # 根据userName获取头像
img = itchat.get_head_img(userName=i["用户名"])
imgFile = open("img/" + str(num) + ".jpg", "wb")
imgFile.write(img)
imgFile.close()
num += 1
7、绘制好友头像拼接
x = 0
y = 0
imgs = os.listdir("img")
random.shuffle(imgs)# random.shuffle(imgs)将图片顺序打乱，
total_img = Image.new('RGBA', (1000, 1000)) # 创建640*640的图片用于填充各小图片
width = int(np.math.sqrt(1000 * 1000 / len(imgs))) # math.sqrt()开平方根计算每张小图片的宽高，
row_num = int(1000 / width) # 每行图片数
for i in imgs:
try:
img = Image.open("img/" + i)
img = img.resize((width, width), Image.ANTIALIAS)# 缩小图片
total_img.paste(img, (x * width, y * width))# 拼接图片，一行排满，换行拼接
x += 1
if x >= row_num:
x = 0
y += 1
except IOError:
print("img/ %s can not open" % (i))
total_img.save("./result/头像拼接图.png")
头像拼接图.png
8、微信好友地区分布统计图
citys = []
for i in datas:
city = i['城市']
citys.append(city)
cityss = filter(None, citys)#去除列表中空白字符，有些微信好友没填城市信息
res = Counter(cityss)
for key1 in list(res.keys()):
if res.get(key1) < 5:
del res[key1]
key1 = list(res.keys())
value1 = list(res.values())
bar = Bar("微信好友分布图")
bar.add("地区分布图", key1, value1, is_more_utils=True, mark_line=["min", "max"],
xaxis_rotate=45, is_label_show=True)
#bar.show_config() # 打印输出图表的所有配置项
bar.render('./result/city.html') # 在指定目录下生成一个 city.html 的文件
print('微信好友地区分布图完成')
微信好友分布图.png
9、微信好友省份分布统计图
# 绘制微信好友地区分布图
provinces = []
for i in datas:
province = i['省份']
provinces.append(province)
provincess = filter(None, provinces)#去除列表中空白字符，有些微信好友没填城市信息
res = Counter(provincess)
for key2 in list(res.keys()):
if res.get(key2) < 3:
del res[key2]
key2 = list(res.keys())
value2 = list(res.values())
bar = Bar("微信好友分布图")
bar.add("地区分布图", key2, value2, is_more_utils=True, mark_line=["min", "max"],
xaxis_rotate=45, is_label_show=True)
#bar.show_config() # 打印输出图表的所有配置项
bar.render('./result/province.html') # 在指定目录下生成一个 city.html 的文件
print('微信好友省份分布图完成')
微信好友分布图.png
10、微信好友全国分布地图
provinces = []
for i in datas:
province = i['省份']
provinces.append(province)
provincess = filter(None, provinces)#去除列表中空白字符，有些微信好友没填城市信息
res = Counter(provincess)
province_keys=res.keys()
province_values=res.values()
map = Map("我的微信好友分布", "@ZhangYuhao",width=1200, height=600)
map.add("", province_keys, province_values, maptype='china', is_visualmap=True,visual_text_color='#000')
map.render(path="./result/china.html")
好友全国分布地图.png
11、微信好友北京区域分布地图
city_keys0= ['丰台区','东城区','大兴区', '海淀区', '西城区' , '朝阳区', '顺义区','平谷区','石景山区','昌平区','密云区','房山区','延庆区','门头沟区','通州区']
city_values0= [52, 20, 31, 57, 22, 49,5,5,2,5,1,5,3,2,1]
map2 = Map("北京地图",'北京', width=1200, height=600)
map2.add('北京', city_keys0, city_values0, visual_range=[1, 10], maptype='北京', is_visualmap=True, visual_text_color='#000')
#map2.show_config()
map2.render(path="./result/beijing.html")
好友北京分布地图.png
12、绘制微信昵称词云图
nicklist = []
for j in datas:
nickname = j['昵称']
rep = re.compile("1f\d+\w*|[<>/=]")
nickname = rep.sub('', nickname)
nicklist.append(nickname)
text = "".join(nicklist)
cut = jieba.cut(text, cut_all=True) # 分词
word = ",".join(cut)
coloring = np.array(Image.open("./temp2.png")) # 电脑中自定义词云的图片
my_wordcloud = WordCloud(background_color="white", max_words=3000, max_font_size=200,
mask=coloring, random_state=100, font_path='./font/simhei.ttf',
scale=2).generate(word) # 定义词云背景图颜色、尺寸、字体大小、电脑中字体选择,random_state 为每个单词返回一个PIL颜色
image_colors = ImageColorGenerator(coloring)
plt.imshow(my_wordcloud.recolor(color_func=image_colors)) # 绘图颜色
plt.imshow(my_wordcloud) # 绘图内容
plt.axis("off")
plt.show() # 显示图
#pwd_path = os.path.abspath(os.path.dirname(os.getcwd()))
#desc_full = os.path.join(pwd_path, 'res')
#my_wordcloud.to_file(path.join(desc_full, 'nickname.png'))
my_wordcloud.to_file('./result/昵称.jpg')
print('昵称词云图完成')
13、绘制个性签名词云图
signlist = []
for k in datas:
signature = k['个性签名']
rep = re.compile("1f\d+\w*|[<>/=]")
signature = rep.sub('', signature)
signlist.append(signature)
text = "".join(signlist)
cut = jieba.cut(text, cut_all=True) # 分词
word = ",".join(cut)
coloring = np.array(Image.open("./temp2.png")) # 电脑中自定义词云的背景图片，需要事先自己准备好
my_wordcloud = WordCloud(background_color="white", max_words=3000, max_font_size=200,
mask=coloring, random_state=100, font_path='./font/simhei.ttf',
scale=2).generate(word) # 定义词云背景图颜色、尺寸、字体大小、电脑中字体选择,random_state 为每个单词返回一个PIL颜色
image_colors = ImageColorGenerator(coloring)
plt.imshow(my_wordcloud.recolor(color_func=image_colors)) # 绘图颜色
plt.imshow(my_wordcloud) # 绘图内容
plt.axis("off")
plt.show() # 显示图
my_wordcloud.to_file('./result/个性签名.jpg')
print('个性签名词云图完成')
个性签名1.jpg
个性签名2.jpg
个性签名3.jpg
个性签名4.jpg
个性签名5.jpg
14、个性签名情感分析
sentimentslist = []
for li in signlist:
if len(li) > 0:
s = SnowNLP(li)
print(li, s.sentiments)
sentimentslist.append(s.sentiments)
fig1 = plt.figure("sentiment")
plt.hist(sentimentslist, bins=np.arange(0, 1, 0.02))
plt.savefig('./result/好友签名情感分析.jpg')
plt.show()
好友签名情感分析.jpg
