import urllib2
import string
import urllib
import re
import random
#设置多个user_agents,防止百度限制IP
user_agents = ['Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20130406 Firefox/23.0', \
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:18.0) Gecko/20100101 Firefox/18.0', \
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533+ \
(KHTML, like Gecko) Element Browser 5.0', \
'IBM WebExplorer /v0.94', 'Galaxy/1.0 en', \
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)', \
'Opera/9.80 (Windows NT 6.0) Presto/2.12.388 Version/12.14', \
'Mozilla/5.0 (iPad; CPU OS 6_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) \
Version/6.0 Mobile/10A5355d Safari/8536.25', \
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) \
Chrome/28.0.1468.0 Safari/537.36', \
'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.0; Trident/5.0; TheWorld)']
def baidu_search(keyword,pn):
p= {'wd': keyword}
res=urllib2.urlopen(("http://www.baidu.com/s?"+urllib.urlencode(p)+"&pn={0}&cl=3&rn=100").format(pn))#&pn={0}&cl=3&rn=100"
html=res.read()
print html
return html
def getList(regex,text):
arr = []
res = re.findall(regex, text)
if res:
for r in res:
arr.append(r)
return arr
def getMatch(regex,text):
res = re.findall(regex, text)
if res:
return res[0]
return ""
def clearTag(text):
p = re.compile(u'<[^>]+>')
retval = p.sub("",text)
return retval
def geturl(keyword):
for page in range(10):
pn=page*100+1
html = baidu_search(keyword,pn)
content = unicode(html, 'utf-8','ignore')
arrList = getList(u"
字这不就是字符串吗,中间那个大括号中的内容会被替换掉的
你这个用法,基本跟这个一样前台后台
,前面{0}里面的0是个不定的值,一般放id,后面就可以得到id。
如果是springmvc的话,,那就是传参的问题