mycrawl v0.1.19

mycrawl

Developed for yiqicha.net to crawl compamny registration information in Shanghai that is based on the website of http://www.sgs.gov.cn/shaic/. Any question is welcomed, contract zunkun.liu@kyl.biz

This crawler can get company registration information , company certifaction process information.You should provide search parameters to crawler when use this module.

How to use?

1. use npm to get the latest package npm install mycrawl
2. generate you crawler

var Crawler = require('mycrawl').Crawler;
var crawler = new Crawler();

API

searchCompanyInformation

  registrationOptions =  {
    homeRefererUrl: 'http://www.sgs.gov.cn/lz/etpsInfo.do?method=index', // The referer url
    registrationResultsUrl: 'http://www.sgs.gov.cn/lz/etpsInfo.do?method=doSearch', // results for keywords url
    registrationDetailUrl: 'http://www.sgs.gov.cn/lz/etpsInfo.do?method=viewDetail' // url for keywords detail
  }
  var keywords = '上海东风';
  crawler.searchCompanyInformation(registrationOptions, keywords, function(err, registrationResults) {
    //you handle...
  });

getMoreRegistrations

crawler.getMoreRegistrations(registrationOptions, keywords, allpageNo, pageNo, function(err, moreRegistrations) {
      callback(err, moreRegistrations)
    })

searchCompanyNameStatus

var companyStatusOptions = {
  targetUrl: 'http://www.sgs.gov.cn/shaic/workonline/appStat!toNameAppList.action'
};

var keywords = '美孕国际'

crawler.searchCompanyNameStatus(companyStatusOptions, keyword, function(err, companyNameStatusInfo) {
  log(keyword, err, companyNameStatusInfo)
})

searchRegistrationStatus

var registrationStatusOption = {
  targetUrl : 'http://www.sgs.gov.cn/shaic/workonline/appStat!toEtpsAppList.action'
}

var keywords = '上海顺风';

crawler.searchRegistrationStatus(registrationStatusOption, keyword, function(err, registrationStatusInfo) {
  log(keyword, err, registrationStatusInfo)
})

getRegistrationDisclosure

registration disclosure information

  var options = {
  keyword: '310114000233023' // 统一社会信用代码/注册号
}

getCompanyDisclosure

This is the same as getRegistrationDisclosure api , but this is for company disclosure information

License: MIT