                        课程
                    
                        /后端开发
                        
                            /Python
                        
                        /Python开发简单爬虫

本课程全部代码python 3.6.3

from bs4 import BeautifulSoup
import re
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<p class="title"><b>The Dormouse's story</b></p>
<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
soup = BeautifulSoup(html_doc,"html.parser",from_encoding="utf-8")
print("获取所有连接")
links =soup.find_all('a')
for link in links:
        print (link.name,link['href'],link.get_text())

print("获取lacie的连接")
link_node=soup.find('a',href='http://example.com/lacie')
print(link_node.name,link_node['href'],link_node.get_text())

print("正则匹配")
link_node=soup.find('a',href=re.compile(r"ill"))
print(link_node.name,link_node['href'],link_node.get_text())

print("获取P段落文字")
P_node=soup.find('p',class_="title")
print(P_node.name,P_node.get_text())

qq_戏时丶_0

2018-11-27

源自：Python开发简单爬虫 6-4

关注问题我要回答

1253

操作

收起

2 回答

龙宸轩
2018-12-24

python3.7.2(版本)

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="http://example.com/elsie" class="sister" id="link1">Elsie</a>,

<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and

<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;

and they lived at the bottom of a well.

...

"""

soup = BeautifulSoup(

html_doc,

'html.parser',

from_encoding='utf8'

)

link = soup.find('a',class_='sister')

print(link.name,link.get_text())

0 回复有任何疑惑可以回复我~

收起回答

weixin_慕沐5442772
2018-12-24

import re
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story</b></p>

<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>

<p class="story">...</p>
"""
#soup = BeautifulSoup(html_doc, 'html.parser',from_encoding='utf-8')
soup = BeautifulSoup(html_doc, 'html.parser')
print('获取所有的链接')
links = soup.find_all('a')
for link_node in links:
   print(link_node.name, link_node['href'], link_node.get_text())
print('获取Lacie的链接')
link_node = soup.find( 'a', href ='http://example.com/lacie')
print(link_node.name, link_node['href'], link_node.get_text())
print('正则表达式匹配')
link_node = soup.find('a',href = re.compile(r'till'))
print(link_node.name, link_node['href'], link_node.get_text())
print('获取P段落')
p_node = soup.find('p',class_='title')#因为class是python关键字，所以要class属性要写成class_
print(p_node.name, p_node.get_text())