Python3 selenium爬取苏宁商家联系电话 进阶版

此处使用了selenium插件 使用的是火狐浏览器 信息存储到csv表格里面
前面详细不多讲如果条件不满足自行百度安装 相比上一版本稍微改进 可以输入多词

# -*- coding: utf-8 -*-
"""
Created on Wed Dec 11 20:21:04 2019

@author: Administrator
"""
from selenium import webdriver
import time
import random
import csv
import codecs

li_list = ["洗手液","袜子","卫生纸"]#格式 li_list = ["洗手液","袜子","卫生纸"]
#要爬取的网址 此处网址为搜索详细产品出现的产品搜索结果页
#注意苏宁搜索行业词出现的产品页面是不一样的
wangzhi = "https://search.suning.com/"
#此处为要爬取的页数默认为 50页
yema = 50
#查数用的没啥实际作用
num = 1
#codevs 防止中文写入时乱码
f = codecs.open('123suning.csv','a',encoding='utf-8')
csv_writer = csv.writer(f)
#谷歌
#browser = webdriver.chrom.webdirver.WebDriver(executable_path="chromedriver")
#火狐
browser1 = webdriver.Firefox(executable_path="geckodriver")

def browser_1(url,browser=browser1):
    #打开网页
    browser.get(url)
    '''
    cookie_list = [{这里放登陆账号后的cookie 注意跟下面的有区别}]
    
    
    for item in cookie_list: browser.add_cookie({
        'domain': 'search.suning.com',
        'name': item['name'],
        'value': item['value'],
        'path': '/',
        'expires': None
    })
    '''
    return(browser)
def browser_2(url,browser=browser1):
    #打开网页
    browser.get(url)
    '''
    cookie_list = [{这里放登陆账号后的cookie.注意跟上面的有区别}]
    
    for item in cookie_list: browser.add_cookie({
        'domain': 'product.suning.com',
        'name': item['name'],
        'value': item['value'],
        'path': '/',
        'expires': None
    })
    '''
    return(browser)
for li in li_list:
    print(li)   
    browser = browser_1(wangzhi)
    input_txt = browser.find_element_by_id("sTxt")
    input_txt.send_keys(li)
    browser.find_element_by_id("sBtn").click()
    time.sleep(random.randint(2,5))
    try:
        browser.find_element_by_class_name("close-btn").click()
    except:
        print(li)
    #通过class找到元素
    #input_guanggao = browser.find_element_by_class_name("close-btn")
    #点一下
    #input_guanggao.click()
    #输入
    #input_txt.send_keys("111")
    #翻页键
    #next_page = browser.find_element_by_class_name("next")
    #数据提取
    urls = []
    shopid_list = []
    nub = 1
    for i in range(yema):
        print(i)
        #将滚动条拖到底部
        js="var q=document.documentElement.scrollTop=100000"
        browser.execute_script(js)
        time.sleep(random.randint(3,5))
        shops = browser.find_elements_by_class_name("sellPoint")
        for shop in shops:
            #print(shop)
            #print("*"*10)
            url = shop.get_attribute('href')
            vip = "/0000000000/"
            #去掉重复店铺
            if "https://product.suning.com/" in url:
                shopid = url[27:37]
                #print(shopid)
                if (vip not in url) & (shopid not in shopid_list):
                    shopid_list.append(shopid)
                    urls.append(url)
                    print(i,"--",nub,"--",url)
                    print(shopid)
                    nub += 1
        print(i,"页")
        i += 1
        js="var q=document.documentElement.scrollTop=500"
        browser.execute_script(js)
        time.sleep(random.randint(2,3))
        if i == yema:
            break
        else:
            next_page = browser.find_element_by_class_name("next")
            time.sleep(random.randint(2,3))
            next_page.click()
            time.sleep(random.randint(2,5))
    print("---"*10)
    for ul in urls:
        browser_shop = browser_2(ul)
        time.sleep(2)
       # if browser_shop.find_element_by_id("chead_companyName"):
          #  driver.quit()
        try:
            #公司名称
            chead_companyName = browser_shop.find_element_by_id("chead_companyName")
            #电话
            chead_telPhone = browser_shop.find_element_by_id("chead_telPhone")
            #地址
            chead_companyAddress = browser_shop.find_element_by_id("chead_companyAddress")
            browser_shop.find_element_by_id("chead_road").click()
            #chead_telPhone.find_element_by_xpath("//*[contains(text(),'13816391436')]").click()
            companyName = chead_companyName.text
            if companyName == "":
                companyName = "null"
            telPhone = chead_telPhone.text
            if telPhone == "":
                telPhone = "null"
            companyAddress = chead_companyAddress.text
            if companyAddress == "":
                companyAddress = "null"
            num += 1
            print(companyName,"==",telPhone,"==",companyAddress,"/",li,"/",num)
            csv_writer.writerow([companyName,telPhone,companyAddress])
        except:
            print("错误页面")
        #browser_shop.close()
f.close()
print("结束")      

仅供交流学习!