python爬虫爬去汽油价格

利用python爬取每天汽油的价格,一直涨车都开不起了,另外最近加了国际原油期货价格在上面,是WTI的

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
获取每天汽油价格
@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

#一些骗人的 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()

    #获取油价格的块
    re_set = re.compile(r'<div id="youjia">(.*)</dl>',re.S)
    re_get = re.findall(re_set,res)

    #获取价格详情
    p = re.compile('<dd>(.*?)</dd>',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()

    #获取油价格的块
    re_set = re.compile(r'\r\n<div class=cpbaojia>\r\n(.*)',re.S)
    re_get = re.findall(re_set,res)
    #print re_get

    #获取价格详情
    p = re.compile('<td bgcolor="#FFFFFF">WTI</td>(.*?)<td bgcolor="#FFFFFF">\xb2\xbc\xc2\xd7\xcc\xd8</td>\r\n',re.S)
    Pricelist = re.findall(p,re_get[0])

    p = re.compile('<td bgcolor="#FFFFFF">(.*?)</td>',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)

这是最近的
这里写图片描述

评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值