# 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)
Python 图片爬虫
最新推荐文章于 2024-05-04 16:08:54 发布