python3.4爬虫demo

from SpiderSimple.HtmLHelper import *import impimport sysimp.reload(sys) #sys.setdefaultencoding('utf-8')  html = getHtml('http://image.baidu.com/')try:  getImage(html)  exit()except Exception as e:  print(e) 

from urllib.request import urlopen,urlretrieve#正则库import re#打开网页def getHtml(url):  page = urlopen(url)          html = page.read()  return html#用正则爬里面的图片地址  def getImage(Html):  try:    #reg = r'src="(.+?/.jpg)" class'    #image = re.compile(reg)      image = re.compile(r'<img[^>]*src[=/"/']+([^/"/']*)[/"/'][^>]*>', re.I)         Html = Html.decode('utf-8')    imaglist = re.findall(image,Html)        x =0        for imagurl in imaglist:        #将图片一个个下载到项目所在文件夹           urlretrieve(imagurl, '%s.jpg' % x)      x+=1   except Exception as e:    print(e)

echo offset PYTHONIOENCODING=utf8python -u %1