0426

import re

import jieba as jieba
import pandas as pd
from wxpy import  *

#初始化，扫码登录
bot = Bot()

#获取好友
my_friends = bot.friends()
print(type(my_friends))

# 使用一个字典统计好友男性和女性的数量
sex_dict = {'male': 0, 'female': 0}

for friend in my_friends:
    # 统计性别
    if friend.sex == 1:
        sex_dict['male'] += 1
    elif friend.sex == 2:
        sex_dict['female'] += 1

print(sex_dict)

# 使用一个字典统计各省好友数量
province_dict = {'北京': 0, '上海': 0, '天津': 0, '重庆': 0,
    '河北': 0, '山西': 0, '吉林': 0, '辽宁': 0, '黑龙江': 0,
    '陕西': 0, '甘肃': 0, '青海': 0, '山东': 0, '福建': 0,
    '浙江': 0, '台湾': 0, '河南': 0, '湖北': 0, '湖南': 0,
    '江西': 0, '江苏': 0, '安徽': 0, '广东': 0, '海南': 0,
    '四川': 0, '贵州': 0, '云南': 0,
    '内蒙古': 0, '新疆': 0, '宁夏': 0, '广西': 0, '西藏': 0,
    '香港': 0, '澳门': 0}

# 统计省份
for friend in my_friends:
    if friend.province in province_dict.keys():
        province_dict[friend.province] += 1

# 为了方便数据的呈现，生成JSON Array格式数据
data = []
for key, value in province_dict.items():
    data.append({'name': key, 'value': value})

print(data)

def write_txt_file(path, txt):
    '''
    写入txt文本
    '''
    with open(path, 'a', encoding='gb18030', newline='') as f:
        f.write(txt)

# 统计签名
for friend in my_friends:
    # 对数据进行清洗，将标点符号等对词频统计造成影响的因素剔除
    pattern = re.compile(r'[一-龥]+')
    filterdata = re.findall(pattern, friend.signature)
    write_txt_file('signatures.txt', ''.join(filterdata))



def read_txt_file(path):
    '''
    读取txt文本
    '''
    with open(path, 'r', encoding='gb18030', newline='') as f:
        return f.read()

content = read_txt_file(txt_filename)
segment = jieba.lcut(content)
words_df=pd.DataFrame({'segment':segment})

stopwords=pd.read_csv("stopwords.txt",index_col=False,quoting=3,sep=" ",names=['stopword'],encoding='utf-8')
words_df=words_df[~words_df.segment.isin(stopwords.stopword)]


import numpy

words_stat = words_df.groupby(by=['segment'])['segment'].agg({"计数":numpy.size})
    words_stat = words_stat.reset_index().sort_values(by=["计数"],ascending=False)

from scipy.misc import imread
from wordcloud import WordCloud, ImageColorGenerator


# 设置词云属性
color_mask = imread('background.jfif')
wordcloud = WordCloud(font_path="simhei.ttf",   # 设置字体可以显示中文
                background_color="white",       # 背景颜色
                max_words=100,                  # 词云显示的最大词数
                mask=color_mask,                # 设置背景图片
                max_font_size=100,              # 字体最大值
                random_state=42,
                width=1000, height=860, margin=2,# 设置图片默认的大小,但是如果使用背景图片的话,                                                   # 那么保存的图片大小将会按照其大小保存,margin为词语边缘距离
                )

# 生成词云, 可以用generate输入全部文本,也可以我们计算好词频后使用generate_from_frequencies函数
word_frequence = {x[0]:x[1]for x in words_stat.head(100).values}
print(word_frequence)
word_frequence_dict = {}
for key in word_frequence:
    word_frequence_dict[key] = word_frequence[key]

wordcloud.generate_from_frequencies(word_frequence_dict)
# 从背景图片生成颜色值
image_colors = ImageColorGenerator(color_mask)
# 重新上色
wordcloud.recolor(color_func=image_colors)
# 保存图片
wordcloud.to_file('output.png')
plt.imshow(wordcloud)
plt.axis("off")
plt.show()

 

import re
import requests
from bs4 import BeautifulSoup
from datetime import datetime
import time
import random
import pandas as pd


def clickCounts(url):
    id = re.findall('\d+',url)[-1]
    clickUrl = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(id)
    clickStruct = requests.get(clickUrl).text
    clickCounts = int(clickStruct.split('.html')[-1][2:-3])
    return clickCounts

def newsdt(showInfo):
    newsDate = showInfo.split()[0].split(':')[1]
    newsTime = showInfo.split()[1]
    newsDT = newsDate + ' ' + newsTime
    dt = datetime.strptime(newsDT,'%Y-%m-%d %H:%M:%S')
    return dt



anews(url):
    newsDetail = {}
    res = requests.get(url)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text,'html.parser')
    newsDetail['newsTitle'] = soup.select('.show-title')[0].text
    showInfo = soup.select('.show-info')[0].text
    newsDetail['newsDT'] = newsdt(showInfo)
    newsDetail['newsClick'] = clickCounts(url)
    return newsDetail

newsUrl = "http://news.gzcc.cn/html/2019/xiaoyuanxinwen_0404/11155.html"
print(anews(newsUrl))



def alist(listUrl):
    res = requests.get(listUrl)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text,'html.parser')
    newsList = []
    for news in soup.select('li'):
        if len(news.select('.news-list-title'))>0:
            newsUrl = news.select('a')[0]['href']
            newsDesc = news.select('.news-list-description')[0].text
            newsDict = anews(newsUrl)
            newsDict['newsUrl'] = newsUrl
            newsDict['description'] = newsDesc
            newsList.append(newsDict)
    return newsList


listUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
allnews = alist(listUrl)
for newtro in allnews:
    print(newtro)

allnews = []
for i in range(2,12):
    listUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    allnews.extend(alist(listUrl))


for n in allnews:
    print(n)
#统计所爬取的新闻总数
print(len(allnews))



import sqlite3
with sqlite3.connect('gzccnewsdb.sqlite') as db:
    newsdf.to_sql('gzccnews',con=db)


with sqlite3.connect('gzccnewsdb.sqlite') as db:
    df2 = pd.read_sql_query('SELECT * FROM gzccnewsdb',con=db)
df2

 

import sqlite3
with sqlite3.connect('gzccnewsdb.sqlite') as db:
    newsdf.to_sql('gzccnews',con=db)

with sqlite3.connect('gzccnewsdb.sqlite') as db:
    df2 = pd.read_sql_query('SELECT * FROM gzccnews',con=db)
df2


!pip install PyMySQL

!pip install sqlalchemy