(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

  1. 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 ...

  2. 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 ...

  3. 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 ...

  4. 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 ...

  5. 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 ...

  6. 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 ...

  7. 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. ...

  8. 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. ...

  9. 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

  1. xdoj 1044---炸红花 (话说 小时候经常玩这个被虐。。。。qwq)

    // 我真的好笨 只会枚举 话说那个ac的370b到底是怎么做的 /(ㄒoㄒ)/~~ #include <iostream> #include <algorithm> usin ...

  2. .NET/C# 项目如何优雅地设置条件编译符号?

    条件编译符号指的是 Conditional Compilation Symbols.你可以在 Visual Studio 的项目属性中设置,也可以直接在项目文件中写入 DefineConstants ...

  3. hdu1081 DP类最大子段和(二维压缩+前缀和数组/树状数组计数)

    题意:给出一个 n * n 的数字矩阵,问最大子矩阵和是多少. 由于和最长子段和问题类似,一开始想到的就是 DP ,一开始我准备用两个循环进行 DP ,对于每一个 (i,j) ,考察(i - 1,j) ...

  4. LM算法的推导过程

  5. JNI学习笔记_C调用Java

    一.笔记 1.C调用Java中的方法,参考jni.pdf pg97可以参考博文:http://blog.csdn.net/lhzjj/article/details/26470999步骤: a. 创建 ...

  6. 使用lua graphql 模块让openresty 支持graphql api

      graphql 是一个很不错的api 查询标准语言,已经有一个lua 的版本支持graphql 项目使用docker&&docker-compose 运行 环境准备 模块安装 lu ...

  7. ballerina 学习 三十 扩展开发(一)

    ballerina 主要是分为两大类 基于ballerina 语言开发的,一般是客户端的connector 使用java语言开发的(类似的基于jvm的都可以),一般是注解以及进行构件生成 baller ...

  8. 转 MetaWeblog API 编写

    如今,许多人都熟悉个人和公司或业界主办的博客.后者明显成为了传统公司和行业网站的下一代新兴产物.博客的内容涉及从简洁的特制产品公告和公共关系到实用且深刻的主题探索,这些主题可能对公司的产品或行业的未来 ...

  9. android 图片解码显示流程

    版权声明:本文为博主原创文章,未经博主同意不得转载. https://blog.csdn.net/jingxia2008/article/details/32327699 问题来源 android 能 ...

  10. string截断

    public static string GetFirstString(string stringToSub, int length)         {            Regex regex ...