python抓取网页信息保存为xml文件_Python抓取聚划算商品分析页面获取商品信息并以XML格式保存到本地...

本文实例为大家分享了Python抓取聚划算商品页面获取商品信息并保存的具体代码，供大家参考，具体内容如下

#!/user/bin/python

# -*- coding: gbk -*-

#Spider.py

import urllib2

import httplib

import StringIO

import gzip

import re

import chardet

import sys

import os

import datetime

from xml.dom.minidom import Document

from BeautifulSoup import BeautifulSoup

## 这段代码是用于解决控制台打印汉字报错的问题

reload(sys)

sys.setdefaultencoding("utf8")

#####################################################

## debug模式开关，开启后可以看到Http请求的头部信息以及debug日志

DEBUG = 1

NO_DEBUG = 0

httplib.HTTPConnection.debuglevel = DEBUG

## 是否显示爬取网页源代码开关

showSrcCode = False

## 压缩方式

ZIP_TYPE = "gzip"

fileName = "auctions"

location = "d://spiderData/"

## header

headerConfig = {"User-Agent":"taobao-yanyuan.qzs", "Accept-encoding":ZIP_TYPE}

#####################################################

#############class SpiderConfig #####################

class SpiderConfig:

"""

configuration for spider name and url

"""

def __init__(self, name, url):

self.name = name

self.url = url

#####################################################

##############class SpiderAuctionDomain##############

class SpiderAuctionDomain:

"""

Store information with auctions spidered by python

"""

title = ""

url = ""

img = ""

price = ""

def __ini