Python 爬虫实例（9）—— 搜索爬取淘宝

最新推荐文章于 2025-11-29 16:24:14 发布

原创最新推荐文章于 2025-11-29 16:24:14 发布 · 67 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#python #爬虫 #开发语言

本文介绍了一种使用Python和Selenium库自动抓取淘宝网站商品信息的方法。通过设置Selenium WebDriver，实现了网页的自动化操作，包括搜索关键词、翻页以及抓取商品图片、名称、价格等详细信息。

# coding:utf-8

import json
import redis
import time
import requests
session = requests.session()
import logging.handlers
import pickle
import sys
import re
import datetime
from bs4 import BeautifulSoup


import sys
reload(sys)
sys.setdefaultencoding('utf8')





import datetime
# 生成一年的日期
def dateRange(start, end, step=1, format="%Y-%m-%d"):
    strptime, strftime = datetime.datetime.strptime, datetime.datetime.strftime
    days = (strptime(end, format) - strptime(start, format)).days
    return [strftime(strptime(start, format) + datetime.timedelta(i), format) for i in xrange(0, days, step)]




def spider():
    from selenium import webdriver
    import os
    # 引入chromedriver.exe
    chromedriver = "C:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe"
    os.environ["webdriver.chrome.driver"] = chromedriver
    browser = webdriver.Chrome(chromedriver)

    # 设置浏览器需要打开的url
    url = "https://www.taobao.com/"
    browser.get(url)
    time.sleep(1)

    browser.find_element_by_id("q").send_keys(u'python')
    browser.find_element_by_class_name("btn-search").click()
    time.sleep(5)

    for i in range(1,100):
        browser.find_element_by_xpath('//a[@trace="srp_bottom_pagedown"]').click()
        time.sleep(15)


        result = browser.page_source

        result_replace = str(result).replace('\n','').replace('\r','').replace('\t','').replace(' ','')


        result_replace = re.findall('<divclass="pic-boxJ_MouseEneterLeaveJ_PicBox">(.*?)</div><divclass="ctx-boxJ_MouseEneterLeaveJ_IconMoreNew">(.*?)</div><divclass="rowrow-4g-clearfix">(.*?)</div></div></div>',result_replace)

        print len(result_replace)

        for item in result_replace:

            item_imgurl = re.findall('data-src="(.*?)"alt=',item[0])[0]
            item_name = re.findall('alt="(.*?)"/></a></div><divclass=',item[0])[0]

            item_loation = re.findall('<divclass="location">(.*?)</div>',item[1])[0]

            company_name = re.findall('</span></span><span>(.*?)</span></a></div><divclass="location">',item[1])[0]


            company_price = re.findall('<divclass="priceg_priceg_price-highlight"><span>¥</span><strong>(.*?)</strong></div>',item[1])[0]

            purchase_num = re.findall('<divclass="deal-cnt">(.*?)人付款</div>',item[1])[0]

            print item_imgurl
            print item_name
            print item_loation
            print company_name

            print company_price
            print purchase_num
            print "="*30

            # time.sleep(1000)

    # 关闭浏览器
    # browser.quit()





spider()