[Python知识库]爬虫案例：类和对象思维获取孔夫子旧书网信息

本案例只做学习，不做他用！

import os
import re
import requests
import random
from lxml import etree
from bs4 import BeautifulSoup
import threading


# html提取并存储类
class Get_html:

    def __init__(self):
        self.headers=self.get_headers()
        self.lst=[]

    #headers获取
    def get_headers(self):
        ua = [
            "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
            "Mozilla/5.0 (compatible; Baiduspider-render/2.0; +http://www.baidu.com/search/spider.html)",
            "Baiduspider-image+(+http://www.baidu.com/search/spider.htm)",
            "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 YisouSpider/5.0 Safari/537.36",
            "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)",
            "Mozilla/5.0 (compatible; Googlebot-Image/1.0; +http://www.google.com/bot.html)",
            "Sogou web spider/4.0(+http://www.sogou.com/docs/help/webmasters.htm#07)",
            "Sogou News Spider/4.0(+http://www.sogou.com/docs/help/webmasters.htm#07)",
            "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0);",
            "Mozilla/5.0 (compatible; bingbot/2.0; +http://www.bing.com/bingbot.htm)",
            "Sosospider+(+http://help.soso.com/webspider.htm)",
            "Mozilla/5.0 (compatible; Yahoo! Slurp China; http://misc.yahoo.com.cn/help.html)"
        ]
        headers = {'User-Agent': random.choice(ua),'Cookie':'kfz_uuid=4f06a81d8a81f5b256c7a2e6a89bdab8; PHPSESSID=51qaqh9hvd8e7ni2opq9sebop3; shoppingCartSessionId=856640faec4cf06b5ee437ad09fac1a3; kfz-tid=fe09c868b427ce1d411020c95c147719; TINGYUN_DATA=%7B%22id%22%3A%22XMf0fX2k_0w%23nUhCMQN2SSk%22%2C%22n%22%3A%22WebAction%2FURI%2Fproduct%252Fbrowse%252Fpc%22%2C%22tid%22%3A%222d44bda41e0e86a%22%2C%22q%22%3A0%2C%22a%22%3A1732%7D; Hm_lvt_bca7840de7b518b3c5e6c6d73ca2662c=1638946047; Hm_lpvt_bca7840de7b518b3c5e6c6d73ca2662c=1638946047; Hm_lvt_33be6c04e0febc7531a1315c9594b136=1638946048; Hm_lpvt_33be6c04e0febc7531a1315c9594b136=1638946048; kfz_trace=4f06a81d8a81f5b256c7a2e6a89bdab8|0|16abc3df3300221b|-; reciever_area=1006000000'
                   }
        return headers

    # 类别获取
    def book_type(self):
        lst_name=[]
        lst_type=[]
        url='https://book.kongfz.com/Cwenxue/'
        ip=['139.213.138.156:4210',
            '113.241.139.30:4230',
            '182.136.102.237:4245',
            ]
        proxies={'http':'http://{}'.format(random.choice(ip)),'https':'https://{}'.format(random.choice(ip))}
        html=requests.get(url,headers=self.get_headers()).text
        # print(html)
        bs=BeautifulSoup(html,'lxml')
        type1=bs.select('div.link-item a')
        for type2 in type1:
            l=type2['href']
            type=l[25:-1]
            name=type2.text
            lst_type.append(type)
            lst_name.append(name)

        for a,b in zip(lst_type,lst_name):
            x = {'type': a, 'name': b}
            self.lst.append(x)

        return self.lst


    # 存储html并建立相应文件夹
    def save_html(self,n):
        for type1 in self.lst:
            url = f'https://book.kongfz.com/C{type1["type"]}/w{n}/'
            html=requests.get(url,headers=self.headers)
            html.encoding='utf-8'
            h=html.text

            file = os.path.join('孔夫子旧书网/', type1['name'])
            path=os.path.exists(file)
            os.mkdir(file) if not path else print('文件夹已建立！')
            with open(file+'/'+str(n)+'.html','w+',encoding='utf-8') as f:
                f.write(h)
                print(file+str(n)+'.html','已保存！')



# 数据提取并存储
class Save():
    def __init__(self):
        self.zuozhe=''
        self.name=''
        self.url=''
        self.chubanshe=''
    # 提取html
    def read(self,n,h):
        for h1 in h:
            file = os.path.join('孔夫子旧书网/', h1['name'])
            with open(file+'/'+str(n)+'.html','r',encoding='utf-8') as f:
                text=f.read()
                # print(text)
                resp=re.compile('<div class="title" title="(.*?)">\s*<a href="(.*?)"')
                title=resp.findall(text)
                resp1=re.compile('<div class="zl-isbn-info">\s*<span class="text">(.*?)</span>\s*<span class="text">(.*?)</span>')
                title2=resp1.findall(text)
                for title3 in title2:
                    self.zuozhe=title3[0]
                    self.chubanshe=title3[1]

                for title1 in title:
                    self.name=title1[0]
                    self.url=title1[1]

                content=f'{self.name},{self.url},{self.zuozhe},{self.chubanshe}\n'
                try:
                    with open('孔夫子旧书网.csv','a+',encoding='ANSI') as f:
                        f.write(content)
                except UnicodeEncodeError:
                    print('已存储完毕！')


if __name__ == '__main__':

    path=os.path.exists('孔夫子旧书网')
    os.mkdir('孔夫子旧书网') if not path else print('文件夹已建立！')

    html=Get_html()
    h=html.book_type()#获取类别

    with open('孔夫子旧书网.csv', 'a+', encoding='ANSI') as f:
            f.write(f'{"书名"},{"url"},{"作者"},{"出版社"}')

    t=threading.BoundedSemaphore(5)
    for n in range(1,20):
        # 多线程存储html
        t=threading.Thread(target=html.save_html,args=(n,))
        t.start()

    save_csv = Save()
    for n in range(1,20):
        save_csv.read(n,h)#把html.book_type=h赋值给save_csv做参数，以求调用lst