Python的scrapy之爬取链家网房价信息并保存到本地

# -*- 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


class LianjiaItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    houseinfo=scrapy.Field()
    houseurl=scrapy.Field()
    housedizhi=scrapy.Field()
    housexiangxi=scrapy.Field()
    houseprice=scrapy.Field()
    houseperprice=scrapy.Field()
    pass

# -*- 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


class LianjiaPipeline(object):
    def process_item(self, item, spider):
        print(‘房屋信息:‘,item[‘houseinfo‘])
        print(‘房屋链接:‘, item[‘houseurl‘])
        print(‘房屋位置:‘, item[‘housedizhi‘])
        print(‘房屋详细信息:‘, item[‘housexiangxi‘])
        print(‘房屋总价:‘, item[‘houseprice‘],‘万‘)
        print(‘平方米价格:‘, item[‘houseperprice‘])
        print(‘====‘*10)
        return item

import os
print(os.getcwd())
class LianjiaPipeline(object):
    def process_item(self, item, spider):
        with open(‘G:\pythonAI\爬虫大全\lianjia\data\house.txt‘, ‘a+‘, encoding=‘utf-8‘) as fp:
            name=str(item[‘houseinfo‘])
            dizhi=str(item[‘housedizhi‘])
            info=str(item[‘housexiangxi‘])
            price=str(item[‘houseprice‘])
            perprice=str(item[‘houseperprice‘])
            fp.write(name + dizhi + info+ price +perprice+ ‘\n‘)
            fp.flush()
            fp.close()
        return item

    print(‘写入文件成功‘)

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

# Scrapy settings for lianjia 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 = ‘lianjia‘

SPIDER_MODULES = [‘lianjia.spiders‘]
NEWSPIDER_MODULE = ‘lianjia.spiders‘


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = ‘lianjia (+http://www.yourdomain.com)‘

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# 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 = 0.5
# 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 = {
    ‘lianjia.middlewares.LianjiaSpiderMiddleware‘: 543,
    #‘scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware‘ : None,
	#‘lianjia.rotate_useragent.RotateUserAgentMiddleware‘ :400
}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
    ‘lianjia.middlewares.LianjiaDownloaderMiddleware‘: 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 = {
    ‘lianjia.pipelines.LianjiaPipeline‘: 300,
    #‘lianjia.iopipelines.LianjiaPipeline‘: 301,
    ‘lianjia.csvpipelines.LianjiaPipeline‘:302,
}

# 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‘


LOG_LEVEL=‘INFO‘
LOG_FILE=‘lianjia.log‘

from scrapy.cmdline import execute

execute([‘scrapy‘, ‘crawl‘, ‘mylianjia‘])