爬虫的第一课
2017-12-31 本文已影响0人
XY圆圆
from bs4 import BeautifulSou
with open('C:/Users/alien/Desktop/web/new_index.html','r') as wb_data:
Soup = BeautifulSoup(wb_data,'lxml')
images = Soup.select('body > div.main-content > ul > li > img')
titles = Soup.select('body > div.main-content > ul > li > div.article-info > h3 > a')
descs = Soup.select('body > div.main-content > ul > li > div.article-info > p.description')
rates = Soup.select('body > div.main-content > ul > li > div.rate > span')
cates = Soup.select('body > div.main-content > ul > li > div.article-info > p.meta-info > span')
print(images,titles,descs,rates,cates,sep='\n-------------\n')