python网络爬虫三Re正则表达式库及应用实例

导学

Re正则表达式库的基本使用以及实例代码分析

单元7:Re(正则表达式)库入门

正则表达式的概念

regular expression RE用来简洁表达一组字符串的表达式。

# 'PY'
# 'PYY'         等价于    PY+
# 'PYYY'  

正则表达式的语法

主要操作符

语法实例

Re库的基本使用

正则表达式的表示类型

• raw string类型(原生字符串类型，不包含对转义符再次转义的字符串)

表示：r’text‘

类如：r’[1-9]\d{5}’ 表示邮政的

• string类型(识别转义字符)

r’[1-9]\\d{5}’

Re库主要功能函数

1. re.search()
   
   
   

2. re.match()
   
   

3. re.findall()
   
   

4. re.split()
   

4. re.finditer()
   

5. re.sub()
   
   

Re等价使用方法

Re库的match对象

match对象类型：re.Match

Re库的贪婪匹配和最小匹配

• 最小匹配
  

单元8:实例2：淘宝商品比价定向爬虫

实例介绍

实例代码

此处必须注意cookie获取问题

import requests
import re


def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        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'\"raw_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]))
        print("")


def main():
    goods = "书包"
    depth = 2
    start_url = "https://s.taobao.com/search?q=" + goods
    infoList = []
    for i in range(depth):
        try:
            url = start_url + "&s=" + str(44 * i)
            headers = {
    
    
                'user-agent': 'Mozilla/5.0',
                # cookie必须为搜索页面的cookie，eg:搜索书包(任意对象都可以)后打开的页面cookie
                #下面第一个为获取的错误cookie
                #"cookie" : "hng=CN%7Czh-CN%7CCNY%7C156; thw=cn; t=615600637dc36fc1851ba01eca8534a3; xlly_s=1; enc=PDEK5itf5DNzs7PCSkCbh6cT4YDr4u5idya6pE4klhqF0BLMgsCHWSHmIvWlg%2BbTQBzE38KF9vCB6qPVaX8el37xx7dRa7caUHjM9kKgRzE%3D; cna=wxljGDEOk1QCAXjg9N6idWXq; sgcookie=E100sDzX9VERblfLqC3Nz03UEiurTf5R4BVTyTeJSpBaX%2BiSCdra0sCEUn88GDHisEUgwfhfSx68TUMrsMh26ggQgXR8d7maaLra9KROJzUdinY%3D; uc3=nk2=F5RDLeCwFgBqebA%3D&vt3=F8dCvUj5hyS1wIkyNEE%3D&lg2=UtASsssmOIJ0bQ%3D%3D&id2=UUphyItjoO1%2F06pKkg%3D%3D; lgc=tb615899205; uc4=nk4=0%40FY4I7jI%2FEO%2FJrpIrBBPwZnufWIAGcg%3D%3D&id4=0%40U2grE1hJPuV%2FpzjWkvAtvaigTNbJQzov; tracknick=tb615899205; _cc_=VT5L2FSpdA%3D%3D; _m_h5_tk=792e3e0db8e8b40d0ee4854e807c2571_1638018358953; _m_h5_tk_enc=a2693b48ae1bd5dac3d93dde417caeda; mt=ci=-1_0; cookie2=12fac170843c022961d8a5227514026d; _tb_token_=5d6e95e17e3e0; alitrackid=www.taobao.com; lastalitrackid=www.taobao.com; JSESSIONID=BF58315189D98C826FF6829A2758D8C4; uc1=cookie14=Uoe3f4Aw7mtHFw%3D%3D; tfstk=cEHdBdT9iFYnHIrt0XdiF8nyVs0RakSLrMaRehaspeClunXRFsvonxQxqBZzuyKO.; l=eBSdHAnqOvxQwm-8BOfZhurza77TMIRfguPzaNbMiOCP_a1W5Y9fW6IVsNYXCnGVHsq9y3uQQyaYBmLF-yIqJxpswAaZk_DmndC..; isg=BCcnBcJECpxshrBK_3iN5F_itlvxrPuOFeclXfmUmrbd6EaqCH1U3jyuCuj2ANMG"
                'cookie' : 'hng=CN|zh-CN|CNY|156; thw=cn; t=615600637dc36fc1851ba01eca8534a3; xlly_s=1; enc=PDEK5itf5DNzs7PCSkCbh6cT4YDr4u5idya6pE4klhqF0BLMgsCHWSHmIvWlg+bTQBzE38KF9vCB6qPVaX8el37xx7dRa7caUHjM9kKgRzE=; cna=wxljGDEOk1QCAXjg9N6idWXq; sgcookie=E100sDzX9VERblfLqC3Nz03UEiurTf5R4BVTyTeJSpBaX+iSCdra0sCEUn88GDHisEUgwfhfSx68TUMrsMh26ggQgXR8d7maaLra9KROJzUdinY=; uc3=nk2=F5RDLeCwFgBqebA=&vt3=F8dCvUj5hyS1wIkyNEE=&lg2=UtASsssmOIJ0bQ==&id2=UUphyItjoO1/06pKkg==; lgc=tb615899205; uc4=nk4=0@FY4I7jI/EO/JrpIrBBPwZnufWIAGcg==&id4=0@U2grE1hJPuV/pzjWkvAtvaigTNbJQzov; tracknick=tb615899205; _cc_=VT5L2FSpdA==; _m_h5_tk=792e3e0db8e8b40d0ee4854e807c2571_1638018358953; _m_h5_tk_enc=a2693b48ae1bd5dac3d93dde417caeda; mt=ci=-1_0; cookie2=12fac170843c022961d8a5227514026d; _tb_token_=5d6e95e17e3e0; alitrackid=www.taobao.com; lastalitrackid=www.taobao.com; JSESSIONID=D5C9B23C2FE90173D7D5BB009992A9B9; uc1=cookie14=Uoe3f4Aw7mw6vQ==; tfstk=chKFBbclVDnEElSSkMsrRvQWmUVdavflGlWV-e7eWBbjivbhgs2gwOftDOWzQ7bh.; l=eBSdHAnqOvxQwQNjBOfZnurza77TtIRfguPzaNbMiOCPO11w5yRNW6IVsVTeCnGVHs0vP3uQQyaYBkLF7ydqJxpswAaZk_DmndC..; isg=BLa20_JEy6NVP4GdRrNsi_YpB-y41_oRDHx0KiCfxxk0Y1f9gGbZIUAVez8PS_Ip'
            }
            html = requests.get(url, headers=headers)
            parsePage(infoList, html.text)
        except:
            continue
    printGoodsList(infoList)


main()

结果

单元9:实例3：股票数据定向爬虫

待补充