天眼查新方式信息爬取

#本文通过新的方式爬取突破

由于公司列表页信息很少反爬，除了公司名称其他信息都没有，所以可以取巧提取注册时间注册资本信息
访问过多过快也会封，测试可以通过随机UA突破
另外公司具体信息详情页可能不同公司展示xpath位置不一样，所以用re
另外经营范围下载回来出现&#x开头的乱码，#&#xxx 的格式其实是unicode，用HTMLParser库解析

最后实现结果：基本3秒能查出5家相关企业具体公司信息

import requests
from lxml import etree
import random
import re
# import HTMLParser
from html.parser import HTMLParser

proxy = {
    "http": 'http://125.70.13.77:8080',
    "http": 'https://183.6.129.212:41949'
}
USER_AGENTS = [
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
    "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
    "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
    "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
    "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
    "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
    "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
]
dd=random.choice(USER_AGENTS)
print(dd)
headers={
    "Referer": "https://www.baidu.com/",

    "User-Agent": "%s"%dd
}
def down_load(url):
    cc=requests.get(url=url,headers=headers,proxies=proxy)
    # cc=etree.HTML(cc)
    # cc.encode("utf-8").decode("utf-8")

    cc.encoding="utf-8"
    return  cc.text

i=input("请输入企业名：")
first_url="https://m.tianyancha.com/search?key=%s"%i
# first_url="http://www.baidu.com"
a=down_load(first_url)
a=etree.HTML(a)
detail_url=a.xpath('//div[contains(@class,"col-xs-10")]/a/@href')
boss=a.xpath('/html/body/div[3]/div[5]/div/div[4]/div/div/div[1]/a/text()')
the_registered_capital=a.xpath('/html/body/div[3]/div[5]/div/div[4]/div/div/div[2]/span/text()')
the_registered_time=a.xpath('/html/body/div[3]/div[5]/div/div[4]/div/div/div[3]/span/text()')
# print(detail_url,boss,the_registered_capital,the_registered_time)

gs=[]
for ii in range(len(boss)):
    aa=down_load(detail_url[ii])
    bb=etree.HTML(aa)
    company=bb.xpath('//div[@class="over-hide"]/div/text()')[0]
    industry = re.findall("行业：</span><span>(.*?)</span></div>",aa,re.S)[0]
    the_enterprise_type = re.findall("企业类型：</span><span>(.*?)</span></div>",aa,re.S)[0]
    registration_number = re.findall("工商注册号：</span><span>(.*?)</span></div>",aa,re.S)[0]
    organization_code = re.findall("组织结构代码：</span><span>(.*?)</span></div>",aa,re.S)[0]
    credit_code = re.findall("统一信用代码：</span><span>(.*?)</span></div>",aa,re.S)[0]
    business_period = re.findall("经营期限：</span><span>(.*?)</span></div>",aa,re.S)[0]
    # approval_date = aa.xpath('/html/body/div[3]/div[1]/div[7]/div/div[11]/span[2]/text()')[0]
    registration_authority =re.findall("登记机关：</span><span>(.*?)</span></div>",aa,re.S)[0]
    registered_address =re.findall("注册地址：</span><span>(.*?)</span></div>",aa,re.S)[0]
    scope_of_business =re.findall('<text class="tyc-num">(.*?)</text>',aa,re.S)[0]
    h=HTMLParser()  #&#xxx;‘ 的格式其实是unicode，&#后面跟的是unicode字符的十进制值，解决字体这样的方法
    scope_of_business=h.unescape(scope_of_business)
    new=["公司名："+company,"法人："+boss[ii],"注册时间："+the_registered_time[ii],"注册资本："+the_registered_capital[ii],"企业类型："+the_enterprise_type,"工商注册号："+registration_number,"组织结构代码："+organization_code,"统一信用代码："+credit_code,"经营年限："+business_period,"登记机关："+registration_authority,"注册地址："+registered_address,"经营范围："+scope_of_business]
    gs.append(new)
print(gs)

天眼查新方式信息爬取

猜你喜欢