python爬虫——图片下载
#-*- coding:utf-8 -*-import re
import requests
def picdown():
word = raw_input('Please input keyword:')
url = 'https://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word='+word+'&ct=201326592&v=flip'
html = requests.get(url).text
#查找所有以objURL开始的字段,re.S表示让”.”可以匹配换行符,
#不然有些标签头和尾是分几行的,就会匹配失败
pic_url = re.findall('"objURL":"(.*?)",',html,re.S)
i = 0
for each in pic_url:
print each
try:
pic= requests.get(each, timeout=10)#请求超时
except requests.exceptions.ConnectionError:
print '[错误]当前图片无法下载'
continue
string = './picture/'+str(i) + '.jpg'#保存文件在当前目录下的picture文件夹中
fp = open(string,'wb')
fp.write(pic.content)
fp.close()
i += 1
if __name__=='__main__':
picdown()
页:
[1]