基本用法-获取网页数据,并保持为index.html
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# 导入urllib中的request模块,用来发送http/https请求
from urllib import request
#获取数据
def get_data():
url='https://search.51job.com/list/000000,000000,0000,00,9,99,web,2,1.html'
# 创建Request对象,指定url和请求头
headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
}
req = request.Request(url, headers=headers)
response = request.urlopen(req)
print(type(response)) # HTTPResponse类型
print(response.getcode()) # 响应状态码
print(response.info())
if response.getcode() == 200:
data = response.read() # 读取响应结果
print(type(data)) # bytes类型
data = str(data, encoding='gbk') # 转换为str
print(data)
# 将数据写入文件中
with open('index.html', mode='w', encoding='gbk') as f:
f.write(data)
if __name__ == '__main__':
get_data()
get_text()方法
get_text()
如果只想得到tag中包含的文本内容,那么可以嗲用 get_text() 方法,这个方法获取到tag中包含的所有文版内容包括子孙tag中的内容,并将结果作为Unicode字符串返回:
markup = '<a href="http://example.com/">\nI linked to <i>example.com</i>\n</a>'
soup = BeautifulSoup(markup)
soup.get_text()
u'\nI linked to example.com\n'
soup.i.get_text()
u'example.com'
可以通过参数指定tag的文本内容的分隔符:
# soup.get_text("|")
u'\nI linked to |example.com|\n'
还可以去除获得文本内容的前后空白:
# soup.get_text("|", strip=True)
u'I linked to|example.com'
或者使用 .stripped_strings 生成器,获得文本列表后手动处理列表:
[text for text in soup.stripped_strings]
# [u'I linked to', u'example.com']
处理数据
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# 导入urllib中的request模块,用来发送http/https请求
from urllib import request
#导入beautifulsoup4
from bs4 import BeautifulSoup
#获取数据
def get_data():
url='https://search.51job.com/list/000000,000000,0000,00,9,99,web,2,1.html'
# 创建Request对象,指定url和请求头
headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
}
req = request.Request(url, headers=headers)
response = request.urlopen(req)
# print(type(response)) # HTTPResponse类型
# print(response.getcode()) # 响应状态码
# print(response.info())
if response.getcode() == 200:
data = response.read() # 读取响应结果
# print(type(data)) # bytes类型
data = str(data, encoding='gbk') # 转换为str
# print(data)
# 将数据写入文件中
with open('index.html', mode='w', encoding='gbk') as f:
f.write(data)
# 处理数据
def parse_data():
with open('index2.html', mode='r', encoding='gbk') as f:
html = f.read()
# 创建BeautifulSoup实例,解析html数据
# 指定使用html解析器parser
bs = BeautifulSoup(html, 'html.parser')
#查找数据
# 1.find()方法,获取第一个匹配的标签
# div = bs.find('div')
# print(div)
# print(type(div)) # Tag类型
# 2.find_all()方法,获取所有匹配的标签
# metas = bs.find_all('meta') # 返回的是集合
# print(metas[0])
# print(bs.find_all(id='hello')) # 根据id获取,返回的是集合
# print(bs.find_all(class_='itany')) # 根据class获取
# 3.select()方法,使用CSS选择器来获取元素
# print(bs.select('#hello'))
# print(bs.select('.itany'))
# print(bs.select('p#world span'))
# print(bs.select('[title]'))
# 4.get_text()方法,获取Tag中的文本
value = bs.select('#hello')[0].get_text()
# print(len(value))
print(value)
if __name__ == '__main__':
# get_data()
parse_data()
find_all()
find_all( name , attrs , recursive , text , **kwargs )
find_all() 方法搜索当前tag的所有tag子节点,并判断是否符合过滤器的条件.这里有几个例子:
soup.find_all("title")
# [<title>The Dormouse's story</title>]
soup.find_all("p", "title")
# [<p class="title"><b>The Dormouse's story</b></p>]
soup.find_all("a")
# [<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>]
soup.find_all(id="link2")
# [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
import re
soup.find(text=re.compile("sisters"))
# u'Once upon a time there were three little sisters; and their names were\n'
find()
find( name , attrs , recursive , text , **kwargs )
find_all() 方法将返回文档中符合条件的所有tag,尽管有时候我们只想得到一个结果.比如文档中只有一个<body>标签,那么使用 find_all() 方法来查找<body>标签就不太合适, 使用 find_all 方法并设置 limit=1 参数不如直接使用 find() 方法.下面两行代码是等价的:
soup.find_all('title', limit=1)
# [<title>The Dormouse's story</title>]
soup.find('title')
# <title>The Dormouse's story</title>
唯一的区别是 find_all() 方法的返回结果是值包含一个元素的列表,而 find() 方法直接返回结果.
find_all() 方法没有找到目标是返回空列表, find() 方法找不到目标时,返回 None .
print(soup.find("nosuchtag"))
# None
soup.head.title 是 tag的名字 方法的简写.这个简写的原理就是多次调用当前tag的 find() 方法:
soup.head.title
# <title>The Dormouse's story</title>
soup.find("head").find("title")
# <title>The Dormouse's story</title>
select()
Beautiful Soup支持大部分的CSS选择器 [6] ,在 Tag 或 BeautifulSoup 对象的 .select() 方法中传入字符串参数,即可使用CSS选择器的语法找到tag:
soup.select("title")
# [<title>The Dormouse's story</title>]
soup.select("p nth-of-type(3)")
# [<p class="story">...</p>]
通过tag标签逐层查找:
soup.select("body a")
# [<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>]
soup.select("html head title")
# [<title>The Dormouse's story</title>]
找到某个tag标签下的直接子标签 [6] :
soup.select("head > title")
# [<title>The Dormouse's story</title>]
soup.select("p > a")
# [<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>]
soup.select("p > a:nth-of-type(2)")
# [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
soup.select("p > #link1")
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]
soup.select("body > a")
# []
找到兄弟节点标签:
soup.select("#link1 ~ .sister")
# [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
soup.select("#link1 + .sister")
# [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
通过CSS的类名查找:
soup.select(".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>]
soup.select("[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>]
通过tag的id查找:
soup.select("#link1")
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]
soup.select("a#link2")
# [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
通过是否存在某个属性来查找:
soup.select('a[href]')
# [<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>]
通过属性的值来查找:
soup.select('a[href="http://example.com/elsie"]')
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]
soup.select('a[href^="http://example.com/"]')
# [<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>]
soup.select('a[href$="tillie"]')
# [<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
soup.select('a[href*=".com/el"]')
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]
通过语言设置来查找:
multilingual_markup = """
<p lang="en">Hello</p>
<p lang="en-us">Howdy, y'all</p>
<p lang="en-gb">Pip-pip, old fruit</p>
<p lang="fr">Bonjour mes amis</p>
"""
multilingual_soup = BeautifulSoup(multilingual_markup)
multilingual_soup.select('p[lang|=en]')
# [<p lang="en">Hello</p>,
# <p lang="en-us">Howdy, y'all</p>,
# <p lang="en-gb">Pip-pip, old fruit</p>]
对于熟悉CSS选择器语法的人来说这是个非常方便的方法.Beautiful Soup也支持CSS选择器API,如果你仅仅需要CSS选择器的功能,那么直接使用 lxml 也可以,而且速度更快,支持更多的CSS选择器语法,但Beautiful Soup整合了CSS选择器的语法和自身方便使用API.