爬虫之BeautifuSoup的简单使用

最新推荐文章于 2024-11-20 23:37:43 发布

CodingALife

最新推荐文章于 2024-11-20 23:37:43 发布

阅读量250

点赞数

CC 4.0 BY-SA版权

分类专栏： Python基础详解

本文链接：https://blog.youkuaiyun.com/mingyuli/article/details/79729632

Python基础详解专栏收录该内容

86 篇文章

订阅专栏

from bs4 import BeautifulSoup as bs
import re

html_doc = """
<html><head><title>The Dormouse's story<a>hello</a></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://exampledcom/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 = bs(html_doc, "html.parser")
#print(soup.prettify())
#print(soup.a)
print(soup.title)
print(soup.title.string)
#结果：None
print(soup.title.get_text())
#结果：The Dormouse's storyhello
print(soup.p)
print(soup.p['class'])
#此函数返回列表形式，需要for循环遍历
print(soup.find_all('a'))
for link in soup.findAll('a'):
    print(link.string)
#获取id=link2的标签
print(soup.find(id='link2'))
#获取id=link2的标签的文本
print(soup.find(id='link2').get_text())
#获取p标签中class为title的标签，需要传参，又因为class是关键字，故需要以下格式{}
print(soup.find("p", {"class": "title"}))
print(soup.find("p", {"class": "story"}).get_text())

#找出所有以b开头的标签
for tag in soup.find_all(re.compile("^b")):
    print(tag.name)
#找出所有名字中包含”t”的标签
for tag in soup.find_all(re.compile("t")):
    print(tag.name)

#.在正则表达式中代表任意字符
dat = soup.findAll("a", href=re.compile(r"^http://example.com/"))
print(dat)
#用\.此时进行转移，代表真正的点号
data = soup.findAll("a", href=re.compile(r"^http://example\.com/"))
print(data)https://blog.youkuaiyun.com/qq_29883591/article/details/52984181?locationNum=2&fps=1