[基礎]-beautifulsoup模組使用詳解
阿新 • • 發佈：2018-11-10
BeautifulSoup是一個模組，該模組用於接收一個HTML或XML字串，然後將其進行格式化，之後遍可以使用他提供的方法進行快速查詢指定元素，從而使得在HTML或XML中查詢指定元素變得簡單。
更多詳情參閱中文文件：https://beautifulsoup.readthedocs.io/zh_CN/v4.4.0/
目錄
7. extract,遞迴的刪除所有的標籤，並獲取刪除的標籤
8. decode,轉換為字串（含當前標籤）；decode_contents（不含當前標籤）
9. encode,轉換為位元組（含當前標籤）；encode_contents（不含當前標籤）
15. is_empty_element,是否是空標籤(是否可以是空)或者自閉合標籤，
22. insert_after,insert_before 在當前標籤後面或前面插入
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
asdf
<div class="title">
<b>The Dormouse's story總共</b>
<h1>f</h1>
</div>
<div class="story">Once upon a time there were three little sisters; and their names were
<a class="sister0" id="link1">Els<span>f</span>ie</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.</div>
ad<br/>sf
<p class="story">...</p>
</body>
</html>
"""
soup = BeautifulSoup(html_doc, features="lxml")
# 找到第一個a標籤
tag1 = soup.find(name='a')
# 找到所有的a標籤
tag2 = soup.find_all(name='a')
# 找到id＝link2的標籤
tag3 = soup.select('#link2')安裝：
pip3 install beautifulsoup4使用示例：
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
...
</body>
</html>
"""
soup = BeautifulSoup(html_doc, features="lxml")1. name，標籤名稱
tag = soup.find('a')
name = tag.name # 獲取
print(name)
tag.name = 'span' # 設定
print(soup)2. attr，標籤屬性
tag = soup.find('a')
attrs = tag.attrs # 獲取
print(attrs)
tag.attrs = {'ik':123} # 設定
tag.attrs['id'] = 'iiiii' # 設定
print(soup)3. children,所有子標
body = soup.find('body')
v = body.children4. children,所有子子孫孫標籤
body = soup.find('body')
v = body.descendants5. clear,將標籤的所有子標籤全部清空（保留標籤名）
tag = soup.find('body')
tag.clear()
print(soup)6. decompose,遞迴的刪除所有的標籤
body = soup.find('body')
body.decompose()
print(soup)7. extract,遞迴的刪除所有的標籤，並獲取刪除的標籤
body = soup.find('body')
v = body.extract()
print(soup)8. decode,轉換為字串（含當前標籤）；decode_contents（不含當前標籤）
body = soup.find('body')
v = body.decode()
v = body.decode_contents()
print(v)9. encode,轉換為位元組（含當前標籤）；encode_contents（不含當前標籤）
body = soup.find('body')
v = body.encode()
v = body.encode_contents()
print(v)10. find,獲取匹配的第一個標籤
tag = soup.find('a')
print(tag)
tag = soup.find(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
tag = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
print(tag)11. find_all,獲取匹配的所有標籤
tags = soup.find_all('a')
print(tags)
tags = soup.find_all('a',limit=1)
print(tags)
tags = soup.find_all(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
tags = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
print(tags)
# ####### 列表 #######
# v = soup.find_all(name=['a','div'])
# print(v)
# v = soup.find_all(class_=['sister0', 'sister'])
# print(v)
# v = soup.find_all(text=['Tillie'])
# print(v, type(v[0]))
# v = soup.find_all(id=['link1','link2'])
# print(v)
# v = soup.find_all(href=['link1','link2'])
# print(v)
# ####### 正則 #######
import re
# rep = re.compile('p')
# rep = re.compile('^p')
# v = soup.find_all(name=rep)
# print(v)
# rep = re.compile('sister.*')
# v = soup.find_all(class_=rep)
# print(v)
# rep = re.compile('http://www.oldboy.com/static/.*')
# v = soup.find_all(href=rep)
# print(v)
# ####### 方法篩選 #######
# def func(tag):
# return tag.has_attr('class') and tag.has_attr('id')
# v = soup.find_all(name=func)
# print(v)
# ## get,獲取標籤屬性
# tag = soup.find('a')
# v = tag.get('id')
# print(v)12. has_attr,檢查標籤是否具有該屬性
# tag = soup.find('a')
# v = tag.has_attr('id')
# print(v)13. get_text,獲取標籤內部文字內容
# tag = soup.find('a')
# v = tag.get_text('id')
# print(v)14. index,檢查標籤在某標籤中的索引位置
# tag = soup.find('body')
# v = tag.index(tag.find('div'))
# print(v)
# tag = soup.find('body')
# for i,v in enumerate(tag):
# print(i,v)15. is_empty_element,是否是空標籤(是否可以是空)或者自閉合標籤，
判斷是否是如下標籤：'br' , 'hr', 'input', 'img', 'meta','spacer', 'link', 'frame', 'base'
# tag = soup.find('br')
# v = tag.is_empty_element
# print(v)16. 當前的關聯標籤
# soup.next
# soup.next_element
# soup.next_elements
# soup.next_sibling
# soup.next_siblings
#
# tag.previous
# tag.previous_element
# tag.previous_elements
# tag.previous_sibling
# tag.previous_siblings
#
# tag.parent
# tag.parents17. 查詢某標籤的關聯標籤
# tag.find_next(...)
# tag.find_all_next(...)
# tag.find_next_sibling(...)
# tag.find_next_siblings(...)
# tag.find_previous(...)
# tag.find_all_previous(...)
# tag.find_previous_sibling(...)
# tag.find_previous_siblings(...)
# tag.find_parent(...)
# tag.find_parents(...)
# 引數同find_all18. select,select_one, CSS選擇器
soup.select("title")
soup.select("p nth-of-type(3)")
soup.select("body a")
soup.select("html head title")
tag = soup.select("span,a")
soup.select("head > title")
soup.select("p > a")
soup.select("p > a:nth-of-type(2)")
soup.select("p > #link1")
soup.select("body > a")
soup.select("#link1 ~ .sister")
soup.select("#link1 + .sister")
soup.select(".sister")
soup.select("[class~=sister]")
soup.select("#link1")
soup.select("a#link2")
soup.select('a[href]')
soup.select('a[href="http://example.com/elsie"]')
soup.select('a[href^="http://example.com/"]')
soup.select('a[href$="tillie"]')
soup.select('a[href*=".com/el"]')
from bs4.element import Tag
def default_candidate_generator(tag):
for child in tag.descendants:
if not isinstance(child, Tag):
continue
if not child.has_attr('href'):
continue
yield child
tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator)
print(type(tags), tags)
from bs4.element import Tag
def default_candidate_generator(tag):
for child in tag.descendants:
if not isinstance(child, Tag):
continue
if not child.has_attr('href'):
continue
yield child
tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator, limit=1)
print(type(tags), tags)19. 標籤的內容
# tag = soup.find('span')
# print(tag.string) # 獲取
# tag.string = 'new content' # 設定
# print(soup)
# tag = soup.find('body')
# print(tag.string)
# tag.string = 'xxx'
# print(soup)
# tag = soup.find('body')
# v = tag.stripped_strings # 遞迴內部獲取所有標籤的文字
# print(v)20.append在當前標籤內部追加一個標籤
# tag = soup.find('body')
# tag.append(soup.find('a'))
# print(soup)
#
# from bs4.element import Tag
# obj = Tag(name='i',attrs={'id': 'it'})
# obj.string = '我是一個新來的'
# tag = soup.find('body')
# tag.append(obj)
# print(soup)21.insert在當前標籤內部指定位置插入一個標籤
# from bs4.element import Tag
# obj = Tag(name='i', attrs={'id': 'it'})
# obj.string = '我是一個新來的'
# tag = soup.find('body')
# tag.insert(2, obj)
# print(soup)22. insert_after,insert_before 在當前標籤後面或前面插入
# from bs4.element import Tag
# obj = Tag(name='i', attrs={'id': 'it'})
# obj.string = '我是一個新來的'
# tag = soup.find('body')
# # tag.insert_before(obj)
# tag.insert_after(obj)
# print(soup)23. replace_with 在當前標籤替換為指定標籤
# from bs4.element import Tag
# obj = Tag(name='i', attrs={'id': 'it'})
# obj.string = '我是一個新來的'
# tag = soup.find('div')
# tag.replace_with(obj)
# print(soup)24. 建立標籤之間的關係
# tag = soup.find('div')
# a = soup.find('a')
# tag.setup(previous_sibling=a)
# print(tag.previous_sibling)25. wrap，將指定標籤把當前標籤包裹起來
# from bs4.element import Tag
# obj1 = Tag(name='div', attrs={'id': 'it'})
# obj1.string = '我是一個新來的'
#
# tag = soup.find('a')
# v = tag.wrap(obj1)
# print(soup)
# tag = soup.find('a')
# v = tag.wrap(soup.find('p'))
# print(soup)26. unwrap，去掉當前標籤，將保留其包裹的標籤
# tag = soup.find('a')
# v = tag.unwrap()
# print(soup)========================================end 木風卜雨========================================
========================================end 木風卜雨========================================