scrapy-redis插件爬取示例
items.pyimport scrapy
class SinaItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass
class SinanewsItem(scrapy.Item):
#大类的标题和url
parentTitle = scrapy.Field()
parentUrls = scrapy.Field()
#小类的标题和子url
subTitle = scrapy.Field()
subUrls = scrapy.Field()
#小类目录存储路径
subFilename = scrapy.Field()
#小类下的子链接
sonUrl = scrapy.Field()
#文章标题和内容
head = scrapy.Field()
content = scrapy.Field()
爬虫脚本sina01.py
# -*- coding: utf-8 -*-
import scrapy
from ..items import SinanewsItem
from scrapy_redis.spiders import RedisSpider
class Sina01Spider(RedisSpider):
name = 'sina01'
#启动爬虫时的命令
redis_key = "sinaspider:start_urls"
#allowed_domains = ['sina.com']
# start_urls = ['http://sina.com/']
#动态定义爬虫取域范围
def __init__(self, *args, **kwargs):
domain = kwargs.pop('domain', '')
self.allowed_domains = filter(None, domain.split(','))
super(Sina01Spider, self).__init__(*args, **kwargs)
def parse(self, response):
items = []
#所有大类的url和标题
parentUrls = response.xpath('//div[@id="tab01"]/div/h3/a/@href').extract()
parentTitle = response.xpath('//div[@id="tab01"]/div/h3/a/text()').extract()
#所有小类的url和标题
subUrls = response.xpath('//div[@id="tab01"]/div/ul/li/a/@href').extract()
subTitle = response.xpath('//div[@id="tab01"]/div/ul/li/a/text()').extract()
#爬取所有大类
for i in range(0, len(parentTitle)):
#爬取所有小类
for j in range(0, len(subUrls)):
item = SinanewsItem()
#保存大类的title和urls
item['parentTitle'] = parentTitle
item['parentUrls'] = parentUrls
#检查小类的url是否以同类别大类url开头，如果是返回True
if_belong = subUrls.startswith(item['parentUrls'])
if (if_belong):
# 存储小类url、title和filename字段数据
item['subUrls'] = subUrls
item['subTitle'] = subTitle
items.append(item)
# 发送每个小类url的Request请求，得到Response连同包含meta数据 一同交给回调函数 second_parse 方法处理
for item in items:
yield scrapy.Request(url=item['subUrls'], meta={'meta_1':item}, callback=self.second_parse)
#对于返回的小类的url，在进行递归请求
def second_parse(self, response):
#提取每次Response的meta数据
meta_1 = response.meta['meta_1']
#取出小类的所有子链接
sonUrls = response.xpath('//a/@href').extract()
items = []
for i in range(0, len(sonUrls)):
#检查每个链接是否以大类url开头、以.shtml结尾，如果是返回True
if_belong = sonUrls.endswith('.shtml') and sonUrls.startwith(meta_1)
# 如果属于本大类，获取字段值放在同一个item下便于传输
if(if_belong):
item = SinanewsItem()
item['parentTitle'] = meta_1['parentTitle']
item['parentUrls'] = meta_1['parentUrls']
item['subUrls'] = meta_1['subUrls']
item['subTitle'] = meta_1['subTitle']
item['sonUrls'] = sonUrls
items.append(item)
# 发送每个小类下子链接url的Request请求，得到Response后连同包含meta数据 一同交给回调函数 detail_parse 方法处理
for item in items:
yield scrapy.Request(url=item['sonUrls'],meta={'meta_2':item},callback=self.detail_parse)
#数据解析方法,获取文章标题和内容
def detail_parse(self, response):
item = response.meta['meta_2']
content = ""
head = response.xpath('/h1[@id="main_title"]/text()')
content_list = response.xpath('//div[@id="artibody"]/p/text()').extract()
#将p标签里的文本内容 合并到一起
for content_one in content_list:
content += content_one
item['head'] = head if len(head) > 0 else "NULL"
item['content'] = content
yield item
settings.py添加
# 使用scrapy-redis里的去重组件，不使用scrapy默认的去重方式
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
# 使用scrapy-redis里的调度器组件，不使用默认的调度器
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
# 允许暂停，redis请求记录不丢失
SCHEDULER_PERSIST = True
# 默认的scrapy-redis请求队列形式（按优先级）
SCHEDULER_QUEUE_CLASS = "scrapy_redis.queue.SpiderPriorityQueue"
# 队列形式，请求先进先出
#SCHEDULER_QUEUE_CLASS = "scrapy_redis.queue.SpiderQueue"
# 栈形式，请求先进后出
#SCHEDULER_QUEUE_CLASS = "scrapy_redis.queue.SpiderStack"
# 只是将数据放到redis数据库，不需要写pipelines文件
ITEM_PIPELINES = {
# 'Sina.pipelines.SinaPipeline': 300,
'scrapy_redis.pipelines.RedisPipeline': 400,
}
# LOG_LEVEL = 'DEBUG'
# Introduce an artifical delay to make use of parallelism. to speed up the
# crawl.
DOWNLOAD_DELAY = 1
# 指定数据库的主机IP
REDIS_HOST = "localhost"
# 指定数据库的端口号
REDIS_PORT = 6379
打开redis客户端添加url测试
lpush sinaspider:start_urls http://news.sina.com.cn/guide/
页:
[1]