【1901010161】自学训练营学习2群 Day13 ##6184

exercises/1901010161/1001S02E03_calculator.py

@@ -7,13 +7,9 @@ def calculate():
 /  for division
 ''')
 
-#<<<<<<< master
+# <<<<<<< master
     number_1 = float(input('Please enter the first number: '))
     number_2 = float(input('Please enter the second number: '))
-#=======
-    number_1 = int(input('Please enter the first number: '))
-    number_2 = int(input('Please enter the second number: '))
-#>>>>>>> master
 
     if operation == '+':
         print('{} + {} = '.format(number_1, number_2))

exercises/1901010161/README.md

@@ -0,0 +1,3 @@
+    ���������˵�14��������ʱ���ܽ�һ���Լ���ѧϰ����ˡ�
+    ���ʼ��Python��һ����֪�����ڵ�һ֪��⣬���ʼ��װ��Ҫ���ںü������ص����ڶԸ������и��ֳ���Python��ѧϰ�ܹ�������������һ���ȡ��뵱������py�ļ�����֪��Ӧ����ô�����������ٶ��ڸ������ʶ�����ôİ���ˡ�����������У���л��λ��������飬�������̾��˽��������Һܶ�ָ����Ҳ���������˲������ġ���������ܶ�д����ÿ����ҵ֮�󡣻�ͷ��ȥ������ܿ����Լ��ijɳ���
+    �Ժ��һ�����ʵ�ʳ������ñ�̴����������ı仯��

exercises/1901010161/d11/00.py

@@ -0,0 +1,36 @@
+import requests
+import getpass
+import yagmail
+from pyquery import PyQuery as py
+from mymodule import stats_word
+
+reponse = requests.get('https://mp.weixin.qq.com/s/pLmuGoc4bZrMNl7MSoWgiA')   # 网页请求
+web_text = reponse.text    # 保存更多网页文本数据
+document = py(web_text)
+content = document('#js_content').text()
+print('content=', content)
+
+w_list = stats_word.stats_text_cn(content, 100)
+w_list = str(w_list)
+print(w_list)
+
+sender = input("请输入发件人邮箱:")
+password = getpass.getpass("输入发件人邮箱授权码:")
+
+yagmail.register(sender, password)
+
+yag = yagmail.SMTP(sender, password, host='smtp.qq.com')
+yag.send('pythoncamp@163.com', '【1901010161】自学训练营学习2群DAY11 Zezhou-Sun', w_list)
+print("发送成功")
+
+'''
+countlist_str = ''.join(str(i) for i in countlist)
+print(countlist_str)
+# Use getpass to enter the email address related information
+import getpass
+recipients = input('pythoncamp@163.com') ##'Enter the email address of the reciever:'
+# Leverage yagmail to send out emai
+import yagmail
+yag = yagmail.SMTP(user=sender, password=password, host='smtp.qq.com')
+yag.send(recipients, '【1901010161】自学训练营学习2群DAY11 Zezhou-Sun', countlist_str)
+'''

exercises/1901010161/d11/1111.code-workspace

@@ -0,0 +1,8 @@
+{
+	"folders": [
+		{
+			"path": "D:\\用户目录\\我的文档\\GitHub\\selfteaching-python-camp\\exercises\\1901010161"
+		}
+	],
+	"settings": {}
+}

exercises/1901010161/d11/main.py

@@ -0,0 +1,12 @@
+from mymodule import stats_word
+
+path = r'd:\用户目录\我的文档\GitHub\selfteaching-python-camp\exercises\1901010161\d11\mymodule\tang300.json'
+with open(path, 'r', encoding='UTF-8') as f:     # byte编码的类型名称是 UTF-8
+
+    read_date = f.read()
+
+
+try:
+    print('出现频率最高的前20个词： \n', stats_word.stats_text_cn(read_date, 20))
+except ValueError:
+    print('ValueError:type of argument is not string!')

exercises/1901010161/d11/mymodule/stats_word.py

@@ -0,0 +1,35 @@
+import re    # 调用正则表达式
+import collections
+import jieba
+count = int()
+
+
+def stats_text_en(text, count):  # 定义英语文本统计函数
+    if type(text) == str:
+        m = re.sub(r'[^A-Za-z]', ' ', text)    # 将text中任意非字母成分替换为空
+        stri = m.split()        # 切分英文单词，建立字符串
+        return(collections.Counter(stri).most_common(count))
+    else:
+        raise ValueError('type of argument is not string')
+
+
+def stats_text_cn(text, count):     # 定义中文文本统计函数
+    if type(text) == str:
+        p = re.compile(r'[\u4e00-\u9fa5]')    # 中文基本汉字（20902字）的编码范围是：\u4e00到\u9fa5
+        res = re.findall(p, text)   # 获取所有中文字符
+        str1 = "".join(res)
+        str2 = jieba.lcut(str1)     # 结巴分词
+        text1 = []
+        for i in str2:
+            if len(i) >= 2:
+                text1.append(i)
+        return(collections.Counter(text1).most_common(count))
+    else:
+        raise ValueError('type of argument is not string')
+
+
+def stats_text(text, count):     # 定义文本统计函数
+    if type(text) == str:
+        return(stats_text_en(text, count) + stats_text_cn(text, count))    # 输出合并英文和中文词频统计结果
+    else:
+        raise ValueError('type of argument is not string')

exercises/1901010161/d12/00.py

@@ -0,0 +1,36 @@
+import requests
+import getpass
+import yagmail
+from pyquery import PyQuery as py
+from mymodule import stats_word
+
+reponse = requests.get('https://mp.weixin.qq.com/s/pLmuGoc4bZrMNl7MSoWgiA')   # 网页请求
+web_text = reponse.text    # 保存更多网页文本数据
+document = py(web_text)
+content = document('#js_content').text()
+print('content=', content)
+
+w_list = stats_word.stats_text_cn(content, 100)
+w_list = str(w_list)
+print(w_list)
+
+sender = input("请输入发件人邮箱:")
+password = getpass.getpass("输入发件人邮箱授权码:")
+
+yagmail.register(sender, password)
+
+yag = yagmail.SMTP(sender, password, host='smtp.qq.com')
+yag.send('pythoncamp@163.com', '【1901010161】自学训练营学习2群DAY11 Zezhou-Sun', w_list)
+print("发送成功")
+
+'''
+countlist_str = ''.join(str(i) for i in countlist)
+print(countlist_str)
+# Use getpass to enter the email address related information
+import getpass
+recipients = input('pythoncamp@163.com') ##'Enter the email address of the reciever:'
+# Leverage yagmail to send out emai
+import yagmail
+yag = yagmail.SMTP(user=sender, password=password, host='smtp.qq.com')
+yag.send(recipients, '【1901010161】自学训练营学习2群DAY11 Zezhou-Sun', countlist_str)
+'''

exercises/1901010161/d12/1111.code-workspace

@@ -0,0 +1,8 @@
+{
+	"folders": [
+		{
+			"path": "D:\\用户目录\\我的文档\\GitHub\\selfteaching-python-camp\\exercises\\1901010161"
+		}
+	],
+	"settings": {}
+}

exercises/1901010161/d12/main.py

@@ -0,0 +1,31 @@
+from mymodule import stats_word
+from wxpy import Bot, Message, embed
+from pyquery import PyQuery
+import requests
+
+bot = Bot()   # 初始化机器人，扫码登录
+my_friend = bot.friends().search('闫')[0]    # 查找好友
+my_friend.send('分享任意微信文章给我')   # 发生文本给好友
+
+# 监听消息
+# 回复好友消息
+@bot.register(my_friend)
+def reply_my_friend(msg):
+    if msg.type == 'Sharing':
+        response = requests.get(msg.url)
+        document = PyQuery(response.text)
+        content = document('#js_content').text()
+        reply = stats_word.stats_text_cn(content, 100)
+    return reply
+embed()
+
+
+path = r'd:\用户目录\我的文档\GitHub\selfteaching-python-camp\exercises\1901010161\d11\mymodule\tang300.json'
+with open(path, 'r', encoding='UTF-8') as f:     # byte编码的类型名称是 UTF-8
+    read_date = f.read()
+
+
+try:
+    print('出现频率最高的前20个词： \n', stats_word.stats_text_cn(read_date, 20))
+except ValueError:
+    print('ValueError:type of argument is not string!')

exercises/1901010161/d12/mymodule/stats_word.py

@@ -0,0 +1,35 @@
+import re    # 调用正则表达式
+import collections
+import jieba
+count = int()
+
+
+def stats_text_en(text, count):  # 定义英语文本统计函数
+    if type(text) == str:
+        m = re.sub(r'[^A-Za-z]', ' ', text)    # 将text中任意非字母成分替换为空
+        stri = m.split()        # 切分英文单词，建立字符串
+        return(collections.Counter(stri).most_common(count))
+    else:
+        raise ValueError('type of argument is not string')
+
+
+def stats_text_cn(text, count):     # 定义中文文本统计函数
+    if type(text) == str:
+        p = re.compile(r'[\u4e00-\u9fa5]')    # 中文基本汉字（20902字）的编码范围是：\u4e00到\u9fa5
+        res = re.findall(p, text)   # 获取所有中文字符
+        str1 = "".join(res)
+        str2 = jieba.lcut(str1)     # 结巴分词
+        text1 = []
+        for i in str2:
+            if len(i) >= 2:
+                text1.append(i)
+        return(collections.Counter(text1).most_common(count))
+    else:
+        raise ValueError('type of argument is not string')
+
+
+def stats_text(text, count):     # 定义文本统计函数
+    if type(text) == str:
+        return(stats_text_en(text, count) + stats_text_cn(text, count))    # 输出合并英文和中文词频统计结果
+    else:
+        raise ValueError('type of argument is not string')

exercises/1901010161/d13/1111.code-workspace

@@ -0,0 +1,8 @@
+{
+	"folders": [
+		{
+			"path": "D:\\用户目录\\我的文档\\GitHub\\selfteaching-python-camp\\exercises\\1901010161"
+		}
+	],
+	"settings": {}
+}

exercises/1901010161/d13/main.py

@@ -0,0 +1,29 @@
+import numpy as np
+from mymodule import stats_word
+from pyquery import PyQuery as py
+import requests
+import matplotlib.pyplot as plt
+
+reponse = requests.get('https://mp.weixin.qq.com/s/_oFklhozwgz_1QnB_pLioA')   # 网页请求
+web_text = reponse.text    # 保存更多网页文本数据
+document = py(web_text)
+content = document('#js_content').text()
+
+w_list = stats_word.stats_text_cn(content, 10)
+w_list = dict(w_list)
+# group_data = list(w_list.values())
+group_data = tuple(w_list.values())
+group_names = list(w_list.keys())
+# plt.rcdefaults()
+fig, ax = plt.subplots()  # 建立一个figure对象，建立一个axis对象
+y_pos = np.arange(len(group_names))
+ax.barh(y_pos, group_data, align='center')
+ax.set_yticks(y_pos)
+ax.set_yticklabels(group_names)
+ax.invert_yaxis()
+ax.set_xlabel('词频')
+ax.set_title('网页中TOP10中文词语')
+plt.show()
+
+# plt.savefig(r'wordsCnt.jpeg')  #保存图片
+# msg.reply_image(r'wordsCnt.jpeg')  #回复图片

exercises/1901010161/d13/mymodule/stats_word.py

@@ -0,0 +1,35 @@
+import re    # 调用正则表达式
+import collections
+import jieba
+count = int()
+
+
+def stats_text_en(text, count):  # 定义英语文本统计函数
+    if type(text) == str:
+        m = re.sub(r'[^A-Za-z]', ' ', text)    # 将text中任意非字母成分替换为空
+        stri = m.split()        # 切分英文单词，建立字符串
+        return(collections.Counter(stri).most_common(count))
+    else:
+        raise ValueError('type of argument is not string')
+
+
+def stats_text_cn(text, count):     # 定义中文文本统计函数
+    if type(text) == str:
+        p = re.compile(r'[\u4e00-\u9fa5]')    # 中文基本汉字（20902字）的编码范围是：\u4e00到\u9fa5
+        res = re.findall(p, text)   # 获取所有中文字符
+        str1 = "".join(res)
+        str2 = jieba.lcut(str1)     # 结巴分词
+        text1 = []
+        for i in str2:
+            if len(i) >= 2:
+                text1.append(i)
+        return(collections.Counter(text1).most_common(count))
+    else:
+        raise ValueError('type of argument is not string')
+
+
+def stats_text(text, count):     # 定义文本统计函数
+    if type(text) == str:
+        return(stats_text_en(text, count) + stats_text_cn(text, count))    # 输出合并英文和中文词频统计结果
+    else:
+        raise ValueError('type of argument is not string')

exercises/1901010161/main.py

@@ -0,0 +1,65 @@
+# 导入模块
+from pylab import *
+import matplotlib.pyplot as plt
+import numpy as np
+from wxpy import *
+import yagmail
+import requests
+from pyquery import PyQuery
+import getpass
+import logging
+from mymodule import stats_word
+
+# 安装依赖包 requests yagmail pyquery lxml
+# pip install -i https://pypi.tuna.tsinghua.edu.cn/simple requests yagmail pyquery lxml
+
+logging.basicConfig(format='file:%(filename)s|line:%(lineno)s|message:%(message)s',level=logging.DEBUG)
+
+# 通过 requests.get 获得 URL网页的文章，存入 response  并返回
+def get_article(url):
+    response = requests.get(url)
+    document = PyQuery(response.text)
+    return document('#js_content').text()
+
+def main():
+
+        # 初始化机器人，扫码登陆
+        bot = Bot()
+
+        # 搜索好友
+        my_friends = bot.friends().search('金融家')[0]
+
+        # 监听 my_friend 的分享的消息，并获得分享消息的 链接
+        @bot.register(chats=my_friends)
+        def proc(msg):
+            try:
+                logging.info('sharing url - %s', msg.url)
+                article = get_article(msg.url)
+                count = 10
+                result = stats_word.stats_text_cn(article, count)  # 调 stats_text_cn ，将所汉字及频次记录 result
+
+                group_data = list(result.values())
+                group_names = list(result.keys())
+
+                y_pos = np.arange(len(group_names))
+
+                plt.rcdefaults()
+                fig, ax = plt.subplots()
+                plt.rcParams['font.sans-serif']=['SimHei'] 
+                ax.barh(y_pos, group_data, align='center')
+                ax.set_yticks(y_pos)
+                ax.set_yticklabels(group_names)
+                ax.invert_yaxis()
+                ax.set_xlabel('词频')
+                ax.set_title('网页中TOP10中文词语') 
+                plt.savefig(r'wordsCnt.jpeg')
+                msg.reply_image(r'wordsCnt.jpeg')
+
+            except Exception as e:
+                logging.exception(e)
+
+        # 进入 Python 命令行、让程序保持运行         
+        embed() 
+
+if __name__ == '__main__':
+    main()