python爬虫（一）

抓取 标题，图片，链接，多个文字 list

from bs4 import BeautifulSoup
import requests

url = 'https://cn.tripadvisor.com/Attractions-g60763-Activities-New_York_City_New_York.html'
wb_data  = requests.get(url)
soup     = BeautifulSoup(wb_data.text,'lxml')
titles   =  soup.select('.property_title > a[target="_blank"]')
imgs     =  soup.select('img[width="160"]')
cates    =  soup.select('div.p13n_reasoning_v2')


for title,img,cate in zip(titles,imgs,cates):
    data = {
        'title':title.get_text(),
        'img':img.get('src'),
        'cate': list(cate.stripped_strings),
    }
    print(data)