爬虫之BeautifulSoup类

安装：pip install BeautifulSoup4

下表列出了主要的解析器,以及它们的优缺点:看个人习惯选取自己喜欢的解析方式

 1 # 获取html代码
 2 import requests
 3 r = requests.get('http://www.python123.io/ws/demo.html')
 4 demo = r.text
 5 from bs4 import BeautifulSoup
 6 soup = BeautifulSoup(demo,'html.parser')
 7 print(soup.prettify()) #按照标准的缩进格式的结构输出，代码如下
 8 
 9  
10   
13  
14  
15   
class="title">
16    
17     The demo python introduces several python courses.
18    
19   
20   
class="course">
21    Python is a wonderful general-purpose programming language. You can learn Python from novice to professional by tracking the following courses:
22    class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">
23     Basic Python
24    
25    and
26    class="py2" href="http://www.icourse163.org/course/BIT-1001870001" id="link2">
27     Advanced Python
28    
29    .
30   
31  
32 

简单浏览数据化方法的用法

 

#demo的源代码
html_d="""


The demo python introduces several python courses.
Python is a wonderful general-purpose programming language. You can learn Python from novice to professional by tracking the following courses:
Basic Python and Advanced Python.

"""
from bs4 import BeautifulSoup
soup=BeautifulSoup(html_d,'html.parser')
# 获取title标签
print(soup.title)
#获取文本内容
print(soup.text)
#获取标签名称
print(soup.title.name)
#获取标签属性
print(soup.title.attrs)
#获取head标签的子节点
print(soup.p.contents)
print(soup.p.children)
#获取所有的a标签
print(soup.find_all('a'))

 

常用解析方法

#demo的源代码
html_d="""


The demo python introduces several python courses.
Python is a wonderful general-purpose programming language. You can learn Python from novice to professional by tracking the following courses:
Basic Python and Advanced Python.

"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html_d,"lxml")
#p下面所有的子节点
print(soup.p.contents) 
soup.contents[0].name
#children本身没有子节点，得到一个迭代器,包含p下所有子节点
print(soup.p.children)
for child in enumerate(soup.p.children):
    print(child)
#子孙节点p下面所有的标签都会出来
print(soup.p.descendants)
for i in enumerate(soup.p.children):
  print(i)
# string 下面有且只有一个子节皆可以取出，如有多个字节则返回为none
print(soup.title.string)
# strings 如果有多个字符串
for string in soup.strings:
    print(repr(string))
#去掉空白
for line in soup.stripped_strings: 
    print(line)
#获取a标签的父节点
print(soup.a.parent) 
#找到a标签的父辈节点
print(soup.a.parents) 
#兄弟节点
print(soup.a.next_sibling) #同一个兄弟
print(soup.a.next_sibling) #上一个兄弟
print(soup.a.next_sibling) #下一个兄弟

find_all的用法( name, attrs, recursive, text, **kwargs)

import re
from bs4 import BeautifulSoup
soup = BeautifulSoup(html_d,"lxml")
# name
for tag in soup.find_all(re.compile('b')):
print(tag.name)
#attrs
print(soup.find_all('p','course'))
#keyword
print(soup.find_all(id='link1'))
#recursive
# print(soup.find_all('a',recursive=False))
# string
# print(soup.find_all(string=re.compile('python')))

小案例

 

import requests
from bs4 import BeautifulSoup
import bs4
#获取URL里面信息
def getHtmlText(url):
    try:
        r= requests.get(url,timeout=30 )
        r.encoding=r.apparent_encoding
        return r.text
    except:
      return ""
#提起网页数据
def fillunivList(ulist,html):
    soup = BeautifulSoup(html,"html.parser")
    for tr in soup.find('tbody').children:
        if isinstance(tr,bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].string,tds[1].string,tds[2].string,tds[3].string])
    pass
#打印数据结果
def printUnivList(ulist,num):
    # tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}\t{:^10}"
    # print(tplt.format('排名', '学校名称', '省份','总分',chr(12288)))
    # for i in range(num):
    #     u = ulist[i]
    #     print(tplt.format(u[0], u[1], u[2],u[3],chr(12288)))
    print("{:^10}\t{:^6}\t{:^10}\t{:^10}".format('排名', '学校名称', '地区', '总分'))
    for i in range(num):
         u = ulist[i]
         print("{:^10}\t{:^6}\t{:^10}\t{:^10}".format(u[0], u[1], u[2], u[3]))
    return
def main():
    unifo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html'
    html = getHtmlText(url)
    fillunivList(unifo,html)
    printUnivList(unifo,20) #打印前20所
main()