                        課程
                    
                        /后端開(kāi)發(fā)
                        
                            /Python
                        
                        /Python開(kāi)發(fā)簡(jiǎn)單爬蟲(chóng)

Python3用eclipse編寫(xiě)本節(jié)課編碼，順利完成

# -*- coding: gb2312 -*-
from bs4 import BeautifulSoup
import re
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
The Dormouse's story

Once upon a time there were three little sisters; and their names were
<a href="<a href="<a href="and they lived at the bottom of a well.

...
"""

soup = BeautifulSoup(html_doc, 'html.parser')????? # 創(chuàng)建對(duì)象

print('--------------獲取所有的鏈接----------------')??????????????????????????????????????????????? # 提取出所有的連接
links = soup.find_all('a')
for link in links:
??? print(link.name, link['href'],link.get_text() )
???
print('-------------------------------------獲取lacie的鏈接------------------------------')
link_node = soup.find('a', )
print(link_node.name, link_node['href'],link_node.get_text())

print('-----------------------------------------模糊匹配/正則匹配--------------------------------------')
link_node = soup.find('a', href=re.compile(r"ill"))
print(link_node.name, link_node['href'],link_node.get_text)

print('----------------------------------獲取p段落文字----------------------------------------------')
p_node = soup.find("p", class_ = "title")
print(p_node.name, p_node.get_text())