scrapy Mongodb 储存

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

import pymongo

from scrapy.exceptions import DropItem

class JobsPipeline(object): # (Jobs→自己的项目名)

    def process_item(self, item, spider):

        return item

class MongoPipeline(object):

    collection_name = '表名'

    def __init__(self, mongo_uri, mongo_db):

        self.mongo_uri = mongo_uri

        self.mongo_db = mongo_db

    @classmethod

    def from_crawler(cls, crawler):

        return cls(

            mongo_uri=crawler.settings.get('MONGO_URI'),

            mongo_db=crawler.settings.get('MONGO_DATABASE', 'items')

        )

    def open_spider(self, spider):

        self.client = pymongo.MongoClient(self.mongo_uri)

        self.db = self.client[self.mongo_db]

    def close_spider(self, spider):

        self.client.close()

    def process_item(self, item, spider):

        self.db[self.collection_name].insert(dict(item))

        return item

settings.py

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

# Scrapy settings for Jobs project

#

# For simplicity, this file contains only settings considered important or

# commonly used. You can find more settings consulting the documentation:

#

#     https://doc.scrapy.org/en/latest/topics/settings.html

#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html

#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'Jobs'

SPIDER_MODULES = ['Jobs.spiders']

NEWSPIDER_MODULE = 'Jobs.spiders'

DOWNLOAD_DELAY = 0

ITEM_PIPELINES = {

    # 'zhaopin.pipelines.ZhaopinPipeline': 300,

    'Jobs.pipelines.MongoPipeline': 400

}

MONGO_URL = 'localhost'

MONGO_DATABASE = 'shuju' # 数据库名

# Crawl responsibly by identifying yourself (and your website) on the user-agent

#USER_AGENT = 'Jobs (+http://www.yourdomain.com)'

# 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 https://doc.scrapy.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 = False

# 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 https://doc.scrapy.org/en/latest/topics/spider-middleware.html

#SPIDER_MIDDLEWARES = {

#    'Jobs.middlewares.JobsSpiderMiddleware': 543,

#}

# Enable or disable downloader middlewares

# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html

#DOWNLOADER_MIDDLEWARES = {

#    'Jobs.middlewares.JobsDownloaderMiddleware': 543,

#}

# Enable or disable extensions

# See https://doc.scrapy.org/en/latest/topics/extensions.html

#EXTENSIONS = {

#    'scrapy.extensions.telnet.TelnetConsole': None,

#}

# Configure item pipelines

# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html

#ITEM_PIPELINES = {

#    'Jobs.pipelines.JobsPipeline': 300,

#}

# Enable and configure the AutoThrottle extension (disabled by default)

# See https://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 https://doc.scrapy.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'

# 设置日志级别为Error，低于次级别的日志就出不来

LOG_LEVEL = 'ERROR'

# 禁用日志输出，所有日志都出不来

# LOG_ENABLED=False

# 保持中文，不被Unicode编码

FEED_EXPORT_ENCODING = 'utf-8'