2018~2019第二学年17级信管班杨秀璋老师《大数据技术及运用》课堂python代码学习汇总（第二部分）

1、python定义类型

print "abc"

strl=raw_input("please input a string:")
print (strl)
print (type(strl))

weight=raw_input("")
print(weight)
print(type(weight))

cj=input("please input cj:")
print(cj,type(cj))

运行结果：

2、查看字符型，输出矩阵，依次输出字符

print range(10)
print (type(range(10)))

for i in range(10):
    print i

num=[1,3,5,7,9]
print num
for k in num:
    print num
str2="ayouleyang"
for a in str2:
    print a

运行结果：

3、翻倍输出及三角形

a="yangyou"
print a
print a*4

for i in range(10):
    print "*"*i
print ""

for i in range(10):
    print "*"*(10-i)
print ""

运行结果：

4、爬取网页源代码

import urllib
import webbrowser as web
url="http://news.gufe.edu.cn/html/news/201903/4325.html"
#获取该网页的源代码html
web.open_new_tab(url)

content=urllib.urlopen(url).read()
print content
#两个参数：保存文件的名称 Write写入文件
open("ecm.html","w").write(content)

运行结果：

5、下载并保存图片

import urllib
url2="https://www.baidu.com/s?wd=%E4%BB%8A%E6%97%A5%E6%96%B0%E9%B2%9C%E4%BA%8B&tn=SE_Pclogo_6ysd4c7a&sa=ire_dl_gh_logo&rsv_dl=igh_logo_pc"
urllib.urlretrieve(url2,"bd.jpg")

运行结果：

6、爬取网页文本

from requests_html import HTMLSession
session = HTMLSession()
url = 'https://www.jianshu.com/p/85f4624485b9'
r = session.get(url)
print(r.html.text)

运行结果：

7、正则表达式获取非为本代码

# -*- coding: utf_8 -*-
import urllib.request
import re

url = "http://www.nipic.com/topic/show_6547_1.html"

content = urllib.request.urlopen(url).read()
print (content)

#<img src="图片地址" />
#正则表达式获取所有图片的地址
nums = re.findall('src="(.*?\.jpg)"', content)
title=re.findall(r"<title>(.*?)</title>",content)
print (title[0])

i = 1
for u in nums:
    print (u)
    name = "img//yxz" + str(i) + ".jpg"
    print (name)
    i = i + 1
    urllib.urlretrieve(u, name)

运行结果：

8、爬取豆瓣网

from bs4 import BeautifulSoup
from urllib import request
# -*- coding: utf-8 -*-
#爬取多页豆瓣评分电影
url = " https://movie.douban.com/top250"
content = request.urlopen(url).read()

#BS解析
soup = BeautifulSoup(content, "html.parser")
print (soup.title)
print (soup.title.text)

#爬取图片地址
nums = soup.findAll('img')
for n in nums:
    print (n)
#爬取正文
info = soup.find_all(attrs={'class': 'item'})
for n in info:
    print (n.text.replace('\n', ''))
    print("=========================")

运行结果：

9、查看微信好友

#—*—coding:utf-8-*-
import itchat
itchat.login()
friends=itchat.get_friends(update='Ture')[0:]
print (u"昵称",u"性别",u"省份",u"城市")
for i in friends[0:]:
   print (i["NickName"],i["Sex"],i["Province"],i["City"])

运行结果：

10、微信自动回复

# -*- coding: utf-8 -*-
import itchat
import time
# import time 
@itchat.msg_register('Text')
def text_reply(msg):
    if not msg['FromUserName'] == myUserName: # 当消息不是由自己发出的时候
        # 发送一条提示给文件助手
        itchat.send_msg(u"[%s]收到好友@%s 的信息：%s\n" %
                        (time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(msg['CreateTime'])),
                         msg['User']['NickName'],
                         msg['Text']), 'filehelper')
        # 回复给好友
        return u'[自动回复]您好，我现在有事不在，一会再和您联系。\n已经收到您的的信息：%s\n' % (msg['Text'])
 
if __name__ == '__main__':
    itchat.auto_login()
    myUserName = itchat.get_friends(update=True)[0]["UserName"]
    itchat.run()

运行结果：

11、QQ好友头像获取

import itchat

# itchat.login（）#微信登录
itchat.auto_login(hotReload=True)#自动登录  保存登录信息  暂时的

friends = itchat.get_friends()#获取好友列表
# print(friends)#[]列表

for friend in friends:
    #获取好友名字
    print(friend['NickName'])  # {}字典  键值队来取值
    #获取头像  @9102085afd09827b10569fd7272d6e0032e4febc8b4bc5a25b8c49cdb2635a19 相当于ID
    img = itchat.get_head_img(userName=friend['UserName'])
    path = "E:\PythonMake\Wechat\images\\"+friend['NickName']+".jpg"
    print("正在下载:%s的信息" % friend['NickName'])
    
    with open(path,'wb') as f:
        f.write(img)

运行结果：