Beautifulsoup的使用

時間 2019-12-14

標籤 beautifulsoup 使用简体版

原文原文鏈接

from bs4 import BeautifulSoup

# html_doc = """
# <html><head><title>The Dormouse's story</title></head>
# <body>
#
#
# <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,'lxml')
# print(soup) #會將不完整的html文本補充完成
# print(soup.prettify()) #將html文本進行結構劃分

# print(soup.p.b) #查找文本的第一個標籤 <p class="title"><b>The Dormouse's story</b></p>
#查找子孫節點
# print(list(soup.p.descendants))
# print(soup.p.a.text) #顯示標籤內的文本
# print(soup.p.children) #<list_iterator object at 0x00000181ABD6A978> ,迭代器使用list()轉爲列表形式
# print(list(soup.p.children)) #['Once upon a time there were three little sisters; and their names were\n', <a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>, ',\n', <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>, ' and\n', <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>, ';\nand they lived at the bottom of a well.']
# print(soup.p.contents)

# print(soup.a.parent) #查找標籤a的父標籤，包括子標籤和內容
# print(soup.a.parents) #<generator object parents at 0x000001D5FC242A40>
# print(list(soup.a.parents)) #結果類型爲列表，查找全部父標籤包括父標籤的內容，直到document

find和findallhtml

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,'lxml')

# print(soup.find_all('a')) #[<a class="sister" hCSSref="http://example.com/elsie" id="link1">Elsie</a>, <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>, <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
# print(soup.find_all('a',id='link2')) #[<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
# print(soup.find('a',id='link2')) #<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
# print(soup.find(id='link2').attrs['href']) #http://example.C/lacie
# print(soup.find_all(attrs={'class':'sister'})) #[<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>, <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>, <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
# print(soup.find('p').find('b')) #<b>The Dormouse's story</b>

CSS選擇器spa

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,'lxml')
# print(soup.select('p b')) #[<b>The Dormouse's story</b>] 查找p標籤下的b標籤
# print(soup.select('p')[1].select('#link2')[0].attrs['href']) #http://example.com/lacie 獲取標籤的屬性
# print(soup.select('p')[1].get_text()) #獲取標籤的文本內容

相關標籤/搜索

每日一句

每一个你不满意的现在，都有一个你没有努力的曾经。