单个页面爬虫

from urllib import request
from bs4 import BeautifulSoup
import ssl

ssl._create_default_https_context=ssl._create_unverified_context

#一、网络请求页面
base_url = "http://www.shanbay.com/wordlist/110521/232414/?page=1"
response = request.urlopen(base_url)
html = response.read()

#二、bs4对象创建
soup = BeautifulSoup(html,'lxml')
tr_list=soup.select('.row')
for tr in tr_list:
    td_list=tr.select('td')
    # print(td_list)
    if td_list!=[]:
        word=td_list[0].contents[0].get_text()
        content=td_list[1].get_text()
        print(word,content)

结果如下：