Python 图片爬虫

# coding:utf-8

import re
import requests


def dowmloadPic(html, keyword):


    pic_url = re.findall('src="(.*?)"',html, re.S)
    i = 0
    print '找到关键词:'+keyword+'的图片,现在开始下载图片...'
    for each in pic_url:
        print '正在下载第'+str(i+1)+'张图片,图片地址:'+str(each)
        try:
            pic = requests.get(each, timeout=10)
        except requests.exceptions.ConnectionError:
            print '【错误】当前图片无法下载'
            continue
        string = 'pictures\\'+keyword+'_'+str(i) + '.jpg'
        # resolve the problem of encode, make sure that chinese name could be store
        fp = open(string.decode('utf-8').encode('cp936'), 'wb')
        fp.write(pic.content)
        fp.close()
        i += 1
        if i==60:
            break



if __name__ == '__main__':
    word = raw_input("Input key word: ")
    # url = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word='+word+'&ct=201326592&v=flip'
    # url = 'http://photo.renren.com/photo/260248220/album-974529014/v7'
    # result = requests.get(url)
    # f = open("src.txt", "r")
    # text = f.read()
    url = 'http://tieba.baidu.com/p/4621662497'
    result = requests.get(url)
    # print(result.text)
    dowmloadPic(result.text, word)

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
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