一.example2包下的
1.re模块的compile函数使用
import repattern=re.compile(r'\d+')
print(pattern)2.match的方法使用
import re
pattern=re.compile(r'\d+')
# m1=pattern.match('one123twothree345four')
#参数2：指定起始位置(包含),参数3：终止位置(包含),注意匹配一次成功后结束
m1=pattern.match('one123twothree345four',3,7)
print(m1.group())3.search方法的使用
import re
pattern=re.compile(r'\d+')
m1=pattern.search('one123twothree345four')
print(m1.group())4.findall方法的使用
import re
pattern=re.compile(r'\d+')result=pattern.findall('hello 123 world 456')
print(result)5.split方法的使用
import restr1='a,b,c'
print(str1.split(','))str2='a,b;;c,d'
pattern=re.compile(r"[\s\,\;]+")
print(pattern.split(str2))
6.sub方法的使用
import re
string='<h1 class="test1">HelloWorld</h1>'pattern=re.compile(r'\d')
print(pattern.sub('2',string))
print(pattern.sub('2',string,1))pattern=re.compile('<(.\\d)\\sclass="(?P<classname>.*?)">.*?</(\\1)>')
print(pattern.search(string).group(3))def fun(m):return 'after sub'+m.group('classname')
print(pattern.sub(fun, string))7.贪婪匹配
import re
string='<h1 class="test1">HelloWorld</h1>'
#贪婪匹配
pattern=re.compile(r'<.\d\sclass=.*>')
print(pattern.search(string).group())
#关闭贪婪匹配
pattern=re.compile(r'<.\d\sclass=.*?>')
print(pattern.search(string).group())8.综合案例
import requests
import re
def handle_detail_re(content):#re.S表示全文匹配# item_search=re.compile('ts_solgcont_title">.*?</div>\r\n\t</div>',re.S)item_search = re.compile('ts_solgcont_title">.*?<div class="ts_solgcont_bot">.*?</div>', re.S)#获取每一条图书的数据all_item=item_search.findall(content)#匹配书名title_search=re.compile('target="_blank">(.*?)</a>')#匹配作者author_search=re.compile('<p>作者(.*?)</p>')for item in all_item:print({"title":title_search.search(item).group(1),"author":author_search.search(item).group(1),})def main():header={"User-Agent":"Mozilla/5.0 (X11; Linux aarch64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36 CrKey/1.54.250320 Edg/135.0.0.0"}booktype=['java','python','c']for key in booktype:url='http://www.cmpedu.com/so.htm?&KEY={}'.format(key)response=requests.get(url,headers=header)handle_detail_re(response.text)if __name__ == '__main__':main()
三.example3下的
安装beautifulsoup4的指令:pip3 install beautifulsoup4
beautifulsoup4:Beautiful Soup（bs4）是一个用于从HTML或XML文件中提取数据的Python库。
1.获取节点
from bs4 import BeautifulSoup
html = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title" name="dromouse"><b>The Dormouse's story</b></p >
<p class="story">Once upon a time there were three little sisters; and their names were
<!-- Elsie -->,and
;
and they lived at the bottom of a well.</p >
<p class="story">...</p >
"""
#参数1:html代码片段
# 参数2：解析器
soup=BeautifulSoup(html,'lxml')
#获得标题
print(soup.title)
#获得头标记
print(soup.head)
#获得体标记
print(soup.body)
#获得标题元素内容
print(soup.title.string)
#获得标记名称
print(soup.title.name)
#默认的模式下只能匹配第一个节点，其他节点会被忽略
print(soup.p)
)