【1901010132】自学训练营学习2群 DAY11

exercises/1901010132/day10/main.py

@@ -0,0 +1,9 @@
+from mymodule import stats_word
+import json
+
+with open(r'\Users\Administrator\Documents\GitHub\selfteaching-python-camp\exercises\1901010132\day10\tang300.json',encoding='UTF-8') as f:
+    read_date = f.read()
+try:
+    print('统计前20的词频数： \n',stats_word.stats_text_cn(read_date,20))
+except ValueError as e:
+    print(e) 

exercises/1901010132/day10/mymodule/stats_word.py

@@ -0,0 +1,50 @@
+text=  '''                       
+"Her eyes beginning to water, she went on,
+"So I would like you all to make me a promise:
+from now on, on your way to school，
+or on your way home, find something beautiful
+to notice. It doesn' t have to be something you
+see -it could be a scent perhaps of freshly
+baked bread wafting out of someone 's house,
+or it could be the sound of the breeze
+slightly rustling the leaves in the trees,
+or the way the morning light catches one
+autumn leaf as it falls gently to the ground.
+Please, look for these things, and remember them."
+　　她的眼睛开始湿润了，她接着说因此我想让你们每个人答应我:
+从今以后，在你上学或者放学的路上，要发现一些美丽的事物。
+它不一定是你看到的某个东西——它可能是一种香味——
+也许是新鲜烤面包的味道从某一座房里飘出来，也许是微风轻拂树叶的声音，
+或者是晨光照射在轻轻飘落的秋叶上的方式。请你们寻找这些东西并且记住它们吧。 
+'''
+import re
+import collections
+import jieba #结巴中文分词
+count=int()
+def stats_text_en(text,count):
+    if type(text) == str: 
+        b=re.sub(r'[^A-Za-z]',' ',text) 
+        list1=b.split() 
+        return(collections.Counter(list1).most_common(count)) 
+    else:
+        raise ValueError('文本为非字符串')
+
+def stats_text_cn(text,count):
+    if not isinstance(text,str): 
+        raise ValueError('文本为非字符串') 
+    p=re.compile(u'[\u4e00-\u9fa5]') 
+    a=re.findall(p,text) 
+    str2=''.join(a)           
+    seg_list = jieba.cut(str2,cut_all=False) #jieba.cut返回的结构是一个可迭代的生成器generator
+    newlist=[]
+    for i in seg_list:
+        if len(i) >= 2:
+            newlist.append(i)
+    return(collections.Counter(newlist).most_common(count)) 
+
+def stats_text(text,count):     
+    if not isinstance(text,str):
+        raise ValueError('文本为非字符串')
+    stats_text_cn(text,count) 
+    stats_text_en(text,count) 
+stats_text(text,count)

exercises/1901010132/day11/main.py

@@ -0,0 +1,27 @@
+import requests
+import pyquery
+from pyquery import PyQuery
+from mymodule import stats_word
+import getpass
+import yagmail
+# 抓取网页
+r = requests.get('https://mp.weixin.qq.com/s/pLmuGoc4bZrMNl7MSoWgiA')
+
+# 提取正文
+document = PyQuery(r.text)
+content = document('#js_content').text()
+print(content)
+
+#词频统计并转为str类型
+#wordString = ''.join(str(i) for i in wordList)
+word_list = stats_word.stats_text_cn(content,100)
+word_str = str(word_list) #转换成str类型
+print(word_str)
+
+#发送统计结果到指定邮箱
+sender = input('请输入发件人邮箱:')
+psw = getpass.getpass() #授权码
+recipients = input('输入收件人邮箱：') #指定邮箱pythoncamp@163.com
+smtp = "smtp.qq.com" #服务器地址
+
+yagmail.SMTP(sender,psw,smtp).send(recipients,'【1901010132】自学训练营学习2群DAY11 bamboo',word_str)

exercises/1901010132/day11/mymodule/stats_word.py

@@ -0,0 +1,50 @@
+text=  '''                       
+"Her eyes beginning to water, she went on,
+"So I would like you all to make me a promise:
+from now on, on your way to school，
+or on your way home, find something beautiful
+to notice. It doesn' t have to be something you
+see -it could be a scent perhaps of freshly
+baked bread wafting out of someone 's house,
+or it could be the sound of the breeze
+slightly rustling the leaves in the trees,
+or the way the morning light catches one
+autumn leaf as it falls gently to the ground.
+Please, look for these things, and remember them."
+　　她的眼睛开始湿润了，她接着说因此我想让你们每个人答应我:
+从今以后，在你上学或者放学的路上，要发现一些美丽的事物。
+它不一定是你看到的某个东西——它可能是一种香味——
+也许是新鲜烤面包的味道从某一座房里飘出来，也许是微风轻拂树叶的声音，
+或者是晨光照射在轻轻飘落的秋叶上的方式。请你们寻找这些东西并且记住它们吧。 
+'''
+import re
+import collections
+import jieba #结巴中文分词
+count=int()
+def stats_text_en(text,count):
+    if type(text) == str: 
+        b=re.sub(r'[^A-Za-z]',' ',text) 
+        list1=b.split() 
+        return(collections.Counter(list1).most_common(count)) 
+    else:
+        raise ValueError('文本为非字符串')
+
+def stats_text_cn(text,count):
+    if not isinstance(text,str): 
+        raise ValueError('文本为非字符串') 
+    p=re.compile(u'[\u4e00-\u9fa5]') 
+    a=re.findall(p,text) 
+    str2=''.join(a)           
+    seg_list = jieba.cut(str2,cut_all=False) #jieba.cut返回的结构是一个可迭代的生成器generator
+    newlist=[]
+    for i in seg_list:
+        if len(i) >= 2:
+            newlist.append(i)
+    return(collections.Counter(newlist).most_common(count)) 
+
+def stats_text(text,count):     
+    if not isinstance(text,str):
+        raise ValueError('文本为非字符串')
+    stats_text_cn(text,count) 
+    stats_text_en(text,count) 
+stats_text(text,count)

exercises/1901010132/day9/main.py

@@ -0,0 +1,8 @@
+from mymodule import stats_word
+import json
+
+with open(r'\Users\Administrator\Documents\GitHub\selfteaching-python-camp\exercises\1901010132\day9\tang300.json',encoding='UTF-8') as f:
+    text=f.read()
+
+
+stats_word.stats_text_cn(text, 100)

exercises/1901010132/day9/mymodule/stats_word.py

@@ -0,0 +1,42 @@
+text=  '''                       
+"Her eyes beginning to water, she went on,
+"So I would like you all to make me a promise:
+from now on, on your way to school，
+or on your way home, find something beautiful
+to notice. It doesn' t have to be something you
+see -it could be a scent perhaps of freshly
+baked bread wafting out of someone 's house,
+or it could be the sound of the breeze
+slightly rustling the leaves in the trees,
+or the way the morning light catches one
+autumn leaf as it falls gently to the ground.
+Please, look for these things, and remember them."
+　　她的眼睛开始湿润了，她接着说因此我想让你们每个人答应我:
+从今以后，在你上学或者放学的路上，要发现一些美丽的事物。
+它不一定是你看到的某个东西——它可能是一种香味——
+也许是新鲜烤面包的味道从某一座房里飘出来，也许是微风轻拂树叶的声音，
+或者是晨光照射在轻轻飘落的秋叶上的方式。请你们寻找这些东西并且记住它们吧。 
+'''
+import re
+import collections
+count=int()
+def stats_text_en(text,count):
+    if type(text)!=str:
+        raise ValueError("文本为非字符串")
+    text=re.sub('[^a-zA-Z]','',text.strip()) #表示所有非英文字母
+    text=text.split()
+    print(collections.Counter(text).most_common(count))
+
+def stats_text_cn(text,count):    #定义检索中文函数
+    if type(text)!=str:
+        raise ValueError("文本为非字符串")
+    text=re.sub('[^\u4e00-\u9fa5]','',text) #[^\u4e00-\u9fa5]表示所有非中文
+    text=' '.join(text)
+    text=text.split()
+    print(collections.Counter(text).most_common(count))
+
+def stats_word(text,count): #定义函数，实现统计汉字和英文单词出现次数
+    if type(text)!=str:
+        raise ValueError("文本为非字符串")
+    stats_text_en(text,count)
+    stats_text_cn(text,count)