【小白菜鳥】有VIP賬號爬企查查資訊，總是被拒絕訪問

# -*- coding-8 -*-

import requests

import lxml

import xlrd

import xlwt

import sys

from bs4 import BeautifulSoup

import xlwt

import time

import urllib





def craw(url, key_word):

    User_Agent = 'Mozilla/5.0 (Windows NT 10.0;Win64; x64) AppleWebKit/537.36(KHTML,like Gecko)Chrome/64.0.3282.140 Safari/537.36 Edge/18.17763'

    re = r'https://www.qcc.com/search?key=' + key_word

    headers = {

        'Accept':'text/html, application/xhtml+xml, application/xml; q=0.9, */*; q=0.8',

        'Accept-Encoding':'gzip, deflate, br',

        'Accept-Language': 'zh-Hans-CN, zh-Hans; q=0.8, en-US; q=0.6, en; q=0.4, ko; q=0.2',

        'Cookie': r'_XXXXXXXXXXXXXXXX',

        'Host': 'www.qcc.com',

        'Upgrade-Insecure-Request':'1',

        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/18.17763',

    }



    try:

        response = requests.get(url, headers=headers)

        if response.status_code != 200:

            response.encoding = 'utf-8'

            print(response.status_code)

            print('ERROR')

        soup = BeautifulSoup(response.text, 'lxml')

    except Exception:

        print('請求都不讓，這企查查是想逆天嗎？？？')

    try:

        com_all_info = soup.find_all(class_='frtrt')[0].tbody

        com_all_info_array = com_all_info.select('td')

        print('開始爬取資料，請勿打開excel')

        # try:

        temp_g_name = com_all_info_array[2].select('a')[0].text  # 公司名稱



        temp_r_name = com_all_info_array[2].select('p')[0].a.text  # 法人名稱



        temp_g_money = com_all_info_array[2].select('p')[0].select('span')[0].text.strip('注冊資本：')  # 注冊資本金



        temp_g_date = com_all_info_array[2].select('p')[0].select('span')[1].text.strip('成立日期：')  # 成立日期



        e = com_all_info_array[2].select('p')[1].select('a')[1]  # 郵箱

        f = e.strip('showHisEmail').strip(';').replace('{','').replace('}','').replace('[','').replace(']','').replace(':','').replace('"','').replace('e','').replace('s','').replace('(','').replace(')','')

        g = f.split(",")



        l = 0

        h = []



        while l < len(g):

            if l % 2 == 0:

                h.append(str(g[l]))

            l += 1



        temp_r_email = '\n'.join(h)



        a = com_all_info_array[2].select('p')[1].select('a')[0]  # 電話



        b = a.strip('showHisTel').strip(';').replace('{','').replace('}','').replace('[','').replace(']','').replace(':','').replace('"','').replace('t','').replace('s','').replace('(','').replace(')','')

        c = b.split(",")



        j = 0

        d = []



        while j < len(c):

            if j % 2 == 0:

                d.append(str(c[j]))

            j += 1



        temp_r_phone = '\n'.join(d)



        temp_g_addr = com_all_info_array[2].select('p')[2].text.strip().strip('地址：')  # 地址



        temp_r_numm = com_all_info_array[2].select('p')[0].select('span')[1].text.strip('統一社會信用代碼：')  # 征信代碼



        g_name_list.append(temp_g_name)



        r_name_list.append(temp_r_name)



        g_money_list.append(temp_g_money)



        g_date_list.append(temp_g_date)



        r_email_list.append(temp_r_email)



        r_phone_list.append(temp_r_phone)



        g_addr_list.append(temp_g_addr)



        r_numm_list.append(temp_r_numm)





    #            except Exception:

    #                print('錯誤！')

    except Exception:

        print('好像被拒絕訪問了呢...請稍后再試叭...')





if __name__ == '__main__':



    global g_name_list



    global r_name_list



    global g_money_list



    global g_date_list



    global r_email_list



    global r_phone_list



    global g_addr_list



    global r_numm_list



    col = []



    data = xlrd.open_workbook(r'C:\企查查資料源.xlsx')



    sheet = data.sheet_by_name('Sheet1')



    col = sheet.col_values(0)



    for key_word in col:

        time.sleep(15)

        key_word = urllib.parse.quote(key_word)

        url = r'https://www.qcc.com/search?key='+key_word

        craw(url, key_word)

    print('正在搜索，請稍后')



    workbook = xlwt.Workbook()



    sheet1 = workbook.add_sheet('企查查資料', cell_overwrite_ok=True)



    style = xlwt.XFStyle()







    font = xlwt.Font()



    font.name = '仿宋'



    font.bold = True





    style.font = font





    print('正在存盤資料，請勿打開excel')



    g_name_list = []



    r_name_list = []



    g_money_list = []



    g_date_list = []



    r_email_list = []



    r_phone_list = []



    g_addr_list = []



    r_numm_list = []



    name_list = ['公司名字','法定法人','注冊資本','成立日期','法人郵箱','法人電話','公司地址','統一社會信用代碼']



    for cc in range(0,len(name_list)):



        sheet1.write(0,cc,name_list[cc],style)



    for i in range(0,len(g_name_list)):



        print(g_name_list[i])



        sheet1.write(i+1,0,g_name_list[i],style)



        sheet1.write(i+1,1,r_name_list[i],style)



        sheet1.write(i+1,2,g_money_list[i],style)



        sheet1.write(i+1,3,g_date_list[i],style)



        sheet1.write(i+1,4,r_email_list[i],style)



        sheet1.write(i+1,5,r_phone_list[i],style)



        sheet1.write(i+1,6,g_addr_list[i],style)



        sheet1.write(i+1,7,r_numm_list[i],style)



    workbook.save(r"C:\Users\Desktop\企查查"+time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) +".xls")



    print('保存完畢~')

uj5u.com熱心網友回復：

標籤：腳本語言(Perl/Python)

上一篇：求教:如何遍歷任何帶有組合的結構體所有成員欄位

下一篇：pip更新失敗