利用 selenium 抓取 淘宝信息

Posted 2020-09-21

import lxml
from bs4 import BeautifulSoup
import time
from selenium import webdriver
import re
driver = webdriver.PhantomJS()
driver.set_window_size(1600,20000)
driver.get("https://item.taobao.com/item.htm?spm=2013.1.0.0.bLyAul&id=17676925595")
time.sleep(10)
date=driver.page_source
soup=BeautifulSoup(date,"lxml")
shu_liang=re.findall(r‘.*title="30天内已售出(\d.*?)件‘,str(soup.select(".tb-sell-counter")))
color=re.findall(r‘<li title="(.*)">颜色分类|li title="(.*)">主要颜色‘,str(soup.select(".attributes-list")))
mig="http://"+ re.match(r‘.*?(//.*?alicdn.*?)_50x50.jpg‘,str(soup.select("#J_UlThumb > li > div > a > img"))).group(1)
daytime=time.strftime(‘%Y/%m/%d‘, time.localtime(time.time()))
leimu=soup.select(".tb-pine")[0].get("data-catid")
dates=[mig,shu_liang,color,daytime,leimu]
title=""
driver.save_screenshot(title.join(re.findall("([\u4e00-\u9fa5])",driver.title))+".jpg")
print(dates)
driver.quit()