BeautifulSoup随记

 

 

soup = BeautifulSoup(html, 'html.parser')

# <img alt="五洋运河人家" class="lj-lazy" data-original="https://ke-image.ljcdn.com/hdic-resblock/e4262fc4-3e37-4d92-aab5-5479a98bd6cf.jpg.232x174.jpg" src="https://s1.ljcdn.com/pegasus/redskull/images/common/blank.gif?_v=20210723191610" title="五洋运河人家"/>
# print(soup.select('a img')[0]['alt'])
img=soup.select('a img')[0]
print(img['title'],img['src'])
//五洋运河人家 https://s1.ljcdn.com/pegasus/redskull/images/common/blank.gif?_v=20210723191610


info=soup.select('div[class="info"]')
title=info[0].select('div[class="title"] > a')
print(title[0]['title'])
五洋运河人家


houseInfo=soup.select('div[class="houseInfo"] > a')
print(houseInfo[0]['href'], houseInfo[0].get_text())
http://hz.zu.ke.com/zufang/c1811043636979/ 9套正在出租

positionInfo=soup.select('div[class="positionInfo"] > a')
for i in positionInfo:
    print(i['href'], i.get_text())

https://hz.ke.com/xiaoqu/gongshu/ 拱墅
https://hz.ke.com/xiaoqu/gongchenqiao/ 拱宸桥

 

 

 

 

tagList=soup.select('div[class="tagList"] > span') 
for i in tagList: 
  print(i.get_text())
近地铁地铁5号线拱宸桥东站