python爬虫入门（2）re模块-正则表达式

正则表达式

匹配IP地址

1. import re
2. re.search(r‘(([01]{0,1}\d{0,1}\d|2[0-4]\d|25[0-5])\.){3}([01]{0,1}\d{0,1}\d|2[0-4]\d|25[0-5])‘,‘192.168.1.1‘)

findall:匹配所有，把所有匹配到的字符放到一个列表中并返回

>>> p = re.compile(‘\d+‘)
>>> p.findall(‘3只小甲鱼，15条腿，多出的3条在哪里？‘)
[‘3‘, ‘15‘, ‘3‘]

编译正则表达式   re.compile()

>>> import re
>>> p = re.compile(‘[a-z]+‘)
>>> p
re.compile(‘[a-z]+‘)

>>> p.match("")
>>> print(p.match(""))
None

>>> m = p.match(‘fishc‘)
>>> m  
<_sre.SRE_Match object; span=(0, 5), match=‘fishc‘>

方法：

group()   返回匹配的字符串

start()    返回匹配的开始位置

end()      返回匹配的结束位置

span()    返回一个元组表示匹配位置（开始，结束）

>>> m.group()
‘fishc‘
>>> m.start()
0
>>> m.end()
5
>>> m.span()
(0, 5)

编译标志，详情请查看http://bbs.fishc.com/thread-57207-1-1.html

设置了编译标志符
charref = re.compile(r"""
 &[#]                # 开始数字引用
 (
     0[0-7]+         # 八进制格式
   | [0-9]+          # 十进制格式
   | x[0-9a-fA-F]+   # 十六进制格式
 )
 ;                   # 结尾分号
""", re.VERBOSE)

未设置编译标志符
charref = re.compile("&#(0[0-7]+|[0-9]+|x[0-9a-fA-F]+);")

示例1：从代理网站上爬IP地址

import urllib.request
import re

def open_url(url):
    req = urllib.request.Request(url)
    req.add_header(‘User-Agent‘,‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36‘)
    page = urllib.request.urlopen(req)#获取页面内容
    html = page.read().decode(‘utf-8‘)#解码页面内容
    return html

def get_img(html):
    p = r‘(?:(?:[0,1]?\d?\d|2[0-4]\d|25[0-5])\.){3}(?:[0,1]?\d?\d|2[0-4]\d|25[0-5])‘  #匹配IP地址
    iplist = re.findall(p,html)

    for each in iplist:
        print(each)

if __name__ == ‘__main__‘:
    url = "http://www.xicidaili.com/"
    get_img(open_url(url))

示例2：爬取妹纸图

import urllib.request
import os
import re

def save_imgs(folder,img_addrs):
    for each in img_addrs:
        filename=each.split(‘/‘)[-1]
        with open(filename,‘wb‘) as f:
            img =url_open(each)
            f.write(img)
        print(1)
    print(2)


def url_open(url):
    reg= urllib.request.Request(url)
    reg.add_header(‘User-Agent‘,‘Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36‘)
    response = urllib.request.urlopen(url)
    html= response.read()
    
    return html
def get_page(url):
    html = url_open(url).decode(‘utf-8‘)
    
    #a = html.find(‘current-comment-page‘)+23
    a = re.search (r‘\[\d{1,4}\]‘,html)
    a = a.group()
    b=len(a)
    a=a[1:b-1]
    return a    
def find_imgs(url):
    html =url_open(url).decode(‘utf-8‘)
    img_addrs= []
    a = html.find(‘img src=‘)
    while a != -1:
        b = html.find(‘.jpg‘,a,a+255)
        if b!= -1 :
            if ‘lanya‘ in html[a+9:b+4]:
                pass
            else:
                img_addrs.append(‘http:‘+html[a+9:b+4])
        else:
            b=a+9
        a = html.find(‘img src=‘,b)
    print(img_addrs)
    return img_addrs



def download_mm(folder=‘ooxx‘,pages=4,star=0):
    os.mkdir(folder)
    os.chdir(folder)
    
    url = ‘http://jandan.net/ooxx/‘  #妹子图地址
    #url = ‘http://jandan.net/pic/‘ #无聊图地址
    if star!= 0 :
        page_num = star
    else:
        page_num=int(get_page(url))
    for i in  range(pages):
    
        page_num-=1
        page_url = url + ‘page-‘+str(page_num)+‘#comments‘
       
        img_addrs=find_imgs(page_url)
     
        save_imgs(folder,img_addrs)
        
        print(page_url)
if __name__==‘__main__‘:
    download_mm()

null