#!/usr/bin/env python
# encoding: utf-8
'''
@author: caopeng
@license: (C) Copyright 2013-2017, Node Supply Chain Manager Corporation Limited.
@contact: deamoncao100@gmail.com
@software: garner
@file: PicDownloader.py
@time: 2017/9/11 0011 17:27
@desc:
'''
#-*- coding:utf-8 -*-
import re
import requests
def dowmloadPic(html,keyword):
pic_url = re.findall('"objURL":"(.*?)",',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 __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'
result = requests.get(url)
dowmloadPic(result.text,word)
python 爬虫
最新推荐文章于 2024-04-01 13:30:49 发布