Beautiful Soup 之 select详解

最新推荐文章于 2024-08-26 00:35:17 发布

原创最新推荐文章于 2024-08-26 00:35:17 发布 · 1.2k 阅读

5 ·

CC 4.0 BY-SA版权

[code language="python"]
### select 传入tag标签

1. soup.select("title")

2. soup.select("p")

### 通过tag标签逐层查找

1. soup.select("body a")
2. soup.select("html head title")

### 找到某个tag标签下的直接子标签

1. soup.select("p > a")
2. soup.select("p > #link1")

### 找到兄弟节点标签:

1. 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>]

2. soup.select("#link1 + .sister")

[<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
###通过CSS的类名查找:

1. 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>]

2. soup.select("[class~=sister]")

###通过tag的id查找:

1. soup.select("#link1")

[<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]

2. 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>,p <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]

###通过属性的值来查找: 正则表达式

1. soup.select('a[href="http://example.com/elsie"]')

[<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]

2. soup.select('a[href^="http://example.com/"]')

3. soup.select('a[href$="tillie"]')

[<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]

4. soup.select('a[href*=".com/el"]')

[<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]

#实例：：：

#coding:utf-8
import requests, re, sys
from bs4 import BeautifulSoup as bs4
reload(sys)
sys.setdefaultencoding("utf-8")
"""
@author: songhao
@software: PyCharm
@file: demo.py
@time: 2017/7/5 下午5:26
"""
r = requests.get("").content

soup = bs4(r,'lxml')
alists = soup.select('a') #取出的a列表

for a in alists:
# 获取文本
print a.get_text()
print a.string
# 获取link
try:
print a['href']
except:
pass

imges = soup.select('img')
for a in imges:
# # 获取文本
# print a.get_text()
# print a.string
# # 获取link
try:
#获取 src
print a['src'] #
except:
pass

ip = soup.select('.article-content ')
for i in ip:
for p in i.select('p'):
print p

#获取全部img链接
imgz = soup.select('img[src]')

print imgz
for u in imgz:
print u['src']

#以什么开头
print soup.select('img[src^="http://qiniu."]')

#以什么结尾
print soup.select('img[src$=".jpg"]')

#包含
print soup.select('div[class*="crayon"]')
print soup.select('div[class*="crayon"]')

常用的css选择器 http://www.168seo.cn/python/23660.html