Day 12

2 days left

Author: Gdong24

19100202/Gdong24/d12/__pycache__/d11_training1.cpython-37.pyc

@@ -0,0 +1,38 @@
+#import package 
+import requests
+import yagmail
+import getpass
+import stats_word
+from pyquery import PyQuery
+
+
+#设置发件人、登录密码、收件人
+sender = input('请输入发件人邮箱地址：')
+psw = input('请输入发件人邮箱登录密码：')
+recipient = input('请输入收件人邮箱地址：')
+smtp = 'smtp.qq.com'
+
+#获取微信公众号文章   
+response = requests.get('https://mp.weixin.qq.com/s/pLmuGoc4bZrMNl7MSoWgiA')
+
+#提取微信公众号正文
+document = PyQuery (response.text)
+content = document ('#js_content').text() 
+#print(content)
+
+#[email protected]
+
+#Day8内容，尝试引用
+try:
+    print('前100的中文词频统计结果： ', stats_word.stats_text_cn(content))  #没有英文，直接调用的中文统计
+except:
+    print("对象不是字符串类型！")
+
+# 统计前100词频
+statList = stats_word.stats_text_cn(content)
+statString = ''.join(str(i) for i in statList)
+print(statString)
+
+#将统计结果发送到 
+#yagmail.SMTP(sender,psw,smtp).send(recipient,'19100202 gdong',statString)  
+

19100202/Gdong24/d12/__pycache__/stats_word.cpython-37.pyc

@@ -0,0 +1,21 @@
+import stats_word
+import requests
+from pyquery import PyQuery
+from wxpy import *
+
+def main():
+    bot = Bot()     #扫描二维码登陆微信
+    my_friend = bot.friends() #回复对象为所有好友
+
+    @bot.register(msg_types=SHARING) #监听好友分享的消息
+    def auto_reply(msg):
+        response = requests.get(msg.url) # 分享网页msg.url 
+		document = PyQuery(response.text)
+		content = document('#js_content').text()  #d11 
+        result = stats_word.stats_text_cn(content,count=100)
+        return result   #将结果返回给好友
+
+    embed() #
+
+if __name__=='__main__':
+    main()

19100202/Gdong24/d12/d11_training1.py

@@ -0,0 +1,27 @@
+#引用package
+import jieba
+import collections 
+from collections import Counter 
+import re
+
+
+#中文词频排序
+def stats_text_cn(text2):
+    #建立列表 local varialbe 
+    cut_list = []
+    word_list = []
+    count_list = []
+    
+    cn_pattern = re.compile(r'[\u4e00-\u9fa5]')
+    text_cn = re.findall(cn_pattern, text2)
+    
+    text_cut = ''.join(text_cn)                      #把筛选返回的list转为str
+    
+    cut_list = jieba.cut(text_cut,cut_all=False)    #使用jieba精准模式分词
+    
+    for word in cut_list:                            #筛选大于等于2字的词
+        if len(word) >= 2:
+            word_list.append(word)
+    #用counter优化输出(day9)
+    count_list = Counter(word_list).most_common(100)
+    return count_list