爬虫抓取

爬虫抓取的方式有两种：

1.简单

import urllib2
dir(urllib2)
urllib2.urlopen(url)
html=responce.read()

2.复杂

import urllib2
def make_opener(headers=None):
    cookie=cookielib.CookieJar()           
    opener=urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie),urllib2.HTTPHandler)
    if headers:
         opener.addheades=headers
    else:
         opener.addheaders=[('User-Agent', 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; QQDownload 718)'),('Accept', 'text   /html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8')]
    return opener
opener=make_opener()
responce=opener.open(url,timeout=10)
html=responce.read()