6.requests编写企查查爬虫
(为编写完善能拿下来数据)
企查查代码数据如下:
#encoding:utf-8
import requests
from lxml import etree
import random
import re
#目标采集地址
base_url1='http://m.qichacha.com'
base_url='https://m.qichacha.com/search?key=' user_agent=[
"Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER) ",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E) ",
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 SE 2.X MetaSr 1.0",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0) ",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.3.4000 Chrome/30.0.1599.101 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 UBrowser/4.0.3214.0 Safari/537.36",
]
cookie=[
'UM_distinctid=16518280d1e3e5-00788a93df88f7-5b193413-1fa400-16518280d1f949; zg_did=%7B%22did%22%3A%20%2216518280dd3b45-0da4e4ab13f793-5b193413-1fa400-16518280dd51f6%22%7D; acw_tc=7b81f49815356947470295339e1fc37a590000ea6190b3cf75ab42853b; PHPSESSID=4l787fmr2v90mh2khj8n6n64l5; CNZZDATA1254842228=226405416-1535690886-null%7C1535690886; Hm_lvt_3456bee468c83cc63fb5147f119f1075=1535595956,1535618789,1535618810,1535694746; zg_de1d1a35bfa24ce29bbf2c7eb17e6c4f=%7B%22sid%22%3A%201535694746927%2C%22updated%22%3A%201535695379242%2C%22info%22%3A%201535595953976%2C%22superProperty%22%3A%20%22%7B%7D%22%2C%22platform%22%3A%20%22%7B%7D%22%2C%22utm%22%3A%20%22%7B%7D%22%2C%22referrerDomain%22%3A%20%22m.baidu.com%22%2C%22cuid%22%3A%20%227d775544e16a1cc0d0ab63b42b4b8aef%22%7D; Hm_lpvt_3456bee468c83cc63fb5147f119f1075=1535695379',
'UM_distinctid=16518280d1e3e5-00788a93df88f7-5b193413-1fa400-16518280d1f949; zg_did=%7B%22did%22%3A%20%2216518280dd3b45-0da4e4ab13f793-5b193413-1fa400-16518280dd51f6%22%7D; acw_tc=7b81f49815356947470295339e1fc37a590000ea6190b3cf75ab42853b; PHPSESSID=4l787fmr2v90mh2khj8n6n64l5; CNZZDATA1254842228=226405416-1535690886-null%7C1535690886; Hm_lvt_3456bee468c83cc63fb5147f119f1075=1535595956,1535618789,1535618810,1535694746; zg_de1d1a35bfa24ce29bbf2c7eb17e6c4f=%7B%22sid%22%3A%201535694746927%2C%22updated%22%3A%201535695791508%2C%22info%22%3A%201535595953976%2C%22superProperty%22%3A%20%22%7B%7D%22%2C%22platform%22%3A%20%22%7B%7D%22%2C%22utm%22%3A%20%22%7B%7D%22%2C%22referrerDomain%22%3A%20%22m.baidu.com%22%2C%22cuid%22%3A%20%227d775544e16a1cc0d0ab63b42b4b8aef%22%7D; Hm_lpvt_3456bee468c83cc63fb5147f119f1075=1535695792',
'UM_distinctid=16518280d1e3e5-00788a93df88f7-5b193413-1fa400-16518280d1f949; zg_did=%7B%22did%22%3A%20%2216518280dd3b45-0da4e4ab13f793-5b193413-1fa400-16518280dd51f6%22%7D; acw_tc=7b81f49815356947470295339e1fc37a590000ea6190b3cf75ab42853b; PHPSESSID=4l787fmr2v90mh2khj8n6n64l5; CNZZDATA1254842228=226405416-1535690886-null%7C1535690886; Hm_lvt_3456bee468c83cc63fb5147f119f1075=1535595956,1535618789,1535618810,1535694746; zg_de1d1a35bfa24ce29bbf2c7eb17e6c4f=%7B%22sid%22%3A%201535694746927%2C%22updated%22%3A%201535695924595%2C%22info%22%3A%201535595953976%2C%22superProperty%22%3A%20%22%7B%7D%22%2C%22platform%22%3A%20%22%7B%7D%22%2C%22utm%22%3A%20%22%7B%7D%22%2C%22referrerDomain%22%3A%20%22m.baidu.com%22%2C%22cuid%22%3A%20%227d775544e16a1cc0d0ab63b42b4b8aef%22%7D; Hm_lpvt_3456bee468c83cc63fb5147f119f1075=1535695925',
'UM_distinctid=16518280d1e3e5-00788a93df88f7-5b193413-1fa400-16518280d1f949; zg_did=%7B%22did%22%3A%20%2216518280dd3b45-0da4e4ab13f793-5b193413-1fa400-16518280dd51f6%22%7D; acw_tc=7b81f49815356947470295339e1fc37a590000ea6190b3cf75ab42853b; PHPSESSID=4l787fmr2v90mh2khj8n6n64l5; CNZZDATA1254842228=226405416-1535690886-null%7C1535690886; Hm_lvt_3456bee468c83cc63fb5147f119f1075=1535595956,1535618789,1535618810,1535694746; zg_de1d1a35bfa24ce29bbf2c7eb17e6c4f=%7B%22sid%22%3A%201535694746927%2C%22updated%22%3A%201535696003819%2C%22info%22%3A%201535595953976%2C%22superProperty%22%3A%20%22%7B%7D%22%2C%22platform%22%3A%20%22%7B%7D%22%2C%22utm%22%3A%20%22%7B%7D%22%2C%22referrerDomain%22%3A%20%22m.baidu.com%22%2C%22cuid%22%3A%20%227d775544e16a1cc0d0ab63b42b4b8aef%22%7D; Hm_lpvt_3456bee468c83cc63fb5147f119f1075=1535696005'
]
# 请求头设置
headers={
'User-agent': random.choice(user_agent),
'cookie': random.choice(cookie)
} name_list=['成都创信广告有限公司'] for name in name_list:
start_url=base_url+str(name)
print(start_url)
response = requests.get(start_url, headers=headers)
_response=response.text
# print(_response)
# content = etree.HTML(_response)
# print(content)
#获取筛选信息链接
search_url=re.findall('</div> <a href="(.*?)" class="a-decoration"> <div class="list-item"> <div class="list-item-top">',_response)
url=base_url1+search_url[0]
# print(url)
# print('*'*100)
response1 = requests.get(url,headers=headers)
_response1=response1.text
#公司名称
company_name=re.findall('<div class="company-name">(.*?)<',_response1)[0]
print('公司名称:'+company_name)
#法人
legal_person=re.findall('<a class="oper" href=".*?">(.*?)</a>',_response1)[0]
print('法人:'+legal_person)
#电话
telephone=re.findall('<a href="tel:.*?" class="phone a-decoration">(.*?)</a>',_response1)[0]
print('电话:'+telephone)
# #地址
# address=re.findall('</div> <div class="address">(.*?)</div> </div>',_response1)[0]
# print(address)
# # print('地址:'+address) # #注册号
# registration_number=re.findall('</div><div class="basic-item-right">(.*?)</div>',_response1)
# print(registration_number)
执行结果如下图:

6.requests编写企查查爬虫的更多相关文章
- Python爬虫爬企查查数据
因为制作B2b网站需要,需要入库企业信息数据.所以目光锁定企查查数据,废话不多说,开干! #-*- coding-8 -*- import requests import lxml import sy ...
- 如何用python无账号无限制获取企查查信息
前言 文的文字及图片来源于网络,仅供学习.交流使用,不具有任何商业用途,版权归原作者所有,如有问题请及时联系我们以作处理. PS:如有需要Python学习资料的小伙伴可以加点击下方链接自行获取http ...
- 12.通过微信小程序端访问企查查(采集工商信息)
需要注意的问题: 一.1.微信端访问企查查小程序需要登录.2.访问抓包获取的url是有时效性的过一段时间就不能用了. http://xcx.qichacha.com/wxa/v1/base/getEn ...
- 11.采集手机端app企查查上司公司数据(未成功)
---恢复内容开始--- 采集企查查手机端app数据: 1.首先手机端安装app并usb连接电脑端,fiddler监控手机请求数据对数据进行分析抓取. 手机端界面与fiddler界面参照: 2.对获取 ...
- 企查查app新增企业数据抓取
企查查每日新增企业数据抓取尚未完成的工作: 需要自行抓包获取设备id,appid,sign等等 sign和时间戳保持一致即可 把所有的数据库.redis配置 无法自动登录,账号需要独立 redis数据 ...
- XPath2Doc,一个半自动采集网页生成Word Docx文件的工具,带企查查和天眼查模板
原始出处:https://www.cnblogs.com/Charltsing/p/XPath2Doc.html 很多人需要从网站采集一些数据填写Word模板,手工操作费时费力还容易出错,所以我给朋友 ...
- Nebula Graph 在企查查的应用
本文首发于 Nebula Graph Community 公众号 背景 企查查是企查查科技有限公司旗下的一款企业信用查询工具,旨在为用户提供快速查询企业工商信息.法院判决信息.关联企业信息.法律诉讼. ...
- Python 利用Python编写简单网络爬虫实例3
利用Python编写简单网络爬虫实例3 by:授客 QQ:1033553122 实验环境 python版本:3.3.5(2.7下报错 实验目的 获取目标网站“http://bbs.51testing. ...
- Python 利用Python编写简单网络爬虫实例2
利用Python编写简单网络爬虫实例2 by:授客 QQ:1033553122 实验环境 python版本:3.3.5(2.7下报错 实验目的 获取目标网站“http://www.51testing. ...
随机推荐
- 【BZOJ1702】[usaco2007margold]队列平衡
原来蛤习线性探测的时候要每次加一个稍大一点的数而不是每次+1……连蛤习都不会写,我tmd是有多弱 原题: N(1<=N<=100000)头牛,一共K(1<=K<=30)种特色, ...
- pycharm PYTHONPATH
Hi brandenju! I believe os.chdir doesn't affect PYTHONPATH so changing your working directory at run ...
- TensorFlow学习线路
如何高效的学习 TensorFlow 代码? 或者如何掌握TensorFlow,应用到任何领域? 作者:黄璞链接:https://www.zhihu.com/question/41667903/ans ...
- vue 回车自动登录
原理: 在密码输入框加入事件:@keyup.enter.native 登录button加入事件:@click 代码: pug 语法: el-form(ref="loginForm" ...
- window.open 和 location.href 区别
window.open():可以在一个网站上打开另外的一个网站的地址 window.location():只能在一个网站中打开本网站的网页
- mysql的一些 参数查询
1 查询 事务 超时时间: SHOW GLOBAL VARIABLES LIKE 'innodb_lock_wait_timeout'; (默认innodb引擎事务的超时时间) 2 查询事务隔离级别 ...
- bzoj 4566 [Haoi2016]找相同字符——广义后缀自动机
题目:https://www.lydsy.com/JudgeOnline/problem.php?id=4566 每个后缀结尾处 ct[ ] = 1 ,按拓扑序 dp 一下就能求出 right 集合的 ...
- oracle常用数据类型说明
类型 含义 存储描述 备注 CHAR 固定长度字符串 最大长度2000bytes VARCHAR2 可变长度的字符串, 最大长度4000bytes 可做索引的最大长度749 NCHAR 根据字符集而定 ...
- 【linux】vim/vi常用指令
0或者"Home”键:光标转移到此段的最前面字节处. $或者"End"键:光标转移到此段的最后面字节处. n<space>:光标向后移动n个字节. n< ...
- 【python】实例-用户登录系统
有N,E,Q三个选择,若选择Q或者中断,则系统退出.若其他选项,则持续让用户选择. #!/usr/bin/env python db = {} def newuser(): prompt = 'log ...