【1901100092】自学训练营学习15群DAY12

exercises/1901100092/d11/main.py

@@ -0,0 +1,27 @@
+from mymodule import stats_word
+from pyquery import PyQuery
+import requests
+import getpass
+import yagmail
+
+def load_file():
+
+    response = requests.get(url = 'https://mp.weixin.qq.com/s/pLmuGoc4bZrMNl7MSoWgiA')
+
+    document = PyQuery(response.text)
+    content = document('#js_content').text()
+    return content
+
+#text=1                  #验证参数检查功能是否生效
+try:
+    i = stats_word.stats_text_cn(load_file())
+    print(i)
+except ValueError:
+    print('stats_text参数应为字符串类型')
+
+sender = input('输入发件人邮箱：')
+password_1 = getpass.getpass('输入发件人邮箱密码：')
+recipients = input('输入收件人邮箱：')
+
+yag = yagmail.SMTP(user = sender,password = password_1,host = 'smtp.qq.com')
+yag.send(to = recipients,subject = "【1901100092】自学训练营学习15群DAY11 Yui",contents = str(i))

exercises/1901100092/d11/mymodule/stats_word.py

@@ -0,0 +1,90 @@
+text = '''
+The Zen of Python, by Tim Peters
+Beautiful is better than ugly.
+Explicit is better than implicit.
+Simple is better than complex.
+Complex is better than complicated.
+Flat is better than nested.
+Sparse is better than dense.
+Readability counts.
+Special cases aren't special enough to break the rules.
+Although practicality beats purity.
+Errors should never pass silently.
+Unless explicitly silenced.
+In the face of ambxiguity, refuse the temptation to guess.
+There should be one-- and preferably only one --obvious way to do it.
+Although that way may not be obvious at first unless you're Dutch.
+Now is better than never.
+Although never is often better than *right* now.
+If the implementation is hard to explain, it's a bad idea.
+If the implementation is easy to explain, it may be a good idea.
+Namespaces are one honking great idea -- let's do more of those!
+
+美丽总比丑陋好
+显式比隐式好
+简单总比复杂好
+复杂总比复杂好
+平的比嵌套的好
+稀疏总比密集好
+可读性
+特殊情况还不足以打破规则
+虽然实用性胜过纯洁性
+错误不应该悄无声息地过去
+除非显式地沉默
+面对敏锐，拒绝猜测的诱惑
+应该有一种——而且最好只有一种——显而易见的方法来做到这一点
+不过，除非你是荷兰人，否则这种方式一开始可能并不明显
+现在总比不做好
+虽然从来没有比“现在”更好
+如果实现很难解释，这是一个坏主意
+如果实现很容易解释，这可能是一个好主意
+名称空间是一个很棒的主意——让我们做更多这样的事情
+'''
+import jieba
+import collections 
+
+
+def stats_text_en(text):
+    if not isinstance(text,str):
+        raise ValueError('参数应为字符串类型')
+
+    elements=text.split()   #整理字符
+    words=[]                #建立列表
+    symbols=',.*-!'
+    for element in elements:
+            for symbol in symbols:
+                element=element.replace(symbol,'')   #清理符号
+            if len(element) and element.isascii():
+                words.append(element)                #将字符加入words列表
+
+    l_en = collections.Counter(words).most_common(100) 
+    return l_en
+
+def stats_text_cn(text):
+    if not isinstance(text,str):
+        raise ValueError('参数应为字符串类型')
+
+    seg_list = jieba.cut(text,cut_all=False)
+
+    cn_characters = []  #建立一个空列表，为下一个循环使用
+    for i in seg_list:
+        if '\u4e00' <= i <= '\u9fff' and len(i) >= 2:
+            cn_characters.append(i)
+
+    l_en_cn = collections.Counter(cn_characters).most_common(100) 
+    return l_en_cn
+
+
+
+def stats_text(text):
+    '''输出合并词频统计结果'''
+    if not isinstance(text,str):
+        raise ValueError('参数应为字符串类型')
+
+    return stats_text_en(text) + stats_text_cn(text)
+
+if __name__ =='__main__':
+    print(stats_text(text))
+
+
+

exercises/1901100092/d12/main.py

@@ -0,0 +1,17 @@
+from mymodule import stats_word
+from pyquery import PyQuery
+import requests
+import getpass
+from wxpy import *
+
+bot = Bot(cache_path = True)
+friend = bot.friends()
+@bot.register(friend,SHARING)
+def load_file(msg):
+    response = requests.get(url = msg.url)
+
+    document = PyQuery(response.text)
+    content = document('#js_content').text()
+    i = str(stats_word.stats_text_cn(content))
+    msg.reply(i)
+embed()

exercises/1901100092/d12/mymodule/stats_word.py

@@ -0,0 +1,90 @@
+text = '''
+The Zen of Python, by Tim Peters
+Beautiful is better than ugly.
+Explicit is better than implicit.
+Simple is better than complex.
+Complex is better than complicated.
+Flat is better than nested.
+Sparse is better than dense.
+Readability counts.
+Special cases aren't special enough to break the rules.
+Although practicality beats purity.
+Errors should never pass silently.
+Unless explicitly silenced.
+In the face of ambxiguity, refuse the temptation to guess.
+There should be one-- and preferably only one --obvious way to do it.
+Although that way may not be obvious at first unless you're Dutch.
+Now is better than never.
+Although never is often better than *right* now.
+If the implementation is hard to explain, it's a bad idea.
+If the implementation is easy to explain, it may be a good idea.
+Namespaces are one honking great idea -- let's do more of those!
+
+美丽总比丑陋好
+显式比隐式好
+简单总比复杂好
+复杂总比复杂好
+平的比嵌套的好
+稀疏总比密集好
+可读性
+特殊情况还不足以打破规则
+虽然实用性胜过纯洁性
+错误不应该悄无声息地过去
+除非显式地沉默
+面对敏锐，拒绝猜测的诱惑
+应该有一种——而且最好只有一种——显而易见的方法来做到这一点
+不过，除非你是荷兰人，否则这种方式一开始可能并不明显
+现在总比不做好
+虽然从来没有比“现在”更好
+如果实现很难解释，这是一个坏主意
+如果实现很容易解释，这可能是一个好主意
+名称空间是一个很棒的主意——让我们做更多这样的事情
+'''
+import jieba
+import collections 
+
+
+def stats_text_en(text):
+    if not isinstance(text,str):
+        raise ValueError('参数应为字符串类型')
+
+    elements=text.split()   #整理字符
+    words=[]                #建立列表
+    symbols=',.*-!'
+    for element in elements:
+            for symbol in symbols:
+                element=element.replace(symbol,'')   #清理符号
+            if len(element) and element.isascii():
+                words.append(element)                #将字符加入words列表
+
+    l_en = collections.Counter(words).most_common(100) 
+    return l_en
+
+def stats_text_cn(text):
+    if not isinstance(text,str):
+        raise ValueError('参数应为字符串类型')
+
+    seg_list = jieba.cut(text,cut_all=False)
+
+    cn_characters = []  #建立一个空列表，为下一个循环使用
+    for i in seg_list:
+        if '\u4e00' <= i <= '\u9fff' and len(i) >= 2:
+            cn_characters.append(i)
+
+    l_en_cn = collections.Counter(cn_characters).most_common(100) 
+    return l_en_cn
+
+
+
+def stats_text(text):
+    '''输出合并词频统计结果'''
+    if not isinstance(text,str):
+        raise ValueError('参数应为字符串类型')
+
+    return stats_text_en(text) + stats_text_cn(text)
+
+if __name__ =='__main__':
+    print(stats_text(text))
+
+
+