scrawl_lottery2.py

# -*- encoding: utf-8 -*-
import urllib2 as url2
from bs4 import BeautifulSoup
import re
import requests
#from vpython import *     # !!! MUST import this,otherwise you're NOT allowed to use curve or others!!!
from visual import *
from visual.graph import *

res = list()
for i in range(1,47):
    url ="http://www.lotto-8.com/listltobig.asp?indexpage="+str(i)+"&orderby=new"
    try:
        response = requests.post(url)
        soup = BeautifulSoup(response.text, "html.parser")
        all = soup.find_all(name="td", attrs={"class":"auto-style5","style":"border-bottom-style: dotted; border-bottom-color: #CCCCCC; font-size:36px;"} )
        for content in all:
            content = content.string.split(u"\xa0")
            for item in content:
                if item!=u",":
                    res.append(item)
    except url2.URLError, e:
        pass
statis = [0 for i in range(50)]
for item in res:
    statis[int(item)] +=1
g1 = gdisplay()
g2 = gdisplay()
f1 = gvbars(gdisplay=g1)
f2 = gvbars(gdisplay=g2)
for x in range(1,50,+1):
    f1.plot(pos=(x,statis[x]))
    f2.plot(pos=(x,sorted(statis)[x]))