天眼查

&&&&

# -*- coding: utf-8 -*
import xlrd
import requests
from bs4 import  BeautifulSoup
import sys
reload(sys)
sys.setdefaultencoding('utf8')
import time

def getCompanyList():
    data = xlrd.open_workbook(u'企查查.xlsx')
    table = data.sheets()[0]
    nrows = table.nrows
    companyList =[]
    for i in xrange(0,nrows):
        rowValues= table.row_values(i)
        for item in rowValues:
            companyList.append(item)
    companyList.pop(0)    #獲得全部公司名列表
    return companyList


def  getUrl(companyName):
    url = "https://www.tianyancha.com/search?key=" + u'%s' % companyName
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.3964.2 Safari/537.36',
        'Cookie':'TYCID=e445690096c411e7b5b4bfe4760c4e65; uccid=c7ae83a70ec8b2157746346fbb1c33ce; ssuid=5112913316; aliyungf_tc=AQAAAAQzsD4A4w0AVdXNfHCBi5H/1dg1; csrfToken=o9nXy2N8cgdG0_N5Iz8CYnt-; RTYCID=4ce5b0431c934dc3bbebe5695ab2863c; bannerFlag=true; token=5d20e41769f143dea5806c52bf6c953b; _utm=2a425496ba624a8482fa563771854afa; tyc-user-info=%257B%2522token%2522%253A%2522eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiIxNTUxNzcwNzkzNSIsImlhdCI6MTUyNjg5Njk1NCwiZXhwIjoxNTQyNDQ4OTU0fQ.daBETlYxMpGXywxEvJCOtHKDFDi0XN-UTJBT9OWe4OaVOfEp_iFMmw3o5mTc-CpDrnF-jCPwxvZK9Iobn9iwRw%2522%252C%2522integrity%2522%253A%25220%2525%2522%252C%2522state%2522%253A%25220%2522%252C%2522redPoint%2522%253A%25220%2522%252C%2522vipManager%2522%253A%25220%2522%252C%2522vnum%2522%253A%25220%2522%252C%2522onum%2522%253A%25220%2522%252C%2522mobile%2522%253A%252215517707935%2522%257D; auth_token=eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiIxNTUxNzcwNzkzNSIsImlhdCI6MTUyNjg5Njk1NCwiZXhwIjoxNTQyNDQ4OTU0fQ.daBETlYxMpGXywxEvJCOtHKDFDi0XN-UTJBT9OWe4OaVOfEp_iFMmw3o5mTc-CpDrnF-jCPwxvZK9Iobn9iwRw; Hm_lvt_e92c8d65d92d534b0fc290df538b4758=1526366266,1526368826,1526889740,1526892761; Hm_lpvt_e92c8d65d92d534b0fc290df538b4758=1526896940',
    }
    response = requests.get(url, headers=headers)
    soup = BeautifulSoup(response.text, 'lxml')
    try:
        url = 'https://www.tianyancha.com/company/'+ soup.find('div',class_='title overflow-width').a['href'].split('-')[1][1:]
    except:
        print  soup.find('div',class_='title overflow-width')
        print  soup.prettify()
    return url


def  qiChaCha(companyName,url):
    headers = {
        'Cookie':'TYCID=e445690096c411e7b5b4bfe4760c4e65; uccid=c7ae83a70ec8b2157746346fbb1c33ce; ssuid=5112913316; aliyungf_tc=AQAAAAQzsD4A4w0AVdXNfHCBi5H/1dg1; csrfToken=o9nXy2N8cgdG0_N5Iz8CYnt-; RTYCID=4ce5b0431c934dc3bbebe5695ab2863c; bannerFlag=true; token=5d20e41769f143dea5806c52bf6c953b; _utm=2a425496ba624a8482fa563771854afa; tyc-user-info=%257B%2522token%2522%253A%2522eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiIxNTUxNzcwNzkzNSIsImlhdCI6MTUyNjg5Njk1NCwiZXhwIjoxNTQyNDQ4OTU0fQ.daBETlYxMpGXywxEvJCOtHKDFDi0XN-UTJBT9OWe4OaVOfEp_iFMmw3o5mTc-CpDrnF-jCPwxvZK9Iobn9iwRw%2522%252C%2522integrity%2522%253A%25220%2525%2522%252C%2522state%2522%253A%25220%2522%252C%2522redPoint%2522%253A%25220%2522%252C%2522vipManager%2522%253A%25220%2522%252C%2522vnum%2522%253A%25220%2522%252C%2522onum%2522%253A%25220%2522%252C%2522mobile%2522%253A%252215517707935%2522%257D; auth_token=eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiIxNTUxNzcwNzkzNSIsImlhdCI6MTUyNjg5Njk1NCwiZXhwIjoxNTQyNDQ4OTU0fQ.daBETlYxMpGXywxEvJCOtHKDFDi0XN-UTJBT9OWe4OaVOfEp_iFMmw3o5mTc-CpDrnF-jCPwxvZK9Iobn9iwRw; Hm_lvt_e92c8d65d92d534b0fc290df538b4758=1526366266,1526368826,1526889740,1526892761; Hm_lpvt_e92c8d65d92d534b0fc290df538b4758=1526896940',
        'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.3964.2 Safari/537.36',
    }
    response = requests.get(url,headers=headers)
    soup =BeautifulSoup(response.text,'lxml')
    companyType=  soup.find('table',class_='table companyInfo-table f14').find_all('td')[8].string   #公司類型
    industry = soup.find('td',colspan="2").string    #行業
    registeredAddress = soup.find('td',colspan="4").text[0:-4]  #註冊地址
    registry = soup.find('table',class_='table companyInfo-table f14').find_all('td')[18].string    #登記機構
    return  [companyName,companyType,industry,registeredAddress,registry]


if __name__ == '__main__':
    start = time.time()
    companyList = getCompanyList()
    for companyName in companyList:
        url = getUrl(companyName)
        try:
            data = qiChaCha(companyName,url)
            print '企業：'+data[0]+'  '+'公司類型:'+data[1]+'  '+'行業: '+data[2]+'  '+'註冊地址: '+data[3]+'  '+'登記機構:' +data[4]
        except  Exception as e:
            data = qiChaCha(companyName, url)
            print '企業：' + data[0] + ' ' + '公司類型:' + data[1] + '' + '行業: ' + data[2] + '' + '註冊地址: ' + data[3] + ' ' + '登記機構:' + data[4]
    end =time.time()
    print end - start

&&&&