urllib+requests+猫眼电影票房信息可视化

import urllib.request
response = urllib.request.urlopen("http://www.shipudong.com/")
print(response.read().decode("utf-8"))

import urllib.parse
import urllib.request
#data参数是可选的,如果要添加参数,并且如果它是字节流编码格式的内容,即bytes类型,则需要bytes()方法转化
data = bytes(urllib.parse.urlencode({"word":"hello"}),encoding="utf-8")
response = urllib.request.urlopen("http://httpbin.org/post",data=data)
print(response.read())

import urllib.request
response = urllib.request.urlopen("http://www.shipudong.com/",timeout=1)
//程序超过1秒后,如果服务器没有请求,就会抛出URLError异常
print(response.read())

from urllib.request import HTTPPasswordMgrWithDefaultRealm,HTTPBasicAuthHandler,build_opener
from urllib.error import URLError
username = "username"
password = "password"
url = "http://localhost:5000/"
p = HTTPPasswordMgrWithDefaultRealm()
p.add_password(None,url,username,password)
auth_handler = HTTPBasicAuthHandler(p)
opener = build_opener(auth_handler)
try:
    result = opener.open(url)
    html = result.read().decode("utf-8")
    print(html)
except URLError as e:
    print(e.reason) 

from urllib.error import URLError
from urllib.request import ProxyHandler,build_opener
proxy_handler = ({
    //这里是你买的IP代理池
    //一般这样写:"http":"ip地址"或者"https":"ip地址"
})
opener = build_opener(proxy_handler)
try:
    response = opener.open("http://www.shipudong.com/")
    print(response.read().decode("utf-8"))
except URLError as e:
    print(e.reason)

from urllib.parse import urlparse
result = urlparse("http://www.shipudong.com/2019/05/03/python-ku-zhi-selenium-de-shi-yong/")
print(type(result),result)

<class 'urllib.parse.ParseResult'> ParseResult(scheme='http', netloc='www.shipudong.com', path='/2019/05/03/python-ku-zhi-selenium-de-shi-yong/', params='', query='', fragment='')

#你得确保你安装了requests这个库哟
import requests
url = "http://www.shipudong.com/"
result = requests.get(url)
print(type(result))
print(result.status_code)
print(result.text)
print(result.cookies)

import requests
import matplotlib as mpl
import matplotlib.pyplot as plt
import time
import pylab as pl
import sys
#一般网站最基本的反爬措施,伪装协议头headers
headers = {
   'accept':'*/*',
   'accept-encoding':'gzip, deflate, sdch, br',
   'accept-language':'zh-CN,zh;q=0.8',
   'origin':'https://piaofang.maoyan.com',
   'referer':'https://piaofang.maoyan.com/dashboard',
   'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64)
          AppleWebKit/537.36
          (KHTML, like Gecko) Chrome/58.0.3029.110 
          Safari/537.36 SE 2.X MetaSr 1.0'
}
#保证中文输出时不会乱码
mpl.rcParams["font.sans-serif"]=["SimHei"]
mpl.rcParams["axes.unicode_minus"]=False
#要爬取网站的url
url = "https://box.maoyan.com/promovie/api/box/second.json"
#用来存获取到的电影票房数据
arr = []
#记录横坐标的数据
a = []
#记录电影的名字
movie_name = []
#爬取电影网站票房信息
def acquireInfo():
   res = requests.get(url, headers=headers)
   res_con = res.json()
   for item in res_con["data"]["list"]:
       arr.append(item["boxInfo"])
       movie_name.append(item["movieName"])
   for i in range(1, 26):
       a.append(i)
   drawChart(movie_name)
#依据信息画图展示
def drawChart(str):
   plt.bar(a,arr,align="center",color="#7FFF00",tick_label=str)
   #使y轴坐标文字标签正常显示
 pl.xticks(rotation=-90)
   #设置图标的主题文字
 plt.title("猫眼电影实时票房信息")
   #设置x y 轴的名称
 plt.xlabel('电影名称')
   plt.ylabel('电影票房')
   plt.show()
#显示进度条
def view_bar(num, total):
   rate = num / total
   rate_num = int(rate * 100)
   r = ' \r %s>%d%%' % ('=' * num, rate_num,)
   sys.stdout.write(r)
   sys.stdout.flush()
if __name__ == '__main__':
   for i in range(0, 101):
       time.sleep(0.1)
       view_bar(i, 100)
   print("数据加载完成!")
   while 1:
       acquireInfo()
       #每0.1s请求一次网站，做到实时数据的刷新
    time.sleep(1)