微信支付服务商java_爬虫微信支付服务商

该脚本使用Python的Selenium库爬取微信支付商户搜索页面的商家信息,包括拓展地域、联系人、电话、邮箱、地址和所属行业等,并将数据保存到MySQL数据库中。通过循环遍历不同页码,获取多条记录,最后对缺失字段进行填充,确保数据完整性。
摘要由CSDN通过智能技术生成

#!/usr/bin/python

# -*- coding: UTF-8 -*-

from selenium import webdriver

from selenium.webdriver.common.keys import Keys

import time

import sys

import pymysql

reload(sys)

sys.setdefaultencoding('utf-8')

driver = webdriver.Firefox(executable_path="/Users/chanming/Desktop/geckodriver")

driver.get("https://pay.weixin.qq.com/index.php/partner/public/search")

time.sleep(2)

st=driver.find_element_by_id('searchPortalText')

st.send_keys(u"付")

driver.find_element_by_id("searchPortalSubmit").click()

time.sleep(3)

alist=list()

# map={'拓展地域:':'dis','联 系 人 :':'userName','电  话:':'phone','邮  箱:':'email','地  址:':'address','所属行业:':'industry'}

map={}

flag=True

for x in xrange(1,23):

nextInput=driver.find_element_by_css_selector('.goto-area input')

nextInput.clear()

nextInput.send_keys(x)

nextButton=driver.find_element_by_css_selector('.goto-area a')

nextButton.click()

time.sleep(1)

searchList=driver.find_elements_by_css_selector('#searchResultList dl')

for comp in searchList:

obj={}

obj['title']=comp.find_element_by_tag_name('dt').text

propNameList=comp.find_elements_by_class_name('lbl')

if flag:

map[propNameList[0].text]='dis'

map[propNameList[1].text]='userName'

map[propNameList[2].text]='phone'

map[propNameList[3].text]='email'

map[propNameList[4].text]='address'

map[propNameList[5].text]='industry'

flag=False

propList=comp.find_elements_by_class_name('ele')

k=0

for propName in propNameList:

obj[map[propName.text]]=propList[k].text

k=k+1

alist.append(obj)

# print len(alist)

driver.close()

db = pymysql.connect(host = '127.0.0.1', port = 3306, user = 'json', passwd = '123456', db = 'youxia', charset="utf8")

cursor = db.cursor()

sql = 'insert into wx_pay_company(dis,userName,phone,email,address,industry,title) values(%s,%s,%s,%s,%s,%s,%s)'

for company in alist:

if not company.has_key('dis'):

company['dis']=''

if not company.has_key('userName'):

company['userName']=''

if not company.has_key('phone'):

company['phone']=''

if not company.has_key('email'):

company['email']=''

if not company.has_key('address'):

company['address']=''

if not company.has_key('industry'):

company['industry']=''

cursor.execute(sql,(company['dis'],company['userName'],company['phone'],company['email'],company['address'],company['industry'],company['title']))

db.commit()

cursor.close()

db.close()

print '运行结束'

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值