python爬虫類ガソリン価格

8036 ワード

pythonを利用して毎日ガソリンの価格を登って、ずっと値上がりして車を運転することができなくて、また最近国際原油先物の価格をプラスして上で、WTIのです
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
        
@author: yufei
@site: http://www.goodid.com
2017-04-08
"""

import re
import urllib2,urllib
import random
import threading
import time
import sqlite3
import sys

#      User Agents
hds=[{'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'},\
    {'User-Agent':'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.12 Safari/535.11'},\
    {'User-Agent':'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Trident/6.0)'},\
    {'User-Agent':'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:34.0) Gecko/20100101 Firefox/34.0'},\
    {'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/44.0.2403.89 Chrome/44.0.2403.89 Safari/537.36'},\
    {'User-Agent':'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50'},\
    {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50'},\
    {'User-Agent':'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0'},\
    {'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1'},\
    {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1'},\
    {'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11'},\
    {'User-Agent':'Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11'},\
    {'User-Agent':'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11'}]

'''
create table OilPrice(
    [id]    integer PRIMARY KEY autoincrement,
    [Oil92]    fot default 0,
    [Oil95]    int default 0,
    [Oil98]    int default 0,
    [Oil0]     int default 0,
    [time]  datetime default (datetime('now', 'localtime'))
);

INSERT INTO OilPrice(id,Oil92,Oil95,Oil98,Oil0,time)  VALUES(NULL,6.1, 7.2, 8.44, 6.55, 20180404);
'''

def sqliteinto(Pricelist):
    con = sqlite3.connect('F:\ID\python\sqlite3\oil.db')
    cur = con.cursor()
    print Pricelist
    sql = '''INSERT INTO OilPrice (id,Oil92,Oil95,Oil98,Oil0,time,WTI,date) VALUES(NULL, ?,?,?,?,?,?,?)'''
    cur.execute(sql,Pricelist)
    con.commit()
    cur.close()
    con.close()

def getPrice():
    url='http://www.qiyoujiage.com/anhui.shtml'
    req = urllib2.Request(url=url,headers=hds[random.randint(0,len(hds)-1)])
    res = urllib2.urlopen(req)
    res = res.read()

    #       
    re_set = re.compile(r'
(.*)',re.S) re_get = re.findall(re_set,res) # p = re.compile('
(.*?)
'
,re.S) Pricelist = re.findall(p,re_get[0]) timep = re.compile(r"(\d+)-(\d+)-.*") nowtime = time.strftime('%Y-%m-%d',time.localtime(time.time())) Pricelist.append(nowtime) return Pricelist def getwPrice(): url='http://youjia.chemcp.com/YuanYouJiaGe.asp' req = urllib2.Request(url=url,headers=hds[random.randint(0,len(hds)-1)]) res = urllib2.urlopen(req) res = res.read() # re_set = re.compile(r'\r
\r
(.*)',re.S) re_get = re.findall(re_set,res) #print re_get # p = re.compile('WTI(.*?)\xb2\xbc\xc2\xd7\xcc\xd8\r
',re.S) Pricelist = re.findall(p,re_get[0]) p = re.compile('(.*?)',re.S) Price = re.findall(p,Pricelist[0]) if len(Price) >= 4: wPrice = Price[0] wtime = Price[3] else: wPrice = 0 wtime = 0 return wPrice,wtime if __name__=="__main__": Pricelist = getPrice() wPrice,wtime = getwPrice() Pricelist.append(wPrice) Pricelist.append(wtime) print Pricelist Pricelist = tuple(Pricelist) sqliteinto(Pricelist)


python        _ 1