工商营业执照报备信息 抓取脚本

gs_query.py

#!/usr/bin/env python
#coding: utf8

import json, re


import requests
try:
    from bs4 import BeautifulSoup
except:
    import BeautifulSoup

"""
    工商营业执照报备信息 抓取脚本

        也可以使用百度的 Site 命令来查询(这里以上海工商局为例):
            https://www.baidu.com/s
                ?wd=site%3A%20www.sgs.gov.cn
                &pn=10&oq=site%3A%20www.sgs.gov.cn
                &ie=utf-8
                &usm=1
                &rsv_idx=1
                &rsv_pq=eebb46df0000c4c9
                &rsv_t=9ad1PvQgC5mDQX%2BEDu%2F%2Bk6LbiKQ802nBP2ksQkMM4dHpuIwRTpXO2uJEOX0
                &rsv_page=1
  Note:
    不同的地区，查询的地址亦不一样，这里使用的是上海工商局查询地址。
"""

def trim(s):
    s = re.sub("\r\n", "\n", re.sub("\t", " ", s) )
    s = re.sub("\s+", " ", s)
    return re.sub("^\n+|\n+$", "", s )

def query(eid):
    url = "http://www.sgs.gov.cn/lz/etpsInfo.do?method=viewDetail"    
    data = {"etpsId": str(eid)} # etpsId: 260000012015080700015
    headers = {
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.71 Safari/537.36",
        "Referer": "http://www.sgs.gov.cn/lz/etpsInfo.do?method=doSearch",
        #"Upgrade-Insecure-Requests": "1",
    }
    r = requests.post(url, data=data, headers=headers)
    return parse(r.content)

def parse(content):
    DOM = BeautifulSoup(content, 'html.parser')

    result = {}

    rlist = DOM.find_all("table", class_="list")
    if rlist == None or rlist == "": rlist = []
    if len(rlist) < 2:
        print "ERROR: HTML 无法解析."
        return ""
    table = rlist[1]

    # 企业基本信息
    company_info = table.find("table", id="resultTbInfo")
    
    nodes = company_info.findChildren()
    section_title = trim(nodes[0].find("td", class_="info_title").string).replace(" ", "")
    section_content = nodes[1].find_next().find_next()
    try:
        title = trim(section_content.find("center", class_="info_table_head").string).replace(" ", "")
        rows = section_content.find("table", class_="list_boder").findChildren()
    except:
        print "WARN: 解析异常."
        return {}
    result[section_title] = {title: {}}


    for row in rows:
        cols = row.find_all("td")
        if len(cols) % 2 != 0:
            # error ...
            return result
        for col in range(0, len(cols), 2):
            key = trim(cols[col].string).replace("\n", "").replace(" ", "").replace(":", "")
            value = trim(cols[col+1].string).replace("\n", "")
            result[section_title][title][key] = value
    


    # 工商年检信息
    section = table.find("table", id="resultTbAnnl")
    section_title = trim(section.findChildren()[0].find("td", class_="info_title").string).replace(" ", "")
    section_content = section.findChildren()[1].find_next().find_next()
    rows = section_content.find("table", class_="list_boder").findChildren()
    
    result[section_title] = {}
    for row in rows:
        cols = row.find_all("td")
        if len(cols) % 2 != 0:
            # error ...
            return result
        for col in range(0, len(cols), 2):
            key = trim(cols[col].string).replace("\n", "").replace(" ", "").replace(":", "")
            value = trim(cols[col+1].string).replace("\n", "")
            result[section_title][key] = value
    """
        {
            "工商年检信息":{
                "年检年度":"年检状态或结果"
            },
            "企业基本信息":{
                "企业法人营业执照":{
                    "注册资本":"1000.000000  万人民币 ",
                    "经营范围":"从事信息科技领域内的技术开发、技术咨询、技术服务 ....",
                    "公司类型":"有限责任公司（国内合资）",
                    "成立日期":" 2015年08月07日 ",
                    "注册号":"310120002873260",
                    "受理机关":"奉贤区市场监管局",
                    "住所":"上海市奉贤区青村镇光明东街1号第20幢2140室",
                    "法定代表人姓名":"彭铭海",
                    "企业状态":"确立",
                    "营业期限":"2015年08月07日 至2045年08月06日",
                    "名称":"上海萌萃信息科技有限公司",
                    "登记机关":"奉贤区市场监管局"
                }
            }
        }

    """
    return result

def report(result):
    for key in result.keys():
        print u"%s :" % (key)
        if type(result[key]) == type({}):
            
            for skey in result[key].keys():
                print u"\t %s :" % (skey)
                if type(result[key][skey]) == type({}):
                    for tkey in result[key][skey].keys():
                        print u"\t\t %s :" % (tkey)
                        print u"\t\t\t %s: %s" %(tkey, result[key][skey][tkey])
        else:
            print u"%s : %s" % (key, result[key])
"""
etpsId:
    length: 21

260000012015080700015
"""
for i in range(260000012015080700015, 260000012015080700300):
    report(query(str(i)))