from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story<span>lqz</span></b><b>adfasdf<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.prettify())# 遍历 搜索###遍历文档树# 遍历文档树:即直接通过标签名字选择,特点是选择速度快,但如果存在多个相同的标签则只返回第一个# 1、用法 通过 . 遍历
a=soup.html.body.a
a=soup.a
print(a)
# 2、获取标签的名称
soup.a 对象
a=soup.a.name
print(a)
# 3、获取标签的属性
a=soup.a.attrs
a=soup.a.attrs.get('id')
print(a)
a=soup.a.attrs.get('href')
print(a)
# 4、获取标签的内容---文本内容
p=soup.p.text # text 会把当前标签的子子孙孙的文本内容都拿出来,拼到一起print(p)
s1=soup.p.string # 当前标签有且只有自己(没有子标签),把文本内容拿出来print(s1)
s1=list(soup.p.strings) #generator 把子子孙孙的文本内容放到生成器中print(s1)
# 5、嵌套选择 . 完后可以继续再 .print(soup.head.title.text)
# # 6、子节点、子孙节点print(soup.p.contents) # p下所有直接子节点print(list(soup.p.children)) # 得到一个迭代器,包含p下所有直接子节点print(list(soup.p.descendants)) ## 7、父节点、祖先节点print(soup.a.parent) #获取a标签的父节点print(list(soup.a.parents)) #找到a标签所有的祖先节点,父亲的父亲,父亲的父亲的父亲...# 8、兄弟节点print(soup.a.next_sibling) #下一个兄弟print(soup.a.previous_sibling) #上一个兄弟print(list(soup.a.next_siblings)) #下面的兄弟们=>生成器对象print(list(soup.a.previous_siblings)) #上面的兄弟们=>生成器对象
3 bs4搜索文档树
# find:找到最符合的第一个 find_all:找到所有
五种过滤器: 字符串、正则表达式、列表、True、方法
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b class ='baby'>The Dormouse's story<span>lqz</span></b><b>adfasdf<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" xx="xx">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" name="zzz">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
soup = BeautifulSoup(html_doc, 'lxml')
# 五种过滤器: 字符串、正则表达式、列表、True、方法# 字符串 通过字符串查找
a=soup.find(name='a')
a=soup.find_all(name='a',class_='sister')
a=soup.find_all(name='a',id='link1')
a=soup.find(text='Elsie').parent
a=soup.find(href='http://example.com/elsie') # 括号中可以写 name,id,class_,href,text,所有属性
a=soup.find(xx='xx') # 括号中可以写 name:标签名,id,class_,href,text,所有属性
a=soup.find(attrs={'class':'sister'}) # 可以通过attrs传属性
a=soup.find(attrs={'name':'zzz'}) # 可以通过attrs传属性print(a)
# 正则表达式import re
a = soup.find_all(class_=re.compile('^b'))
找出所有有链接的标签
a = soup.find_all(href=re.compile('^http'))
a = soup.find_all(name=re.compile('^b'))
打印出所有图片地址
# print(a)## 列表
a = soup.find_all(name=['b','body','span'])
a = soup.find_all(class_=['sister','title'])
print(a)
# True
a=soup.find_all(href=True)
a=soup.find_all(src=True,name='img')
print(a)
# 方法 查询所有有class但是没有id的标签
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b class ='baby'>The Dormouse's story<span>lqz</span></b><b>adfasdf<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" xx="xx">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" name="zzz">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
soup = BeautifulSoup(html_doc, 'lxml')
# css选择器'''
div
.类名
#id号
div a # div下的子子孙孙中得a
div>a #div直接子节点
'''# res=soup.select('.sister')# res=soup.select('#link1')# res=soup.p.find(name='b').select('span')# print(res)# 以后,基本所有的解析器都会支持两种解析:css,xpath,都可以去页面中复制import requests
res=requests.get('http://it028.com/css-selectors.html')
# res.encoding=res.apparent_encoding
res.encoding='utf-8'# print(res.text)
soup=BeautifulSoup(res.text,'lxml')
res=soup.select('#content > table > tbody > tr:nth-child(14) > td:nth-child(3)')
# //*[@id="content"]/table/tbody/tr[14]/td[3]print(res)
5 selenium基本使用
# requests 发送请求,不能加载ajax # selenium:直接操作浏览器,不是直接发送http请求,而是用代码控制模拟人操作浏览器的行为,js会自动加载# appnium :直接操作手机# 使用步骤(操作什么浏览器:1 谷歌(为例) 2 ie 3 Firefox)1 下载谷歌浏览器驱动(跟浏览器版本一致)
-https://registry.npmmirror.com/binary.html?path=chromedriver/
-浏览器版本:114.0.5735.199
-驱动版本对应
-放到项目路径下
2 写代码
# pip3.8 install seleniumfrom selenium import webdriver
import time
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
service = Service(executable_path='./chromedriver.exe')
bro = webdriver.Chrome(service=service) # 打开了浏览器
bro.get('https://www.baidu.com')
time.sleep(1)
# 有id优先用id找
input_name = bro.find_element(by=By.ID, value='kw')
# 往标签中写内容
input_name.send_keys('性感美女诱惑')
button=bro.find_element(By.ID,'su')
button.click()
time.sleep(2)
bro.close()