Question

import re
import requests
import bs4
import datetime
from urllib import quote
import urllib2, cookielib

class smzdm(object):
    def __init__(self):
        pass

    def getoff(self,keyword):

        headers={'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
        'Accept-Encoding':'gzip, deflate, sdch',
        'Accept-Language':'zh-CN,zh;q=0.8,en;q=0.6,zh-TW;q=0.4',
        'Cache-Control':'max-age=0',
        'Connection':'keep-alive',
        'Cookie':'''smzdm_user_source=0976117114331F28EB6D3C3979605D97; __gads=ID=7f857c698119a4fb:T=1473839452:S=ALNI_MYdWGclXArRQSMaAa_ReL0LFFJBfg; __jsluid=1676c2e0d0b8dcf7a752595a8db32ed6; smzdm_wordpress_360d4e510beef4fe51293184b8908074=user%3A5933507146%7C1483103361%7C608649ec42bc38522a6e17f8cd013d9b; smzdm_wordpress_logged_in_360d4e510beef4fe51293184b8908074=user%3A5933507146%7C1483103361%7Ceb944dea579f5e1e0318bef13f2cda21; user-role-smzdm=subscriber; sess=ZGQyYmF8MTQ4MzEwMzM2MXw1OTMzNTA3MTQ2fDlmYWYxYTQxNzIzODliNmI3M2VlY2Q2MzYyM2IwYjYz; user=user%3A5933507146%7C5933507146; PHPSESSID=ecndosaes8t2ddum97c5h60t62; wt3_eid=%3B999768690672041%7C2147461801100790519%232148117884200550731; wt3_sid=%3B999768690672041; smzdm_user_view=453FB6F62468F7F6C548F0B86926372B; crtg_rta=criteo_D_728*90%3D1%3Bcriteo_300600zy03%3D1%3Bcriteo_300250zy02%3D1%3Bcriteo_300250zy01%3D1%3Bcriteo_300250newzy02%3D1%3Bcriteo_300600newzy11%3D1%3B; s_his=%E8%80%B3%E6%B8%A9%E6%9E%AA%2C%E6%96%B0%E5%AE%89%E6%80%A1%20%E5%90%B8%E5%A5%B6%E5%99%A8%2CSCF332%2F01%2C%E6%B8%A9%E5%A5%B6%E5%99%A8%2C%E5%A5%B6%E7%93%B6%E6%B6%88%E6%AF%92%2C%E5%A4%A7%E7%8E%8B%E5%A4%A9%E4%BD%BF%2C%E5%90%B8%E5%A5%B6%E5%99%A8; Hm_lvt_9b7ac3d38f30fe89ff0b8a0546904e58=1480035459; Hm_lpvt_9b7ac3d38f30fe89ff0b8a0546904e58=1481250397; _ga=GA1.2.1138807399.1473839451; _gat_UA-27058866-1=1; amvid=f192af9ebab282d29dc88438c918d2af''',
        'Host':'search.smzdm.com',
        'Upgrade-Insecure-Requests':1,
        'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36'}

        url='http://search.smzdm.com/?c=faxian&s=%s'%keyword

        req=requests.get(url,headers=headers)       
        soup = bs4.BeautifulSoup(req.text, 'lxml')

        soupstr=str(soup)

        start=datetime.datetime.now()

        result=re.findall(r'<a class="z-btn z-btn-red".*? href="(.*?)" onclick="dataLayer.push\((.*?)\)" target="_blank">直达链接</a>.*?  (\d{2}:\d{2})',soupstr,re.S)  #No.1

        #result=re.findall(r'<a class="z-btn z-btn-red".*? href="(.*?)" onclick="dataLayer.push\((.*?)\)" target="_blank">直达链接</a>.*? (\d{2}:\d{2})',soupstr,re.S)  #No.2
        ctime=datetime.datetime.now()-start

        print 'keyword %s has %s results costs %s' %(keyword,len(result),ctime)
        return result

if __name__ == '__main__':
    sm=smzdm()
    sm.getoff('philips')

此代码用于搜索我的关键字smzdm.com（中国电子商务网站），然后返回今天的促销信息。看看No.2 re.findall，它运行1ms。但是No.1 re.findall，它需要差不多3分钟。匹配结果越少，运行时间越长。与它们唯一不同的是在{1}中{1}}和</a>.*?之间还有一个空格而不是第2个。为什么会出现这个问题以及如何优化我的代码。谢谢。

Answer 1

您应该使用美丽的汤树soup来搜索正确的<a> - 标记，例如

buttons = soup.findAll("a", {"class": "z-btn-red"}, text="直达链接")

然后从那里开始。

Answer 2

您应该不使用正则表达式解析HTML。

请参阅one of the most upvoted answer in StackOverflow

你应该使用elemtree或类似的东西。长字符串中的正则表达式耗费大量资源，因此执行速度很慢;无论如何，你最终（几乎可以肯定）得到错误的结果，因为正则表达式只适用于常规语言generated by type three grammars（HTML不是）

带有空格的Python正则表达式运行得非常慢

2 个答案: