爬取征信中国某公司详情页各项

深碍√TFBOYSˉ_ 2022-02-04 17:07 158阅读 0赞

代码如下：

import requests
    from bs4 import BeautifulSoup
    import time
    keyword = input('请输入要查询的公司名称:')
    # url = 'https://www.creditchina.gov.cn/xinyongxinxi/index.html?index=0&keyword=%s'%(kewword)
    headers = {
            'Accept':'*/*',
            'Accept-Language':'zh-CN,zh;q=0.9',
            'Connection':'keep-alive',
            'Cookie':'FSSBBIl1UgzbN7N443S=ZOHeNdsAa1NPxz9eyBLNMFlxx.Be6H2e_qBzTpP_DHwO3qCfY5eQ2xiGZ0vYqLnY; insert1_cookie=76657641; __jsluid=f179712ba4ed88c9e5aa2ca49e9a81ba; __guid=220564254.3713248492679842000.1557054574440.247; Hm_lvt_0076fef7e919d8d7b24383dc8f1c852a=1557054577; browseHistory=%5B%7B%22name%22%3A%22%E5%8C%97%E4%BA%AC%E5%B0%8F%E7%B1%B3%E7%A7%91%E6%8A%80%E6%9C%89%E9%99%90%E8%B4%A3%E4%BB%BB%E5%85%AC%E5%8F%B8%E6%97%A0%E9%94%A1%E5%88%86%E5%85%AC%E5%8F%B8%22%2C%22encryStr%22%3A%22fW9oZnV9Q0ZqeQ%3D%3D%5Cn%22%7D%2C%7B%22name%22%3A%22%E5%8C%97%E4%BA%AC%E5%B0%8F%E7%B1%B3%E7%A7%91%E6%8A%80%E6%9C%89%E9%99%90%E8%B4%A3%E4%BB%BB%E5%85%AC%E5%8F%B8%E6%97%A0%E9%94%A1%E5%88%86%E5%85%AC%E5%8F%B8%22%2C%22encryStr%22%3A%22fW9oZnV9Q0ZqeQ%3D%3D%5Cn%22%7D%2C%7B%22name%22%3A%22%E5%8C%97%E4%BA%AC%E5%B0%8F%E7%B1%B3%E7%A7%91%E6%8A%80%E6%9C%89%E9%99%90%E8%B4%A3%E4%BB%BB%E5%85%AC%E5%8F%B8%E5%90%88%E8%82%A5%E5%88%86%E5%85%AC%E5%8F%B8%22%2C%22encryStr%22%3A%22fWVbc1tDO2M5Mg%3D%3D%5Cn%22%7D%2C%7B%22name%22%3A%22%E5%8C%97%E4%BA%AC%E5%B0%8F%E7%B1%B3%E7%A7%91%E6%8A%80%E6%9C%89%E9%99%90%E8%B4%A3%E4%BB%BB%E5%85%AC%E5%8F%B8%E5%90%88%E8%82%A5%E5%88%86%E5%85%AC%E5%8F%B8%22%2C%22encryStr%22%3A%22fXJbOzZGO3ZReg%3D%3D%5Cn%22%7D%2C%7B%22name%22%3A%22%E5%8C%97%E4%BA%AC%E5%B0%8F%E7%B1%B3%E7%A7%91%E6%8A%80%E6%9C%89%E9%99%90%E8%B4%A3%E4%BB%BB%E5%85%AC%E5%8F%B8%E6%97%A0%E9%94%A1%E5%88%86%E5%85%AC%E5%8F%B8%22%2C%22encryStr%22%3A%22ekExZEFxQ0t7MQ%3D%3D%5Cn%22%7D%5D; Hm_lpvt_0076fef7e919d8d7b24383dc8f1c852a=1557059306; monitor_count=33; FSSBBIl1UgzbN7N443T=3hF7pO0m_smfZRP0HmIwwpN6uhCmQR6C075ydnchtUia7wBRGl0GeY9Pje09PAsrY1QkQZUqpxCY3nYnNECDBk96Qfn7avlKfy71duFaqtNsybweoZnFNgBMwTFHWbbT901cStkB.EFFLvI5rCk844JEBetg2LYNM_Q_RB1EzH.SazrJQOw7YdrToxUkO7673OFFQ5UZo19mKUQy1pWkRJxbyktwMjqBEmOFqHlWz1rxucq',
            'Host':'www.creditchina.gov.cn',
            'Referer':'https://www.creditchina.gov.cn/xinyongxinxi/index.html?index=0&keyword=%E6%8B%9C%E5%85%8B%E6%B4%9B%E5%85%8B',
            'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
            'X-Requested-With':'XMLHttpRequest'
    
    
    }
    page = 1
    while True:
    
        try:
            url = 'https://www.creditchina.gov.cn/api/credit_info_search?keyword=%s&templateId=&page=%d' % (keyword,page)
    
            response = requests.get(url=url,headers = headers)
            # text = response.content.decode('utf-8')
            text = response.json()
            # print(text)
            # with open('xinyong.html','w',encoding='utf-8') as fp:
            #     fp.write(text)
            data = text['data']['results']
            # print(data)
            if data:
                for i in data:
                    headers = {
                        'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
                    }
                    name = i['name']
                    encryStr = i['encryStr'].split('\n')[0]
    
                    # # 信息概览
                    link = 'https://www.creditchina.gov.cn/api/credit_info_detail?encryStr='+encryStr
                    response1 = requests.get(url =link,headers= headers)
                    text1 = response1.json()
                    # print(text1)
                    print('公司名称:',text1['result']['entName'])
                    print('工商注册号:',text1['result']['regno'])
                    print('法人信息:',text1['result']['legalPerson'])
                    print('成立日期:',text1['result']['esdate'])
                    print('企业类型:',text1['result']['enttype'])
                    print('登记机关:',text1['result']['regorg'])
    
                    with open('xinyong.txt','a',encoding='utf-8') as fp:
                        fp.write('公司名称:'+text1['result']['entName']+'工商注册号:'+text1['result']['regno']+'法人信息:'+text1['result']['legalPerson']+'成立日期:'+text1['result']['esdate']+'企业类型:'+text1['result']['enttype']+'登记机关:'+text1['result']['regorg']+'\n')
                    # # 行政许可
                    # link1 ='https://www.creditchina.gov.cn/api/pub_permissions_name?name=%s&page=1&pageSize=10'%(name)
                    # response2 = requests.get(url=link1,headers=headers)
                    # text2 = response2.json()
                    # print(text2)
                    # # print('行政许可:',text2['result']['results'])
                    # # 行政处罚
                    # link3 = 'https://www.creditchina.gov.cn/api/pub_penalty_name?name=%s&page=1&pageSize=10'%(name)
                    # response3 = requests.get(url=link3, headers=headers)
                    # text3 = response3.json()
                    # # print(text3)
                    # # print('行政处罚:',text3['result']['result'])
                    #
                    # # 守信红名单
                    # link4 = 'https://www.creditchina.gov.cn/api/record_param?encryStr=%s&creditType=2&dataSource=0&pageNum=1&pageSize=10'%(encryStr)
                    # response4 = requests.get(url=link,headers =headers)
                    # text4 = response4.json()
                    # # print(text4)
                    # # print('守信红名单',text4['result'])
                    #
                    #
                    # # 重点关注名单
                    # link5 = 'https://www.creditchina.gov.cn/api/record_param?encryStr=%s&creditType=4&dataSource=0&pageNum=1&pageSize=10'%(encryStr)
                    # response5 = requests.get(url = link5,headers =headers)
                    # text5 = response5.json()
                    # # print(text5)
                    # # print('重点关注名单',text5['result'])
                    #
                    # # 黑名单
                    # link6 ='https://www.creditchina.gov.cn/api/record_param?encryStr=%s&creditType=8&dataSource=0&pageNum=1&pageSize=10'%(encryStr)
                    # response6 = requests.get(url=link6,headers=headers)
                    # text6 = response6.json()
                    # print(text6)
                    # print('黑名单',text6['result'])
                    # time.sleep(1)
                    page+=1
    
            else:
                print('没有数据了')
                break
        except Exception as e:
            print('爬取失败',e)

”