python之re库

raw string 类型（原生字符串类型）

表示为r’text‘         

string类型 需要\\来表示\

有转义字符是建议使用raw string

 

 

 

 

 

 

 

 

贪婪匹配

默认输出匹配最长的子串

 

最小匹配 

 

 

淘宝案例 

import requests
import re
def getHTMLText(url):
    try:
        r=requests.get(url)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        return ""

def parsePage(ilt,html):
    
    try:
        plt=re.findall(r'\"view_price\"\:\"[\d\.]*\"',html)
        tlt=re.findall(r'\"view_title\"\:\".*?\"',html) 
        for i in range(len(plt)):
            price=eval(plt[i].split(':')[1])
            title=eval(tlt[i].split(':')[1])
            ilt.append([price,title])
    except:    
        print("")

def printGoodsList(ilt):
    tplt="{:4}\t{:8}\t{:16}"
    print(tplt.format("序号","价格","商品名称"))
    count=0
    for g in ilt:
        count=count+1
        print(tplt.format(count,g[0],g[1]))
    

def main():
    goods='书'
    depth=0
    start_url='https://s.taobao.com/search?q='+goods
    infoList=[]
    for i in range(depth):
        try:
            url=start_url+'&imgfile=&js=1&stats_click=search_radio_all%3A1&initiative_id=staobaoz_20190417&ie=utf8&bcoffset=3&ntoffset=3&p4ppushleft=1%2C48&s='+str(44*i)
            html=getHTMLText(url)
            parsePage(infoList,html)
        except:
            continue
    printGoodsList(infoList)
main()