sun scrapy_redis

作者: Aedda | 来源:发表于2019-04-10 20:10 被阅读0次

spiders——Sun1.py

import scrapy
from scrapy.spiders import CrawlSpider,Rule
from scrapy.linkextractors import LinkExtractor
from SunDistributeSpider.items import SundistributespiderItem

class Sun1Spider(CrawlSpider):
    name = 'Sun1'
    allowed_domains = ['wz.sun0769.com']
    start_urls = ['http://wz.sun0769.com/index.php/question/questionType?type=4&page=']

    # 匹配翻页
    pagelink = LinkExtractor(restrict_xpaths=('//div[@class="pagination"]/a[text()=">"]',))
    # 匹配每个帖子的链接
    contentlink = LinkExtractor(restrict_xpaths=('//a[@class="news14"]',))
    rules = [
        Rule(pagelink, follow=True),
        Rule(contentlink, callback='parse_item')
    ]



    def parse_item(self,response):
        print('url:',response.url)
        item = SundistributespiderItem()
        # 标题
        item['name'] = response.xpath('//div[@class="wzy1"]/table[1]//td[2]/span[1]/text()').extract()[0]
        # 编号
        item['number'] = response.xpath('//div[@class="wzy1"]/table[1]//td[2]/span[2]/text()').extract()[0].strip().split(':')[-1]
        # 编号
        item['url'] = response.url
        # 内容
        item['content'] = response.xpath('//div[@class="wzy1"]/table[2]//td[@class="txt16_3"]//text()').extract()
        item['content'] = ''.join(item['content']).strip()

        tmp = response.xpath('//div[@class="wzy3_2"]/span/text()').extract()[0].strip().split(' ')
        item['author'] = tmp[0].split('：')[-1]
        item['pub_date'] = tmp[1].split('：')[-1] + ' '+ tmp[2]

        yield item

spiders——Sun2.py

# -*- coding: utf-8 -*-
import scrapy
from scrapy_redis.spiders import RedisSpider
from ..items import SundistributespiderItem


class Sun2Spider(RedisSpider):
    name = 'Sun2'
    # allowed_domains = ['wz.sun0769.com']
    # start_urls = ['http://wz.sun0769.com/']
    redis_key = 'Sun2:start_urls'
    offset = 0

    def __init__(self, *args, **kwargs):
        # Dynamically define the allowed domains list.
        domain = kwargs.pop('domain', '')
        self.allowed_domains = filter(None, domain.split(','))
        super(Sun2Spider, self).__init__(*args, **kwargs)

    def parse(self, response):
        # 提取每个页面中帖子的链接
        links = response.xpath("//a[@class='news14']/@href").extract()
        print('len:',len(links))
        # 遍历，请求详情页面
        for link in links:
            yield scrapy.Request(link,callback=self.parse_item)

        # 设置页码终止的条件
        if self.offset < 30000:
            self.offset += 30
            yield scrapy.Request(self.url+str(self.offset),callback=self.parse)


    def parse_item(self,response):
        item = SundistributespiderItem()
        # 标题
        item['name'] = response.xpath('//div[@class="wzy1"]/table[1]//td[2]/span[1]/text()').extract()[0]
        # 编号
        item['number'] = response.xpath('//div[@class="wzy1"]/table[1]//td[2]/span[2]/text()').extract()[0].strip().split(':')[-1]
        # 编号
        item['url'] = response.url
        # 内容
        item['content'] = response.xpath('//div[@class="wzy1"]/table[2]//td[@class="txt16_3"]//text()').extract()
        item['content'] = ''.join(item['content']).strip()

        tmp = response.xpath('//div[@class="wzy3_2"]/span/text()').extract()[0].strip().split(' ')
        item['author'] = tmp[0].split('：')[-1]
        item['pub_date'] = tmp[1].split('：')[-1] + ' '+ tmp[2]
        print(tmp)

        yield item

spiders——Sun3.py

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import Rule
from scrapy_redis.spiders import RedisCrawlSpider
from ..items import SundistributespiderItem

class Sun3Spider(RedisCrawlSpider):
    name = 'Sun3'
    # allowed_domains = ['wz.sun0769.com']
    # start_urls = ['http://wz.sun0769.com/']
    redis_key = 'Sun3:start_urls'

    def __init__(self, *args, **kwargs):
        # Dynamically define the allowed domains list.
        domain = kwargs.pop('domain', '')
        self.allowed_domains = filter(None, domain.split(','))
        super(Sun3Spider, self).__init__(*args, **kwargs)

    # 匹配翻页
    pagelink = LinkExtractor(restrict_xpaths=('//div[@class="pagination"]/a[text()=">"]',))
    # 匹配每个帖子的链接
    contentlink = LinkExtractor(restrict_xpaths=('//a[@class="news14"]',))
    rules = [
        Rule(pagelink, follow=True),
        Rule(contentlink, callback='parse_item')
    ]


    def parse_item(self,response):
        print('url:',response.url)
        item = SundistributespiderItem()
        # 标题
        item['name'] = response.xpath('//div[@class="wzy1"]/table[1]//td[2]/span[1]/text()').extract()[0]
        # 编号
        item['number'] = response.xpath('//div[@class="wzy1"]/table[1]//td[2]/span[2]/text()').extract()[0].strip().split(':')[-1]
        # 编号
        item['url'] = response.url
        # 内容
        item['content'] = response.xpath('//div[@class="wzy1"]/table[2]//td[@class="txt16_3"]//text()').extract()
        item['content'] = ''.join(item['content']).strip()

        tmp = response.xpath('//div[@class="wzy3_2"]/span/text()').extract()[0].strip().split(' ')
        item['author'] = tmp[0].split('：')[-1]
        item['pub_date'] = tmp[1].split('：')[-1] + ' '+ tmp[2]

        yield item

items.py

import scrapy


class SundistributespiderItem(scrapy.Item):
    # define the fields for your item here like:
    # 标题，编号，链接，内容，投诉者，投诉时间
    name = scrapy.Field()
    number = scrapy.Field()
    url = scrapy.Field()
    content = scrapy.Field()
    author = scrapy.Field()
    pub_date = scrapy.Field()

middlewares.py

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

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

from scrapy import signals


class SundistributespiderSpiderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Response, dict
        # or Item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)


class SundistributespiderDownloaderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

main.py

from scrapy import cmdline
name = 'Sun2'
cmd = 'scrapy crawl {0}'.format(name)

cmdline.execute(cmd.split())

settings.py

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

# Scrapy settings for SunDistributeSpider 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 = 'SunDistributeSpider'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'SunDistributeSpider (+http://www.yourdomain.com)'
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
SCHEDULER_PERSIST = True

ITEM_PIPELINES = {
    'scrapy_redis.pipelines.RedisPipeline': 400,
}

DOWNLOAD_DELAY = 1
#REDIS_HOST='192.168.10.132'
REDIS_HOST='127.0.0.1'
REDIS_PORT=6379
# REDIS_PARAMS = {
#     'password': '123',
# }

SPIDER_MIDDLEWARES = {
    'scrapy.spidermiddlewares.offsite.OffsiteMiddleware': None,
}

# 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 = 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 = {
#    'SunDistributeSpider.middlewares.SundistributespiderSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'SunDistributeSpider.middlewares.SundistributespiderDownloaderMiddleware': 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 = {
#    'SunDistributeSpider.pipelines.SundistributespiderPipeline': 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'

sun scrapy_redis

相关文章

网友评论

延伸阅读

深度阅读

栏目导航

热点阅读

笑笑酱爬虫