python 简单爬虫

使用urllib.request 和re 模块
 1 from urllib.request import *
import re #处理网络访问
#获取网页
url = 'https://image.baidu.com/search/index?tn=baiduimage&ct=201326592&lm=-1&cl=2&ie=gbk&word=%C3%C0%C5%AE%CD%BC%C6%AC&fr=ala&ala=1&alatpl=adress&pos=0&hs=2&xthttps=111111'
#打开网页
hmtl = urlopen(url)
#获取html代码 ，decode 解码
obj = hmtl.read().decode()
#使用re,找出所有的objURL链接  .*?匹配所有结果
urls = re.findall(r'"objURL":"(.*?)"',obj)
index = 1
for url in urls:
    try:
        if re.search('.jpg$',url):
            print('downloading........%d'%index)
            urlretrieve(url,'pic' +str(index)+ '.jpg')
        else:
            print('downloading........%d' % index)
            urlretrieve(url, 'pic' + str(index) + '.png')
        index += 1

    except Exception:
        print('download error....%d'%index)
    else:
        print('download complete')

爬取一张图片

使用requests 模块
1 import requests
image_url = 'http://www.cnblogs.com/Images/Skins/BJ2008.jpg'
response = requests.get(image_url)
with open('outlook.jpg','wb') as f:
    f.write(response.content)