1 newsdf = pd.read_csv(r\'C:\Users\Czc\PycharmProjects\news.csv\')
 2 
 3 import sqlite3
 4 \'\'\'
 5 with sqlite3.connect(\'gzccnewsdb.sqlite\') as db:
 6     newsdf.to_sql(\'gzccnews\',con = db)
 7 \'\'\'
 8 with sqlite3.connect(\'gzccnewsdb.sqlite\') as db:
 9     df2 = pd.read_sql_query(\'SELECT * FROM gzccnews\',con=db)
10 
11 
12 import pymysql
13 from sqlalchemy import create_engine
14 coninfo = "mysql+pymysql://root:@localhost:3306/gzccnews?charset=utf8"
15 engine = create_engine(coninfo,encoding="utf-8")
16 
17 newsdf.to_sql(name=\'news\',con=engine,if_exists=\'append\',index= False,index_label=\'id\')

  1 # -*- coding: utf-8 -*-
  2 
  3 import numpy as np
  4 import itchat
  5 import matplotlib.pyplot as plt
  6 # 登录微信，会弹出二维码，用手机微信扫一扫即可登录
  7 itchat.login()
  8 # 获取好友的所有数据
  9 friends = itchat.get_friends(update=True)[0:]
 10 
 11 # ***-----统计好友性别比例-----***
 12 # 初始化计数器
 13 male = female = other = 0
 14 # friends[0]是自己的信息，因此从friends[1]开始
 15 for i in friends[1:]:
 16     sex = i[\'Sex\']
 17     if sex == 1:
 18         male += 1
 19     elif sex == 2:
 20         female += 1
 21     else:
 22         other += 1
 23 # 计算朋友总数
 24 total = len(friends[1:])
 25 # 打印输出好友性别比例
 26 print(
 27     "男性好友: %.2f%%" % (float(male)/total * 100) + "\n" +
 28     "女性好友: %.2f%%" % (float(female)/total * 100) + "\n" +
 29     "不明性别好友: %.2f%%" % (float(other)/total * 100)
 30     )
 31 
 32 
 33 # 进行绘图
 34 label_name = ["Boy", "Girl", "Unknown"]
 35 gender_list = [male, female, other]
 36 plt.figure()
 37 plt.bar(range(len(gender_list)), gender_list, tick_label=label_name)
 38 
 39 # 绘图中文显示设置
 40 plt.rcParams[\'font.sans-serif\']=[\'SimHei\']
 41 plt.rcParams[\'axes.unicode_minus\']=False
 42 
 43 plt.xlabel(u\'性别\')
 44 plt.ylabel(u\'人数\')
 45 plt.title(u\'好友性别比例\')
 46 
 47 # 在柱状图上显示数字
 48 x=np.arange(3)
 49 y=np.array(gender_list)
 50 for a,b in zip(x,y):
 51     plt.text(a, b+0.1, \'%.2f\' % b, ha=\'center\', va= \'bottom\',fontsize=12)
 52 
 53 
 54 # ***-----获取各类信息-----***
 55 # 定义函数，爬取所有好友的指定信息
 56 def get_var(var):
 57     variable = []
 58     for i in friends[1:]:
 59         value = i[var]
 60         variable.append(value)
 61     return variable
 62 
 63 # 调用函数，得到对应信息，并存入csv文件，保存到桌面
 64 NickName = get_var("NickName")
 65 Sex = get_var("Sex")
 66 Province = get_var("Province")
 67 City = get_var("City")
 68 Signature = get_var("Signature")
 69 
 70 # Excel 打开中文乱码问题 未解决
 71 # 不过可以通过Excel->数据->文本导入的形式，将csv文件导入，就可以避免乱码问题
 72 from pandas import DataFrame
 73 
 74 data = {"NickName": NickName, "Sex": Sex, "Province": Province,
 75             "City": City, "Signature": Signature}
 76 frame = DataFrame(data)
 77 frame.to_csv(\'data.csv\', encoding=\'utf_8_sig\', index=True)
 78 
 79 # ***-----统计好友城市分布-----***
 80 city_dict = {}
 81 x_city = []
 82 y_city = []
 83 for city_name in City:
 84     if city_name in city_dict:
 85         city_dict[city_name] += 1
 86     else:
 87         city_dict[city_name] = 1
 88 city_list = sorted(city_dict.items(), key=lambda item:item[1], reverse=True)
 89 # 将前14个城市排序显示，去除排名第一的未知城市（城市信息为空的好友）
 90 for i in city_list[1:15]:
 91     x_city.append(i[0])
 92     y_city.append(i[1])
 93 plt.figure()
 94 plt.bar(range(len(x_city)), y_city, tick_label=x_city)
 95 plt.xlabel(u\'城市\')
 96 plt.ylabel(u\'人数\')
 97 plt.title(u\'好友城市分布\')
 98 # 在柱状图上显示数字
 99 x=np.arange(len(x_city))
100 y=np.array(y_city)
101 for a,b in zip(x,y):
102     plt.text(a, b+0.06, \'%.2f\' % b, ha=\'center\', va=\'bottom\', fontsize=9)
103 
104 # ***-----根据个性签名绘制词云图-----***
105 # 通过正则匹配清洗数据
106 import re
107 Signature_list = []
108 for i in friends:
109     signature = i["Signature"].strip().replace("span", "").replace("class", "").replace("emoji", "")
110     rep = re.compile("lf\d+\w*|[<>/=]")
111     signature = rep.sub("", signature)
112     Signature_list.append(signature)
113 text = "".join(Signature_list)
114 # 调包进行分词
115 import jieba
116 wordlist = jieba.cut(text, cut_all=False)
117 word_space_split = " ".join(wordlist)
118 # 调包进行词云图绘制
119 from wordcloud import WordCloud, ImageColorGenerator
120 import PIL.Image as Image
121 coloring = np.array(Image.open("czc.jpg"))
122 my_wordcloud = WordCloud(background_color="white", max_words=200,
123 mask=coloring, max_font_size=70, random_state=42, scale=2,
124 font_path="C:\Windows\Fonts\SimHei.ttf").generate(word_space_split)
125 image_colors = ImageColorGenerator(coloring)
126 plt.figure()
127 plt.imshow(my_wordcloud.recolor(color_func=image_colors))
128 plt.imshow(my_wordcloud)
129 plt.axis("off")
130 plt.show()