解析庫-beautifulsoup模塊

時間 2019-11-11

標籤解析 beautifulsoup 模塊简体版

原文原文鏈接

# -*- coding: utf-8 -*-
from bs4 import BeautifulSoup

# 安裝：pip install beautifulsoup4
# Beautiful Soup支持Python標準庫中的HTML解析器,還支持一些第三方的解析器,其中一個是 lxml .根據操做系統不一樣,能夠選擇下列方法來安裝lxml:
# 安裝解析器：pip install lxml
# 另外一個可供選擇的解析器是純Python實現的 html5lib , html5lib的解析方式與瀏覽器相同,能夠選擇下列方法來安裝html5lib:
# 安裝解析器：pip install html5lib


# 基本使用：直接鏈接網頁太麻煩，直接拿下載好的網頁作測試；

# html_doc = """
# <html><head><title>The Dormouse's story</title></head>
# <body>
# <p class="title"><b>The Dormouse's story</b></p>
# <p class="title"><b>The Dormouse's story2</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>
# """

# 基本使用：容錯處理，文檔的容錯能力指的是在HTML代碼不完整的狀況下，使用該模塊能夠識別錯誤
# 使用該Beautifulsoup解析上述代碼，可以獲得一個bearutifulsoup對象，而且按照標準格式輸出
# soup = BeautifulSoup(html_doc,"lxml")    # 具備容錯功能
# print(soup.prettify())     #能夠處理好縮進,按照標準格式輸出
# soup = BeautifulSoup(html_doc,"html.parser")
# print(soup)

# 遍歷文檔樹
# 一、用法
# soup = BeautifulSoup(open("a.html"),"lxml")
# soup = BeautifulSoup(html_doc,"lxml")
# print(soup.p)       #存在多個相同的標籤只返回第一個
# print(soup.a)
# 二、獲取標籤的名稱
# print(soup.p.name)           #獲取該標籤的名稱，不過有點畫蛇添足
# 三、獲取標籤屬性
# print(soup.p.attrs)
# 四、獲取標籤的內容
# print(soup.p.string)      # p下邊沒有子元素的時候返回他的文本，不然返回none
# print(soup.p.strings)       # 拿到p的生成器對象
# print(soup.p.text)            #去文本內容
# for line in soup.stripped_strings:
#     print(line)                 # 去掉空白，打印p的文本內容
# 五、嵌套選擇：
# print(soup.head.title.string)      #標籤嵌套
# print(soup.body.a.string)
# 六、子節點，子孫接點
# print(soup.p.contents)       #取p下邊的全部子節點
# print(soup.p.children)         #獲得一個迭代器，包含p下的全部子節點
# for i in soup.p.children:
#     print(i)
# for i,child in enumerate(soup.p.children):
#     print(i,child)
# print(soup.p.descendants)
# for i,child in enumerate(soup.p.descendants):
#     print(i,child)        # 獲取子孫接點
# 七、父節點，祖先接點
# print(soup.a.parent)          #獲取a的父節點
# print(list(soup.a.parents))     #獲取到a的全部祖先元素、
# 八、兄弟接點
# print(soup.a.next_sibling)     #h獲取a的上一個兄弟
# print(soup.a.previous_sibling)   # h獲取a的下一個兄弟

# print(list(soup.a.next_siblings))    #全部的兄弟列表
# print(soup.a.previous_siblings)     #兄弟的生成器對象

# 搜索文檔樹
# 五種過濾器: 字符串、正則表達式、列表、True、方法

    # 一、字符串：標籤名
    # print(soup.find_all("b"))
    # 二、正則表達式
    # import re
    # print(soup.find_all(re.compile("^b")))
    # 三、列表
    # print(soup.find_all(["a","b"]))     # 找到a或b
    # 四、True
    # print(soup.find_all(True))     #找到全部的tag
    # for tag in soup.find_all(True):
    #     print(tag.name)           #找到全部的標籤名
    # 五、方法:若是沒有合適過濾器,那麼還能夠定義一個方法,方法只接受一個元素參數 ,若是這個方法返回 True 表示當前元素匹配而且被找到,若是不是則反回 False
    # def has_class_but_no_id(tag):
    #     return tag.has_attr("class") and not tag.has_attr("id")
    #
    # print(soup.find_all(has_class_but_no_id))
# find_all( name , attrs , recursive , text , **kwargs )
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p id="my p" class="title"><b id="bbb" class="boldest">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>
"""
import re
from bs4 import BeautifulSoup
soup=BeautifulSoup(html_doc,'lxml')

# 一、name: 搜索name參數的值可使任一類型的 過濾器 ,字符竄,正則表達式,列表,方法或是 True
# print(soup.find_all(name=re.compile("^t")))
# 二、keyword: key=value的形式，value能夠是過濾器：字符串 , 正則表達式 , 列表, True .
# print(soup.find_all(id=re.compile("my")))
# print(soup.find_all(href=re.compile("lacie"),id=re.compile("\d")))
# print(soup.find_all(id=True))?
# # 有些tag屬性在搜索不能使用,好比HTML5中的 data-* 屬性:
# data_soup = BeautifulSoup('<div data-foo="value">foo!</div>','lxml')
# # data_soup.find_all(data-foo="value") #報錯：SyntaxError: keyword can't be an expression
# # 可是能夠經過 find_all() 方法的 attrs 參數定義一個字典參數來搜索包含特殊屬性的tag:
# print(data_soup.find_all(attrs={"data-foo": "value"}))
# # [<div data-foo="value">foo!</div>]
# 三、按照類名查找，注意關鍵字是class_，class_=value,value能夠是五種選擇器之一
# print(soup.find_all('a',class_='sister')) #查找類爲sister的a標籤
# print(soup.find_all('a',class_='sister ssss')) #查找類爲sister和sss的a標籤，順序錯誤也匹配不成功
# print(soup.find_all(class_=re.compile('^sis'))) #查找類爲sister的全部標籤
# 四、attrs
# print(soup.find_all("p",attrs={"class":"story"}))
# 五、text: 值能夠是：字符，列表，True，正則
# print(soup.find_all(text='Elsie'))
# print(soup.find_all('a',text='Elsie'))
# 六、limit參數:若是文檔樹很大那麼搜索會很慢.若是咱們不須要所有結果,可使用 limit 參數限制返回結果的數量.效果與SQL中的limit關鍵字相似,當搜索到的結果數量達到 limit 的限制時,就中止搜索返回結果??
# print(soup.find_all("a",limit=2))
# 七、recursive:調用tag的 find_all() 方法時,Beautiful Soup會檢索當前tag的全部子孫節點,若是隻想搜索tag的直接子節點,可使用參數 recursive=False .
# print(soup.html.find_all("a"))
# print(soup.find_all("a"))
# print(soup.html.find_all("a",recursive=False))



# find( name , attrs , recursive , text , **kwargs )   # 和find_all相似

# html_doc = """
# <html><head><title>The Dormouse's story</title></head>
# <body>
# <p class="title">
#     <b>The Dormouse's story</b>
#     Once upon a time there were three little sisters; and their names were
#     <a href="http://example.com/elsie" class="sister" id="link1">
#         <span>Elsie</span>
#     </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>;
#     <div class='panel-1'>
#         <ul class='list' id='list-1'>
#             <li class='element'>Foo</li>
#             <li class='element'>Bar</li>
#             <li class='element'>Jay</li>
#         </ul>
#         <ul class='list list-small' id='list-2'>
#             <li class='element'><h1 class='yyyy'>Foo</h1></li>
#             <li class='element xxx'>Bar</li>
#             <li class='element'>Jay</li>
#         </ul>
#     </div>
#     and they lived at the bottom of a well.
# </p>
# <p class="story">...</p>
# """
# from bs4 import BeautifulSoup
# soup=BeautifulSoup(html_doc,'lxml')


# css選擇器
# 一、css選擇器
# print(soup.select(".sister span"))

# print(soup.select("#link1"))
# print(soup.select("#link1 span"))

# print(soup.select("#list-2 .element.xxx"))
# print(soup.select("#list-2")[0].select(".element"))
# 二、獲取屬性
# print(soup.select("#list-2 h1")[0].attrs)

# 三、獲取內容
# print(soup.select("#list-2 h1")[0].get_text())

import requests
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="title"><b>The Dormouse's story2</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)     #完整的HTML文檔
# print(soup.text)   #全部網頁的文本信息
# print(soup.p.attrs)     #獲取到第一個p的屬性值
# print(soup.find_all("p"))    #獲取到全部的p標籤的標籤信息
p_s = soup.find_all("p")
# for p in p_s:       #循環每個p標籤
#     print(p.text)    #打印每一個p標籤的文本信息
# for p in p_s:
    # print(p.a)          #打印p下邊的a標籤
# a_l = soup.find("a")
# print(a_l.get("href"))      #獲取到a標籤的href屬性

# a_s = soup.find_all("a",attrs={"class":"sister"})    #找到全部具備sister屬性的a標籤
# print(a_s)

# a_t = soup.find_all("a",text="Elsie")            #獲取到a標籤的文本是elsie的標籤
# print(a_t)


# a_ls = soup.find_all("a")
# for a in a_ls:
#     print(a.get("href"))

# select_a = soup.select("#link1")[0]
# print(select_a)