python爬虫和百度搜索有什么不一样_爬虫 页面不存在_百度搜索

1.学写爬虫，遇到一个问题，加了values={"wd":"test","ie":"utf-8"}就报错了，也就是我向百度页面搜索里面输入test就报错，百度了一圈没找到答案，请教一下各位大神如何处理，如果可以的话能否说明这是为什么，以及怎么处理类似的情况，谢谢！

2.代码如下(版本2.7)：

(randHeader用来生成随机的Header，savef保存输出结果，logging.info用来调试，try处理可能的错误，其他部分就是爬虫的主体)

#coding:utf-8

import random

import urllib2

import urllib

import os

import logging

logging.basicConfig(level=logging.INFO)

def savef(html,tpath):

#12输入输出目录不存在，就创建

if not os.path.exists(tpath):

os.makedirs(tpath)

#12打开需要保存的文件(该命令下，如果文件不存在就创建新文件)

with open(os.path.join(tpath,'2.html'),'w') as f:

f.write(html)

with open(os.path.join(tpath,'2.xml'),'w') as f:

f.write(html)

with open(os.path.join(tpath,'2.txt'),'w') as f:

f.write(html)

def randHeader():

head_connection = ['Keep-Alive','close']

head_accept = ['text/html, application/xhtml+xml, */*']

head_accept_language = ['zh-CN,fr-FR;q=0.5','en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3']

head_user_agent = ['Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko',

'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36',

'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; rv:11.0) like Gecko)',

'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1',

'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3',

'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070803 Firefox/1.5.0.12',

'Opera/9.27 (Windows NT 5.2; U; zh-cn)',

'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0',

'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)',

'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080219 Firefox/2.0.0.12 Navigator/9.0.0.6',

'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Win64; x64; Trident/4.0)',

'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)',

'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E)',

'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Maxthon/4.0.6.2000 Chrome/26.0.1410.43 Safari/537.1 ',

'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E; QQBrowser/7.3.9825.400)',

'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0 ',

'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.92 Safari/537.1 LBBROWSER',

'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; BIDUBrowser 2.x)',

'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/3.0 Safari/536.11']

header = {

'Connection': head_connection[0],

'Accept': head_accept[0],

'Accept-Language': head_accept_language[1],

'User-Agent': head_user_agent[random.randrange(0,len(head_user_agent))]

}

return header

"""

#输出随机Header

for i in range(10):

print(randHeader())

"""

url1="http://www.baidu.com/"

kkk=url1.split("/")[2]

headers=randHeader()

logging.info("headers=%s" % headers)

values={"wd":"test","ie":"utf-8"}

data=urllib.urlencode(values)

request=urllib2.Request(url1,data,headers)

#HTTP错误处理

try:

urllib2.urlopen(request)

except URLError,e:

logging.info("e.code=%s" % e.code)

logging.info("e.read()=" % e.read())

response=urllib2.urlopen(request)

html=response.read()

#根目录

cpath="I:\\"

#拼输出目录

tpath=os.path.join(cpath,kkk)

savef(html,tpath)

3.输出结果如下：

页面不存在_百度搜索

...由于太多，后面就省略了