python 简单爬虫

ok075588 2017-11-23 04:24:37

您好，一个简单的爬虫，新手不懂，不能正确返回结果。求帮手指正，谢谢.



#coding=utf-8

import urllib

import urllib2

import requests

import cookielib

import time

import socket

html='http://www.nlfang.com/info_list.asp'



post_data={'area_city': '%C4%CF%C1%EA%CF%D8&',

    'late_class': '%B7%BF%CE%DD%B3%F6%CA%DB&',

    'info_key': '%D6%D0%D1%EB'}



cook={'ASPSESSIONIDSQTTDCBB': 'DJIHGCDDJDDONFJDIGFIGCLC', 'Hm_lvt_b1214475eca64e9e15a8bf68ccb444e4': '1511423469', 'ad_play_index': '29', 'Hm_lpvt_b1214475eca64e9e15a8bf68ccb444e4': '1511423469', 'Hm_lvt_239f7aa51fc37d3b008907442ed09e64': '1511423468', 'Hm_lpvt_239f7aa51fc37d3b008907442ed09e64': '1511423468'}



header={'Accept': 'text/html, application/xhtml+xml, */*',

    'Referer': 'http://www.nlfang.com/',

    'Accept-Language': 'zh-CN',

    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Trident/7.0; rv:11.0) like Gecko',

    'Content-Type': 'application/x-www-form-urle',

    'Accept-Encoding': 'gzip, deflate',

    'Host': 'www.nlfang.com',

    'Content-Length': '86',

    'Connection': 'Keep-Alive',

    'Cache-Control': 'no-cache',

    'Cookie': cook}

post_data=urllib.urlencode(post_data)

res=urllib2.Request(html,headers=header,data=post_data)

response=urllib2.urlopen(res)

print response

...全文

196 3 打赏收藏转发到动态举报

写回复

用AI写文章

3 条回复

切换为时间正序

请发表友善的回复…

发表回复

扶瑶直上 2017-11-28

打赏
举报

直接requests就行了

# coding=utf-8
import requests

html = 'http://www.nlfang.com/info_list.asp'

post_data = {'area_city': '%C4%CF%C1%EA%CF%D8&',
             'late_class': '%B7%BF%CE%DD%B3%F6%CA%DB&',
             'info_key': '%D6%D0%D1%EB'}

cook = {'ASPSESSIONIDSQTTDCBB': 'DJIHGCDDJDDONFJDIGFIGCLC', 'Hm_lvt_b1214475eca64e9e15a8bf68ccb444e4': '1511423469',
        'ad_play_index': '29', 'Hm_lpvt_b1214475eca64e9e15a8bf68ccb444e4': '1511423469',
        'Hm_lvt_239f7aa51fc37d3b008907442ed09e64': '1511423468',
        'Hm_lpvt_239f7aa51fc37d3b008907442ed09e64': '1511423468'}

header = {'Accept': 'text/html, application/xhtml+xml, */*',
          'Referer': 'http://www.nlfang.com/',
          'Accept-Language': 'zh-CN',
          'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Trident/7.0; rv:11.0) like Gecko',
          'Content-Type': 'application/x-www-form-urle',
          'Accept-Encoding': 'gzip, deflate',
          'Host': 'www.nlfang.com',
          'Content-Length': '86',
          'Connection': 'Keep-Alive',
          'Cache-Control': 'no-cache',
          }
session = requests.session()
r = session.get(html, headers=header, data=post_data, cookies=cook)
print r.text

扶瑶直上 2017-11-28

打赏
举报

# coding=utf-8
import requests

html = 'http://www.nlfang.com/info_list.asp'

post_data = {'area_city': '%C4%CF%C1%EA%CF%D8&',
             'late_class': '%B7%BF%CE%DD%B3%F6%CA%DB&',
             'info_key': '%D6%D0%D1%EB'}

cook = {'ASPSESSIONIDSQTTDCBB': 'DJIHGCDDJDDONFJDIGFIGCLC', 'Hm_lvt_b1214475eca64e9e15a8bf68ccb444e4': '1511423469',
        'ad_play_index': '29', 'Hm_lpvt_b1214475eca64e9e15a8bf68ccb444e4': '1511423469',
        'Hm_lvt_239f7aa51fc37d3b008907442ed09e64': '1511423468',
        'Hm_lpvt_239f7aa51fc37d3b008907442ed09e64': '1511423468'}

header = {'Accept': 'text/html, application/xhtml+xml, */*',
          'Referer': 'http://www.nlfang.com/',
          'Accept-Language': 'zh-CN',
          'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Trident/7.0; rv:11.0) like Gecko',
          'Content-Type': 'application/x-www-form-urle',
          'Accept-Encoding': 'gzip, deflate',
          'Host': 'www.nlfang.com',
          'Content-Length': '86',
          'Connection': 'Keep-Alive',
          'Cache-Control': 'no-cache',
          }
session = requests.session()
r = session.get(html, headers=header, data=post_data, cookies=cook)
print r.text