宜搜全站数十万小说爬虫

自从看了师傅爬了顶点全站之后，我也手痒痒的，也想爬一个比较牛逼的小说网看看，于是选了宜搜这个网站，好了，马上开干，这次用的是mogodb数据库，感觉mysql太麻烦了下图是我选择宜搜里面遍历的网站

Paste_Image.png

先看代码框架图

Paste_Image.png

第一个，肯定先提取排行榜里面每个类别的链接啊，然后进入链接进行爬取，先看all_theme文件

from bs4 import BeautifulSoup
import requests
from MogoQueue import MogoQueue
spider_queue = MogoQueue('novel_list','crawl_queue')#实例化封装数据库操作这个类，这个表是存每一页书籍的链接的
theme_queue = MogoQueue('novel_list','theme_queue')#这个表是存每一个主题页面的链接的
html = requests.get('http://book.easou.com/w/cat_yanqing.html')

soup = BeautifulSoup(html.text,'lxml')

all_list = soup.find('div',{'class':'classlist'}).findAll('div',{'class':'tit'})
for list in all_list:
    title = list.find('span',{'class':'name'}).get_text()
    book_number = list.find('span',{'class':'count'}).get_text()
    theme_link = list.find('a')['href']
    theme_links='http://book.easou.com/'+theme_link#每个书籍类目的数量
    #print(title,book_number,theme_links)找到每个分类的标题和每个类目的链接，然后再下面的links提取出来
    theme_queue.push_theme(theme_links,title,book_number)
links=['http://book.easou.com//w/cat_yanqing.html',
'http://book.easou.com//w/cat_xuanhuan.html',
'http://book.easou.com//w/cat_dushi.html',
'http://book.easou.com//w/cat_qingxiaoshuo.html',
'http://book.easou.com//w/cat_xiaoyuan.html',
'http://book.easou.com//w/cat_lishi.html',
'http://book.easou.com//w/cat_wuxia.html',
'http://book.easou.com//w/cat_junshi.html',
'http://book.easou.com//w/cat_juqing.html',
'http://book.easou.com//w/cat_wangyou.html',
'http://book.easou.com//w/cat_kehuan.html',
'http://book.easou.com//w/cat_lingyi.html',
'http://book.easou.com//w/cat_zhentan.html',
'http://book.easou.com//w/cat_jishi.html',
'http://book.easou.com//w/cat_mingzhu.html',
'http://book.easou.com//w/cat_qita.html',
]
def make_links(number,url):#这里要解释一下，因为每个类目的书页不同，而且最末页是动态数据，源代码没有
    #这里采取了手打上最后一页的方法，毕竟感觉抓包花的时间更多
    for i in range(int(number)+1):
        link=url+'?attb=&s=&tpg=500&tp={}'.format(str(i))
        spider_queue.push_queue(link)#这里将每一页的书籍链接插进数据库
        #print(link)

make_links(500,'http://book.easou.com//w/cat_yanqing.html')
make_links(500,'http://book.easou.com//w/cat_xuanhuan.html')
make_links(500,'http://book.easou.com//w/cat_dushi.html')
make_links(5,'http://book.easou.com//w/cat_qingxiaoshuo.html')
make_links(500,'http://book.easou.com//w/cat_xiaoyuan.html')
make_links(500,'http://book.easou.com//w/cat_lishi.html')
make_links(500,'http://book.easou.com//w/cat_wuxia.html')
make_links(162,'http://book.easou.com//w/cat_junshi.html')
make_links(17,'http://book.easou.com//w/cat_juqing.html')
make_links(500,'http://book.easou.com//w/cat_wangyou.html')
make_links(474,'http://book.easou.com//w/cat_kehuan.html')
make_links(427,'http://book.easou.com//w/cat_lingyi.html')
make_links(84,'http://book.easou.com//w/cat_zhentan.html')
make_links(9,'http://book.easou.com//w/cat_jishi.html')
make_links(93,'http://book.easou.com//w/cat_mingzhu.html')
make_links(500,'http://book.easou.com//w/cat_qita.html')

看看运行结果，这是书籍类目的

Paste_Image.png

这是构造出的每一个类目里面所有的页数链接，也是我们爬虫的入口，一共5000多页

Paste_Image.png

接下来是封装的数据库操作，因为用到了多进程以及多线程每个进程，他们需要知道那些URL爬取过了、哪些URL需要爬取！我们来给每个URL设置两种状态：
outstanding:等待爬取的URL
complete:爬取完成的URL
processing:正在进行的URL。
嗯！当一个所有初始的URL状态都为outstanding；当开始爬取的时候状态改为：processing；爬取完成状态改为：complete；失败的URL重置状态为：outstanding。为了能够处理URL进程被终止的情况、我们设置一个计时参数，当超过这个值时；我们则将状态重置为outstanding。

from pymongo import MongoClient,errors
from _datetime import datetime,timedelta
class MogoQueue():
    OUTSIANDING = 1
    PROCESSING = 2
    COMPLETE = 3
    def __init__(self,db,collection,timeout=300):
        self.client=MongoClient()
        self.Clinet=self.client[db]
        self.db=self.Clinet[collection]
        self.timeout=timeout
    def __bool__(self):
        record = self.db.find_one(
            {'status': {'$ne': self.COMPLETE}}
        )
        return True if record else False
    def push_theme(self,url,title,number):#这个函数用来添加新的URL以及URL主题名字进去队列
        try:
            self.db.insert({'_id':url,'status':self.OUTSIANDING,'主题':title,'书籍数量':number})
            print(title,url,'插入队列成功')
        except errors.DuplicateKeyError as e:#插入失败则是已经存在于队列了
            print(title,url,'已经存在队列中')
            pass
    def push_queue(self,url):
        try:
            self.db.insert({'_id':url,'status':self.OUTSIANDING})
            print(url,'插入队列成功')
        except errors.DuplicateKeyError as e:#插入失败则是已经存在于队列了
            print(url,'已经存在队列中')
            pass
    def push_book(self,title,author,book_style,book_introduction,book_url):
        try:
            self.db.insert({'_id':book_url,'书籍名称':title,'书籍作者':author,'书籍类型':book_style,'简介':book_introduction})
            print(title, '书籍插入队列成功')
        except errors.DuplicateKeyError as e:
            print(title, '书籍已经存在队列中')
            pass


    def select(self):
        record = self.db.find_and_modify(
            query={'status':self.OUTSIANDING},
            update={'$set':{'status': self.PROCESSING, 'timestamp':datetime.now() }}
        )
        if record:
            return record['_id']
        else:
            self.repair()
            raise KeyError
    def repair(self):
        record = self.db.find_and_modify(
            query={
                'timestamp':{'$lt':datetime.now()-timedelta(seconds=self.timeout)},
                'status':{'$ne':self.COMPLETE}
            },
            update={'$set':{'status':self.OUTSIANDING}}#超时的要更改状态

        )
        if record:
            print('重置URL',record['_id'])
    def complete(self,url):
        self.db.update({'_id':url},{'$set':{'status':self.COMPLETE}})

接下来是爬虫主程序

from ip_pool_request import html_request
from bs4 import BeautifulSoup
import random
import multiprocessing
import time
import threading
from ip_pool_request2 import download_request
from MogoQueue import MogoQueue
def novel_crawl(max_thread=8):
    crawl_queue = MogoQueue('novel_list','crawl_queue')#实例化数据库操作，链接到数据库，这个是爬虫需要的书籍链接表
    book_list = MogoQueue('novel_list','book_list')#爬取的内容放进这里
    def pageurl_crawler():
        while True:
            try:
                url = crawl_queue.select()#从数据库提取链接，开始抓
                print(url)
            except KeyError:#触发这个异常，则是链接都被爬完了
                print('队列没有数据，你好坏耶')
            else:
               
                data=html_request.get(url,3)
                soup = BeautifulSoup(data,'lxml')

                all_novel = soup.find('div',{'class':'kindContent'}).findAll('li')


                for novel in all_novel:#提取所需要的所以信息
                    text_tag =novel.find('div',{'class':'textShow'})
                    title = text_tag.find('div',{'class':'name'}).find('a').get_text()
                    author = text_tag.find('span',{'class':'author'}).find('a').get_text()
                    book_style = text_tag.find('span',{'class':'kind'}).find('a').get_text()
                    book_introduction= text_tag.find('div',{'class':'desc'}).get_text().strip().replace('\n','')
                    img_tag = novel.find('div',{'class':'imgShow'}).find('a',{'class':'common'})

                    book_url = 'http://book.easou.com/' + img_tag.attrs['href']
                    book_list.push_book(title,author,book_style,book_introduction,book_url)
                    crawl_queue.complete(url)#完成之后改变链接的状态
                    #print(title,author,book_style,book_introduction,book_url)
    threads=[]
    while threads or crawl_queue:
        for thread in threads:
            if not thread.is_alive():
                threads.remove(thread)
        while len(threads)< max_thread:
            thread = threading.Thread(target=pageurl_crawler())#创建线程
            thread.setDaemon(True)#线程保护
            thread.start()
            threads.append(thread)
        time.sleep(5)
def process_crawler():
    process=[]
    num_cups=multiprocessing.cpu_count()
    print('将会启动的进程数为',int(num_cups)-2)
    for i in range(int(num_cups)-2):
        p=multiprocessing.Process(target=novel_crawl)#创建进程
        p.start()
        process.append(p)
        for p in process:
            p.join()
if __name__ == '__main__':
    process_crawler()

让我们来看看结果吧

Paste_Image.png

里面因为很多都是重复的，所有去重之后只有十几万本，好失望......