python解析html文件，提取标签中一个元素

对于本地html文件
 1 # -*- coding: utf-8 -*-
# 使用BeautifulSoup解析网页
from bs4 import BeautifulSoup

#获取要解析的标签
with open('test.html','r',encoding='utf-8') as wb_data:
    Soup = BeautifulSoup(wb_data,'lxml');    #将要解析的文件传入
    print(Soup);    #打印读入Soup中的内容
    print("!--------------\n")
    shot_name = Soup.select('body > div > div > table > tbody > tr > td > a');     #将要解析的标签元素路径传入
    #shot_name = Soup.select('body > div > div > div > ol > li > a');     #将要解析的标签元素路径传入
        #可以从网站上直接复制
    print(shot_name,sep='\n!!---------------\n');      #打印解析标签元素包含内容
wb_data.close();

#解析标签内容-------使用get_text()获得文本内容,使用get('')方法获取标签属性值
list = [];
for shot in shot_name:
    data = shot.get('href').strip('\/');
    list.append(data);

with open('shot_names.txt', 'w+') as f:
    for i in list:
        f.writelines(i + '\n')

 

2、对于网页

# -*- coding: utf-8 -*-
from bs4 import BeautifulSoup
import requests


url = 'https://hao.360.cn/?a1004'
wb_data = requests.get(url)
soup = BeautifulSoup(wb_data.text,'lxml')   #把web_data变得可读
#解析网页元素，从网站上复制元素的CSS路径
#这里以链接为例
#famous-section > ul.list.first.gclearfix > li:nth-child(7) > a
url_famous = soup.select('#famous-section > ul.list.first.gclearfix > li > a')
#famous-section > ul.list.last.gclearfix > li:nth-child(1) > a
url_famous .append(soup.select('#famous-section > ul.list.last.gclearfix > li > a'))
print(url_famous)
#focus_news > ul > li:nth-child(1) > a
url_focus = soup.select('#focus_news > ul > li > a')
print(url_focus)