以词云图方式观察分析微信好友签名状况
一、环境
python 3.6.5
二、代码
# 导入wordcloud & matplotlib & itchat & re & np & image模块
from wordcloud import WordCloud,ImageColorGenerator
import matplotlib.pyplot as plt
import itchat,re,io,jieba
import numpy as np
from PIL import Image
#定义好友签名函数parse_signature()
def parse_signature():
# 网页端登陆
itchat.login()
siglist = []
# 获取所有好友信息
friends = itchat.get_friends(update=True)[1:]
# for 循环获取好友签名
for i in friends:
signature = i["Signature"].strip().replace("span","").replace("class","").replace("emoji","")
# 正则删掉一些冗余符号
rep = re.compile("1f\d+\w*|[<>/=]")
# 调用sub实现替换
signature = rep.sub("",signature)
siglist.append(signature)
# 得到text文本
text = "".join(siglist)
# 将得到的数据放入text.txt文本中
with io.open("text.txt","a",encoding="utf-8") as f:
# 通过jieba分词进行分词并通过空格分隔
wordlist = jieba.cut(text,cut_all=True)
word_space_split = "".join(wordlist)
f.write(word_space_split)
f.close()
# 调用parse_signature()函数,获取用户签名text文件
parse_signature()
# 定义词云制作函数
def draw_signature():
# 读取要生成词云的文件
text = open(u"text.txt",encoding="utf-8").read()
# 读入背景图片(提前准备好!)
coloring = np.array(Image.open("timg.jpg"))
# 对签名文件jieba
wordlist_after_jieba = jieba.cut(text, cut_all=True)
# 将jieba后的文件组合到wl_space_split中
wl_space_split = " ".join(wordlist_after_jieba)
# 实例化对象
my_wordcloud = WordCloud(background_color="white", #背景颜色
max_words=2000, #最大词数
mask=coloring, #设置背景图片
max_font_size=40, #显示字体最大值
random_state=42, #设置有多少种随机生成状态(有多少种配色方案)
scale=2, #比例
font_path="Droid Sans Fallback.ttf").generate(wl_space_split) #选择字体解决口字形问题
# 根据图片生成词云相应颜色
image_colors = ImageColorGenerator(coloring)
my_wordcloud.recolor(color_func=image_colors)
#显示图片
plt.imshow(my_wordcloud.recolor(color_func=image_colors))
plt.axis("off")
plt.show()
# 调用draw_signature()函数,显示微信好友签名词云
draw_signature()
三、效果图