python 网络爬虫抓取图片

#-*- encoding: utf-8 -*-
'''
Created on 2014-4-24
 @author: Leon Wong
'''
import urllib2
import urllib
import re
import time
import os
import uuid
 #获取二级页面url
def findUrl2(html):
    re1 = r'http://tuchong.com/\d+/\d+/|http://\w+(?<!photos).tuchong.com/\d+/'
    url2list = re.findall(re1,html)
    url2lstfltr = list(set(url2list))
    url2lstfltr.sort(key=url2list.index)
    #print url2lstfltr
    return url2lstfltr
 #获取html文本
def getHtml(url):
    html = urllib2.urlopen(url).read().decode('utf-8')#解码为utf-8
    return html
 #下载图片到本地
def download(html_page , pageNo):
    #定义文件夹的名字
    x = time.localtime(time.time())
    foldername = str(x.__getattribute__("tm_year"))+"-"+str(x.__getattribute__("tm_mon"))+"-"+str(x.__getattribute__("tm_mday"))
    re2=r'http://photos.tuchong.com/.+/f/.+\.jpg'
    imglist=re.findall(re2,html_page)
    print imglist
    download_img=None
    for imgurl in imglist:
        picpath = 'D:\\TuChong\\%s\\%s'  % (foldername,str(pageNo))
        filename = str(uuid.uuid1())
        if not os.path.exists(picpath):
            os.makedirs(picpath)
        target = picpath+"\\%s.jpg" % filename
        print "The photos location is:"+target
        download_img = urllib.urlretrieve(imgurl, target)#将图片下载到指定路径中
        time.sleep(1)
        print(imgurl)
    return download_img

# def callback(blocknum, blocksize, totalsize):
#     '''回调函数
#     @blocknum: 已经下载的数据块
#     @blocksize: 数据块的大小
#     @totalsize: 远程文件的大小
#     '''
#     print str(blocknum),str(blocksize),str(totalsize)
#     if blocknum * blocksize >= totalsize:
#         print '下载完成'

def quitit():
    print "Bye!"
    exit(0)


if __name__ == '__main__':
    print '''            *****************************************
            **    Welcome to Spider for TUCHONG    **
            **      Created on 2014-4-24           **
            **      @author: Leon Wong             **
            *****************************************'''
    pageNo = raw_input("Input the page number you want to scratch (1-100),please input 'quit' if you want to quit>")
    while not pageNo.isdigit() or int(pageNo) > 100 :
        if pageNo == 'quit':quitit()
        print "Param is invalid , please try again."
        pageNo = raw_input("Input the page number you want to scratch >")

    #针对图虫人像模块来爬取
    html = getHtml("http://tuchong.com/tags/%E4%BA%BA%E5%83%8F/?page="+str(pageNo))

    detllst = findUrl2(html)
    for detail in detllst:
        html2 = getHtml(detail)
        download(html2,pageNo)
    print "Finished."


转载自:点击打开链接

学习:http://www.cnblogs.com/xin-xin/p/4297852.html

评论
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