# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
# from scrapy.spiders import CrawlSpider, Rule
from scrapy.spiders import Rule
from scrapy_redis.spiders import RedisCrawlSpider
from xiaoshuo.items import XiaoshuoItem

class XsSpider(RedisCrawlSpider):
    name = 'xs'
    # allowed_domains = ['zu.bd.fang.com']
    # start_urls = ['http://zu.bd.fang.com/house/']

    redis_key = "xsSpider:start_urls"

    def __init__(self,*args,**kwargs):
        domain = kwargs.pop('domain','')
        self.allowed_domains = filter(None,domain.split(','))
        super(XsSpider,self).__init__(*args,**kwargs)

    page_link = LinkExtractor(allow = (r'zu.bd.fang.com/house/i\d+/'))

    project_link = LinkExtractor(allow = (r'zu.bd.fang.com/chuzu/3_\d+_1.htm'))

    rules = (
        Rule(page_link),
        Rule(project_link, callback='parse_item'),
    )

    def parse_item(self, response):
        item = XiaoshuoItem()

        item['title'] = response.xpath('//div[@class="wid1200 clearfix"]//h1/text()')[0].extract()

        yield item

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

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


class XiaoshuoItem(Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = Field()

# -*- 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 json

class XiaoshuoPipeline(object):
    def __init__(self):
        self.filename = open('xs.json','wb+')

    def process_item(self, item, spider):
        content = json.dumps(dict(item),ensure_ascii = False)+'\n'
        self.filename.write(content.encode('utf-8'))
        return item

    def close_spider(self,spider):
        self.filename.close()

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

# Scrapy settings for xiaoshuo 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 = 'xiaoshuo'

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

# 使用scrapy-redis 里的去重组件，不使用scrapy默认的去重
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
# 使用scrapy-redis里的调度器组件，不实用scrapy默认的调度器
SCHEDULER = "scrapy_redis.scheduler.Scheduler"

# 允许暂停，redis请求记录不丢失
SCHEDULER_PERSIST = True


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'xiaoshuo (+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 = 2
# 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 = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3493.3 Safari/537.36',
    '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 = {
#    'xiaoshuo.middlewares.XiaoshuoSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'xiaoshuo.middlewares.XiaoshuoDownloaderMiddleware': 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 = {
    'xiaoshuo.pipelines.XiaoshuoPipeline': 300,
    'scrapy_redis.pipelines.RedisPipeline':400,
}

# 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'