1901100296 自学训练营学习20群 DAY13

exercises/1901100296/d11/main.py

@@ -1,17 +1,41 @@
 from mymodule import stats_word
 import getpass
 import yagmail
+import requests
+import logging
+from pyquery import PyQuery
 
-def postemail(content,title):
+# 获取网页内容
+def get_content(url):
+    # 请求网页返回内容
+    response = requests.get(url)
+    # 提取微信公众号正⽂
+    document = PyQuery(response.text) 
+    content = document('#js_content').text()
+    return content
+# 发邮件
+def post_email(content,title):
     sender = input('输⼊发件⼈邮箱:')
     password = getpass.getpass('输⼊发件⼈邮箱密码(可复制粘贴):') 
     recipients = input('输⼊收件⼈邮箱:')
-    yag = yagmail.SMTP(sender,password)
+    # yag = yagmail.SMTP(sender,password)
+    # yag = yagmail.SMTP(sender,password,'smtp.163.com')
+    yag = yagmail.SMTP(sender,password,'smtp.qq.com')
     yag.send(recipients,title,content)
 
+def main():
+    logging.basicConfig(format='file:%(filename)s|line:%(lineno)d|message:%(message)s',level=logging.DEBUG)
+    try:
+        url='https://mp.weixin.qq.com/s/pLmuGoc4bZrMNl7MSoWgiA'
+        content = stats_word.stats_text_cn(get_content(url),100)
+        # content = '测试！！'
+        # print('统计结果：',content)
+        # logging.info('%s %s',type(content),str(content))
+        post_email(content,'1901100296 自学训练营学习20群DAY11')
+        logging.info('已发送，请注意查收！')
+    except Exception as e:
+        logging.exception(e)
+
 if __name__ == '__main__':
-    url='https://mp.weixin.qq.com/s/pLmuGoc4bZrMNl7MSoWgiA'
-    content = stats_word.stats_text_cn(stats_word.getcontent(url),100)
-    # print('统计结果：',content)
-    postemail(content,'统计结果')
+    main()
 

exercises/1901100296/d11/mymodule/stats_word.py

@@ -1,19 +1,7 @@
 import collections
 import jieba
-import requests
-import yagmail
-import json
-from pyquery import PyQuery
-
-# 获取网页内容
-def getcontent(url):
-    # 请求网页返回内容
-    response = requests.get(url)
-    # 提取微信公众号正⽂
-    document = PyQuery(response.text) 
-    content = document('#js_content').text()
-    return content
 
+import json
 
 # 封装统计汉字词频的函数
 def stats_text_cn(text,count):
@@ -28,6 +16,9 @@ def stats_text_cn(text,count):
             words.append(word)
     # 使用标准库的Counter统计词和词频数，返回前count位的数据
     cnt_words = collections.Counter(words).most_common(count)
+
+    # res_words = str(cnt_words)
+
     res_words=''
     for r in cnt_words:
         a,b = r

exercises/1901100296/d12/main.py

@@ -2,45 +2,27 @@
 import getpass
 import yagmail
 from wxpy import *
-# import wxpy
 
 
-def postemail(content,title):
-    sender = input('输⼊发件⼈邮箱:')
-    password = getpass.getpass('输⼊发件⼈邮箱密码(可复制粘贴):') 
-    recipients = input('输⼊收件⼈邮箱:')
-    yag = yagmail.SMTP(sender,password)
-    yag.send(recipients,title,content)
+logging.basicConfig(format='file:%(filename)s|line:%(lineno)d|message:%(message:%(message)s',level=logging.DEBUG)
+def main():
+    # 初始化机器人，扫码登录
+    bot = Bot()
+    # 找到好友和群聊
+    my_friends = bot.friends()
+    # family_group = bot.groups()
 
+    # 监听好友信息，自动响应分享类型的消息
+    @bot.register(my_friends,SHARING)
+    def handler(msg):
+        try:
+            logging.info('sharing url=%s',msg.url)
+            result = stats_word.stats_text_cn(stats_word.getcontent(msg.url),100)
+            msg.reply(str(result))
+        except Exception as e:
+            logging.exception(e)
+    embed()
+if __name__ == '__main__':
+    main()
 
-# 初始化机器人，扫码登录
-bot = Bot()
-# 找到好友和群聊
-my_friend = bot.friends().search('老运')[0]
-# family_group = bot.groups().search('家人')[0]
-
-# 发送消息给好友
-my_friend.send('hello!')
-# my_friend.send_image('1.jpg')
-# 自动响应消息
-# 打印消息
-@bot.register()
-def just_print(msg):
-    print(msg)
-# 取得消息内容的URL
-@bot.register()
-def get_url(msg):
-    if msg.type == SHARING:
-        content = stats_word.stats_text_cn(stats_word.getcontent(msg.url),100)
-        # 回复好友消息
-        @bot.register(my_friend)
-        def reply_my_friend():
-            return '处理结果：{}'.format(content)
-
-embed()
-# if __name__ == '__main__':
-    # url='https://mp.weixin.qq.com/s/pLmuGoc4bZrMNl7MSoWgiA'
-    # content = stats_word.stats_text_cn(stats_word.getcontent(url),100)
-    # print('统计结果：',content)
-    # postemail(content,'统计结果')
 

exercises/1901100296/d12/mymodule/stats_word.py

@@ -28,11 +28,6 @@ def stats_text_cn(text,count):
             words.append(word)
     # 使用标准库的Counter统计词和词频数，返回前count位的数据
     cnt_words = collections.Counter(words).most_common(count)
-    res_words=''
-    for r in cnt_words:
-        a,b = r
-        w = a + ':' +str(b)
-        # print(w)
-        res_words = res_words + '\n' + w
-
-    return res_words
+
+    return cnt_words
+

exercises/1901100296/d13/main.py

@@ -0,0 +1,52 @@
+from mymodule import stats_word
+import getpass
+import yagmail
+from wxpy import *
+import  matplotlib.pyplot as plt
+import matplotlib
+import numpy as np
+from os import path
+
+logging.basicConfig(format='file:%(filename)s|line:%(lineno)d|message:%(message:%(message)s',level=logging.DEBUG)
+
+file_path = path.join(path.dirname(path.abspath(__file__)),'SimHei.ttf')
+
+# 将统计结果画成条形图并返回条形图的保存路径
+def stats_barplot(list_data):
+    zhfont1 = matplotlib.font_manager.FontProperties(fname=file_path)
+
+    words = [x[0] for x in list_data ]
+    frequence = [x[1] for x in list_data]
+
+    fig,ax = plt.subplots()
+    ax.barh(words,frequence)
+    ylabels = ax.get_yticklabels()
+    plt.setp(ylabels,FontProperties=zhfont1)
+    ax.set_xlabel('词频',FontProperties=zhfont1)
+    ax.set_ylabel('词语',FontProperties=zhfont1)
+    ax.set_title('文章中出现次数在前10的词语',FontProperties=zhfont1)
+    png_path = path.join(path.dirname(path.abspath(__file__)),'stats_words_barplot.png')
+    fig.savefig(png_path,transparen=False,dpi=80,bbox_inches="tight")
+    # plt.show()
+    return png_path
+
+def main():
+    # 初始化机器人，扫码登录
+    bot = Bot()
+    # 找到好友和群聊
+    my_friends = bot.friends()
+    # family_group = bot.groups()
+
+    # 监听好友信息，自动响应分享类型的消息
+    @bot.register(my_friends,SHARING)
+    def handler(msg):
+        try:
+            logging.info('sharing url=%s',msg.url)
+            msg.reply(stats_barplot(result))
+        except Exception as e:
+            logging.exception(e)
+    embed()
+
+if __name__ == '__main__':
+    main()
+

exercises/1901100296/d13/mymodule/stats_word.py

@@ -0,0 +1,31 @@
+import collections
+import jieba
+import requests
+import yagmail
+import json
+from pyquery import PyQuery
+
+# 获取网页内容
+def getcontent(url):
+    # 请求网页返回内容
+    response = requests.get(url)
+    # 提取微信公众号正⽂
+    document = PyQuery(response.text) 
+    content = document('#js_content').text()
+    return content
+
+
+# 封装统计汉字词频的函数
+def stats_text_cn(text,count):
+    if type(text)!=str:
+        raise ValueError('输入类型 %s,参数必须是 str 类型'%type(text))
+    # 使用jieba分词
+    seg_words = jieba.cut(text)
+    # 长度大于等于2的词
+    words = []
+    for word in seg_words:
+        if len(word) >= 2:
+            words.append(word)
+    # 使用标准库的Counter统计词和词频数，返回前count位的数据
+    cnt_words = collections.Counter(words).most_common(count)   
+    return cnt_words