python盗墓笔记爬虫爬虫scrapy——MongoDB存储

截止日期2018年5月10日盗墓笔记版本，仅作为参考，因网页格式变化，有一部分未爬取出来

目标网站：盗墓笔记小说网站
目标网址：http://www.daomubiji.com/
目标内容：
    盗墓笔记小说的信息，具体内容包括：
        书标题
        章数
        章标题
    输出结果保存在MongoDB中

xxx\novelspider\novelspider\settings.py

# -*- coding: utf-8 -*-

# Scrapy settings for novelspider project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     http://doc.scrapy.org/en/latest/topics/settings.html
#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'novelspider'

SPIDER_MODULES = ['novelspider.spiders']
NEWSPIDER_MODULE = 'novelspider.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.22 Safari/537.36 SE 2.X MetaSr 1.0'

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
COOKIES_ENABLED = True

MONGODB_HOST = '127.0.0.1'
MONGODB_PORT = 27017
MONGODB_DBNAME = 'jikexueyuan'
MONGODB_DOCNAME = 'Book'

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'novelspider.middlewares.NovelspiderSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'novelspider.middlewares.MyCustomDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'novelspider.pipelines.NovelspiderPipeline': 300,
}
###############################################################################
# 这样在爬虫里调用
# yield item
# 的时候都会由经这个FilePipeline来处理。后面的数字400表示的是优先级。
# 可以在此配置多个Pipeline，scrapy会根据优先级，把item依次交给各个item来处理，每个处理完的结果会传递给下一个pipeline来处理。
# 可以这样配置多个pipeline:
# ITEM_PIPELINES = {
#             'miao.pipelines.Pipeline00': 400,
#             'miao.pipelines.Pipeline01': 401,
#             'miao.pipelines.Pipeline02': 402,
#             'miao.pipelines.Pipeline03': 403,
#             ## ...
#         }
########################################################################################

# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage

xxx\novelspider\novelspider\pipelines.py

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
from items import NovelspiderItem
from scrapy.conf import settings #使得settings的配置项在这里可以使用
import pymongo

class NovelspiderPipeline(object):
    def __init__(self):
        host = settings['MONGODB_HOST'] # IP
        port = settings['MONGODB_PORT']# 端口号
        dbName = settings['MONGODB_DBNAME']# 数据库的名字
        # client = pymongo.MongoClient(host=host,port=port)#括号里面的可有可无，因为数据库在本地
        client = pymongo.MongoClient(host=host, port=port)
        tdb = client[dbName]
        self.post = tdb[settings['MONGODB_DOCNAME']]# 记录的名字Book

    def process_item(self, item, spider):
        bookInfo = dict(item)#将item转化为字典并插入到数据库里面
        self.post.insert(bookInfo)
        return item

# 网上查询pymongo初始化数据库
# from pymongo import MongoClient
# client = MongoClient()
# #创建数据库，两种方式
# db = client.peopleinfo     #方式一
# db = client['peopleinfo']  #方式二

xxx/novelspider/main.py

#encoding=utf-8
from scrapy import cmdline
cmdline.execute("scrapy crawl novelspider".split())
#使用scrapy里面负责执行Windows命令的一个类，执行scrapy crawl doubanTest，这个命令是爬虫运行，这与
# 平常的python程序不一样，之前运行程序是使用python，然后是这个程序的名字，
#cmd对应文件夹（doubantest）下中输入scrapy crawl doubanTest

xxx\novelspider\novelspider\items.py

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html

# import scrapy
from scrapy import Field,Item


class NovelspiderItem(Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    # pass
    bookName = Field()
    chapterURL = Field()
    bookTitle = Field()
    chapterNum = Field()
    chapterName = Field()
    chapterName2 = Field()
    chapterName3 = Field()

    #表征要抓取的数据

xxx\novelspider\novelspider\spiders\novspider.py

#encoding=utf-8

from scrapy.spiders import CrawlSpider
from scrapy.selector import Selector
from novelspider.items import NovelspiderItem
# import redis
from scrapy.http import Request

class novSpider(CrawlSpider):
    name = 'novelspider'
    # redis_key = 'novelspider:start_urls'
    start_urls = ['http://www.daomubiji.com/dao-mu-bi-ji-1']
    # url3 = 'https://movie.douban.com/top250'

    j = 0
    url2 = []
    for i in range(2, 12):
        urls = ['dao-mu-bi-ji-2015', 'sha-hai', 'zang-hai-hua']
        # print urls[j]
        # name = 'novelspider'
        if i < 9:
            a = 'http://www.daomubiji.com/dao-mu-bi-ji-' + str(i)
            url2.append(a)
            # redis_key = 'novelspider:start_urls'
        else:
            a = 'http://www.daomubiji.com/' + urls[j]
            url2.append(a)
            j = j + 1
            # redis_key = 'novelspider:start_urls'
    print url2

    # urls = 'http://www.daomubiji.com/dao-mu-bi-ji-1'
    # start_urls = ['http://www.daomubiji.com/']
    # print start_urls
    # j = 0
    # for i in range(1,12):
    #     urls = ['dao-mu-bi-ji-2015','sha-hai','zang-hai-hua']
    #     # print urls[j]
    #     name = 'novelspider'
    #     if i<9:
    #         start_urls = ['http://www.daomubiji.com/dao-mu-bi-ji-'+str(i)]
    #         redis_key = 'novelspider:start_urls'
    #     else:
    #         start_urls = ['http://www.daomubiji.com/'+ urls[j]]
    #         j = j+1
    #         redis_key = 'novelspider:start_urls'
    #     print start_urls
    #     # start_urls = ['http://www.daomubiji.com/']
    def parse(self,response):
        selector = Selector(response)#处理网页的源代码
        # print response.body
        bookName = selector.xpath('//h1[@class ="focusbox-title"]/text()').extract()[0]
        # print bookName
        # content = selector.xpath('//div[@class ="focusbox-text"]/text()')
        url = selector.xpath('//article[@class="excerpt excerpt-c3"]/a/@href').extract()
        # print url
        excerpts = selector.xpath('//article[@class="excerpt excerpt-c3"]/a/text()').extract()
        print excerpts
        item = NovelspiderItem()
        for i in range(len(url)):
        # for i in range(len(url) + 1):
            item['bookName'] = bookName
            item['chapterURL'] = url[i]
            # print i
            # print item
            # for each in excerpts:
            try:
                item['bookTitle'] = excerpts[i].split(' ')[0]
                item['chapterNum'] = excerpts[i].split(' ')[1]
                item['chapterName'] = excerpts[i].split(' ')[2]
                # item['chapterName2'] = excerpts[i].split(' ')[3]
                # item['chapterName3'] = excerpts[i].split(' ')[4]
            except Exception,e:
                continue
            # try:
            #     item['chapterName'] = excerpts[i].split(' ')[2]
            # except Exception,e:
            #     item['chapterName'] = excerpts[i].split(' ')[1]
            # try:
            #     item['chapterName2'] = excerpts[i].split(' ')[3]
            # except Exception, e:
            #     item['chapterName'] = excerpts[i].split(' ')[2]
            # try:
            #     item['chapterName3'] = excerpts[i].split(' ')[4]
            # except Exception, e:
            #     item['chapterName'] = excerpts[i].split(' ')[3]
            yield item
        for i in range(2, 12):
            yield Request(self.url2[i], callback=self.parse)
           # yield Request(self.urls, callback=self.parse)  # 添加了一个回调函数，函数自身，递归给这个函数自己，并重新爬取
           #  nextLink = selector.xpath('//span[@class="next"]/link/@href').extract()
        #第十页是最后一页，没有下一页的链接
        # if nextLink:
        #     nextLink = nextLink[0]
        #     print nextLink
        #     yield Request(self.url+nextLink,callback=self.parse)#添加了一个回调函数，函数自身，递归给这个函数自己，并重新爬取