? 内容介绍
>pip install beautifulsoup4
import requests
from bs4 import BeautifulSoup
r = requests.get(‘https://python123.io/ws/demo.html‘)
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
print(soup)
print(soup.prettify()) # 美化输出
Beautiful Soup 库是解析、遍历、维护“标签树”的功能库
| 基本元素 | 说明 |
|---|---|
| Tag | 最基本的信息组织单元 |
| Name | 名字 |
| Attribute | 属性 |
| NavigableString | 标签内非属性字符串 |
| Comment | 标签内字符串的注释部分 |
import requests
from bs4 import BeautifulSoup
r = requests.get(‘https://python123.io/ws/demo.html‘)
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
#print(soup)
print(soup.title)
print(soup.a.name)
print(soup.a.parent.name)
print(soup.a.parent.parent.name)
print(‘--fengexian-----------------‘)
tag = soup.a
print(tag)
print(tag.attrs)
print(tag.attrs[‘class‘])
print(tag.attrs[‘href‘])
print(type(tag.attrs))
print(type(tag))
print(‘--fengexian-------string----------‘)
print(soup.a.string)
print(soup.p.string)
print(‘--fengexian----------注释-------‘)
D:\develop_study\python\Python38-32\python.exe D:/code_file/first_web/爬虫/慕课/慕课01.py
<title>This is a python demo page</title>
a
p
body
--fengexian-----------------
<a class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">Basic Python</a>
{‘href‘: ‘http://www.icourse163.org/course/BIT-268001‘, ‘class‘: [‘py1‘], ‘id‘: ‘link1‘}
[‘py1‘]
http://www.icourse163.org/course/BIT-268001
<class ‘dict‘>
<class ‘bs4.element.Tag‘>
--fengexian-------string----------
Basic Python
The demo python introduces several python courses.
--fengexian----------注释-------
Process finished with exit code 0
| 属性 | 说明 |
|---|---|
| .contents | 子节点的列表，将 |
| .children | 子节点的迭代类型，与.contents类似，用于循环遍历儿子节点 |
| .descendants | 子孙节点的迭代类型，包含所有子孙节点，用于循环遍历 |
Python 3.8.2 (tags/v3.8.2:7b3ab59, Feb 25 2020, 22:45:29) [MSC v.1916 32 bit (Intel)] on win32
Type "help", "copyright", "credits" or "license()" for more information.
>>> import requests
>>> from bs4 import BeautifulSoup
>>> r = requests.get(‘https://python123.io/ws/demo.html‘)
>>> demo = r.text
>>> soup = BeautifulSoup(demo,"html.parser")
>>> soup.head
<head><title>This is a python demo page</title></head>
>>> soup.head.contents
[<title>This is a python demo page</title>]
>>> soup.body.contents
[‘\n‘, <p class="title"><b>The demo python introduces several python courses.</b></p>, ‘\n‘, <p class="course">Python is a wonderful general-purpose programming language. You can learn Python from novice to professional by tracking the following courses:
<a class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">Basic Python</a> and <a class="py2" href="http://www.icourse163.org/course/BIT-1001870001" id="link2">Advanced Python</a>.</p>, ‘\n‘]
>>> len(soup.body.contents)
5
>>> soup.body.contents[1]
<p class="title"><b>The demo python introduces several python courses.</b></p>
>>> for child in soup.body.children:
print(child)
<p class="title"><b>The demo python introduces several python courses.</b></p>
<p class="course">Python is a wonderful general-purpose programming language. You can learn Python from novice to professional by tracking the following courses:
<a class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">Basic Python</a> and <a class="py2" href="http://www.icourse163.org/course/BIT-1001870001" id="link2">Advanced Python</a>.</p>
>>>
| 属性 | 说明 |
|---|---|
| .parent | 节点的父亲标签 |
| .parents | 节点先辈标签的迭代类型，用于循环遍历先辈节点 |
import requests
from bs4 import BeautifulSoup
r = requests.get(‘https://python123.io/ws/demo.html‘)
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
for parent in soup.a.parents:
if parent is None:
print(parent)
else:
print(parent.name)
p
body
html
[document]
| 属性 | 说明 |
|---|---|
| .next_sibling | 返回按照HTML文本顺序的下一个平行节点标签 |
| .previous_sibling | 返回按照HTML文本顺序的上一个平行节点标签 |
| .next_siblings | 迭代类型，返回按照HTML文本顺序的后续所有平行节点标签 |
| .previous_siblings | 迭代类型，返回按照HTML文本顺序的前续所有平行节点标签 |
import requests
from bs4 import BeautifulSoup
r = requests.get(‘https://python123.io/ws/demo.html‘)
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
print(soup.a.next_sibling)
print(soup.a.next_sibling.next_sibling)
print(soup.a.previous_sibling)
print(soup.a.previous_sibling.previous_sibling)
for sibling in soup.a.next_siblings:
print(sibling)
for sibling in soup.a.previous_siblings:
print(sibling)
.prettify
import requests
from bs4 import BeautifulSoup
r = requests.get(‘https://python123.io/ws/demo.html‘)
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
print(soup.prettify)
print("-----------------------------------------------")
print(soup.a.prettify)
原文：https://www.cnblogs.com/chenfei2928/p/12696812.html