利用python爬虫获取黄金价格 使用python爬虫获取黄金价格的核心代码

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
获取每天黄金价格
@author: yufei
@site: http://www.antuan.com
2017-05-11
"""
import re
import urllib2,urllib
import random
import threading
import time
import sqlite3
import sys
from __builtin__ import exit
#Some 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 GoldPricelist(
  [id]  integer PRIMARY KEY autoincrement,
  [name]  varchar default 0,
  [price]  varchar default 0,
  [time] datetime default (datetime('now', 'localtime'))
);
INSERT INTO OilPrice(id,name,price,time) VALUES(NULL,sss, 300, 20180404);
'''
def sqliteinto(Pricelist):
  con = sqlite3.connect('F:\ID\python\sqlite3\Gold.db')
  cur = con.cursor()
  print Pricelist
  sql = '''INSERT INTO GoldPrices (id,name,price,time) VALUES(NULL,?,?,?)'''
  cur.execute(sql,Pricelist)
  con.commit()
  cur.close()
  con.close()
def getPrice():
  url='http://www.dyhjw.com/matter_gold/'
  req = urllib2.Request(url=url,headers=hds[random.randint(0,len(hds)-1)])
  res = urllib2.urlopen(req)
  res = res.read()
  #获取的块
  re_set = re.compile(r'<dl class="main_bname">(.*?)</div>',re.S)
  re_get = re.findall(re_set,res)
  #获取价格详情
  p = re.compile('target="_blank">(.*?)<span class="zd">-</span>\n ',re.S)
  Pricelist = re.findall(p,re_get[0])
  for i in range(0,len(Pricelist)):
    p = re.compile('(.*?)</a>\n              <span class="jg">(.*)</span>',re.S)
    Price = re.findall(p,Pricelist[i])
    gname = Price[0][0]
    gprice = Price[0][1]
    timep = re.compile(r"(\d+)-(\d+)-.*")
    nowtime = time.strftime('%Y-%m-%d',time.localtime(time.time()))
    datas = []
    datas.append(gname.decode('utf8'))
    datas.append(gprice)
    datas.append(nowtime)
    datas = tuple(datas)
    sqliteinto(datas)
if __name__=="__main__":
  getPrice()