爬取商品信息

因为是本地网页，网页文件就不上传了
直接上爬取代码

p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 11.0px Menlo}p.p2 {margin: 0.0px 0.0px 0.0px 0.0px; font: 11.0px Menlo; min-height: 13.0px}p.p3 {margin: 0.0px 0.0px 0.0px 0.0px; font: 11.0px Menlo; color: #272ad8}p.p4 {margin: 0.0px 0.0px 0.0px 0.0px; font: 11.0px Menlo; color: #008400}span.s1 {font-variant-ligatures: no-common-ligatures; color: #bb2ca2}span.s2 {font-variant-ligatures: no-common-ligatures}span.s3 {font-variant-ligatures: no-common-ligatures; color: #000000}span.s4 {font-variant-ligatures: no-common-ligatures; color: #272ad8}

from bs4 import BeautifulSoup
import requests

with open('/Users/wangpegnfei/Desktop/Plan-for-combating-master/week1/1_2/1_2answer_of_homework/1_2_homework_required/index.html') as web_data:
    bsObj = BeautifulSoup(web_data, 'lxml')
    images = bsObj.select('div.thumbnail > img')
    titles = bsObj.select('div.caption > h4 > a')
    prices = bsObj.select('div.caption > h4.pull-right')
    stars = bsObj.select('body > div > div > div.col-md-9 > div > div > div > div.ratings > p:nth-of-type(2)')
    reviews = bsObj.select('div.ratings > p.pull-right')
    #print(stars)
    #for star in stars:
        #print(star)

    for image, title, price, star, review in zip(images, titles, prices, stars, reviews):
        data = {
            'title':title.get_text(),
            'image':image.get('src'),
            'price':price.get_text(),
            'star':len(star.find_all('span',{'class':'glyphicon glyphicon-star'})),
            'review':review.get_text()
        }
        print(data)