u014299421的博客

#!/usr/bin/python# -*- coding: UTF-8 -*- import urllib.requestimport urllib.errorimport reimport threadingfrom lxml import etreeimport timeimport pandas as pdimport sysimport numpy as np ...

import urllib.requestimport urllib.parseimport urllib.errorimport jsonimport jsonpathimport pandas as pdimport timeurl="***"#可从Fiddler中查看headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0;...

1、python函数 #lambda函数，打印test2_fun0: 1001fun0=lambda a:a+1print('test2_fun0:',fun0(1000))#map函数，打印111，122，133li=[11,22,33]new_list=map(lambda a:a+100,li)#函数，列表，遍历列表中的每一个元素，执行传递过来的函数参数for i in ...

1 python始终记录变量最新值。2 变量应简短且具有描述性，如student_name等。3 变量名推荐小写。4 单双引号括起来的，字符串可以包含引号和撇号。用法："this's a cup"5 title()将每个单词的首字母都改为大写。用法：str.title()6 upper()将字符串转化为大写。用法：str.upper()7 lower()将字符串转化为小写。用法：str...

1、直方图（连续型，例身高图）mu=100#mean of distribution,平均数sigma=20#standard deviation of distribution,平均差x=mu+sigma*np.random.randn(2000)plt.hist(x,bins=10,color='r',normed=True)#bins表示有几个直方图,normed表示是否标准化，...

#!/usr/bin/python# -*- coding: UTF-8 -*- import urllib.requestimport urllib.errorimport refrom lxml import etreeimport timeimport pandas as pdimport sysimport jiebaimport numpy #numpy计...

#!/usr/bin/python# -*- coding: UTF-8 -*- import urllib.requestimport urllib.errorimport reimport threadingfrom lxml import etreeimport timeimport pandas as pdfrom html.parser import HTMLPa...

1、pandas选择数据 import pandas as pdimport numpy as np s=pd.Series([1,3,6,np.nan,44,1])print(s)0 1.01 3.02 6.03 NaN4 44.05 1.0dtype: float64dates=pd.date_range('20...

1、array=np.array([[1,2,3],[4,5,6]])print(array)print('number of dim:',array.ndim)print('shape:',array.shape)print('size:',array.size)[[1 2 3] [4 5 6]]number of dim: 2shape:(2, 3)size: 6...

import urllib.requestfrom lxml import etree headers = ('Referer','https://tieba.baidu.com/p/4640092720?pn=1')#防盗链，修改访问来源opener = urllib.request.build_opener()opener.addheaders = [headers]urllib...

import urllib.requestfrom lxml import etreeheaders = ('Referer','http://bbs.tianya.cn/post-funinfo-2325132-1.shtml')#防盗链，修改访问来源opener = urllib.request.build_opener()opener.addheaders = [headers]...

1、b站网址：https://www.bilibili.com/bangumi/play/ss11936/2、弹幕网址：http://comment.bilibili.com/13306224.xml，13306224为cid3、用python 编写爬虫，并进行文本分析，生成词云。import urllib.requestimport urllib.errorimport p...