python网络爬虫 CrawlSpider使用详解

# spider文件

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule

class ChoutiSpider(CrawlSpider):
  name = 'chouti'
  # allowed_domains = ['www.xxx.com']
  start_urls = ['https://dig.chouti.com/1']

  # 连接提取器：从起始url对应的页面中提取符合规则的所有连接；allow=正则表达式
  # 正则为空的话，提取页面中所有连接
  link = LinkExtractor(allow=r'\d+')
  rules = (
    # 规则解析器:将连接提取器提取到的连接对应的页面源码进行指定规则的解析
    # Rule自动发送对应链接的请求
    Rule(link, callback='parse_item', follow=True),
    # follow：True 将连接提取器 继续 作用到 连接提取器提取出来的连接 对应的页面源码中
  )
  def parse_item(self, response):
    item = {}
    #item['domain_id'] = response.xpath('//input[@id="sid"]/@value').get()
    #item['name'] = response.xpath('//div[@id="name"]').get()
    #item['description'] = response.xpath('//div[@id="description"]').get()
    return item

# 1.spider文件
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from sunLineCrawl.items import SunlinecrawlItem,ContentItem
class SunSpider(CrawlSpider):
  name = 'sun'
  # allowed_domains = ['www.xxx.com']
  start_urls = ['http://wz.sun0769.com/index.php/question/questionType?type=4&page=']

  link = LinkExtractor(allow=r'type=4&page=\d+') # 提取页码连接
  link1 = LinkExtractor(allow=r'question/2019\d+/\d+\.shtml') # 提取详情页连接
  rules = (
    Rule(link, callback='parse_item', follow=False),
    Rule(link1, callback='parse_detail'),
  )
  # 解析出标题和网友名称数据
  def parse_item(self, response):
    tr_list = response.xpath('//*[@id="morelist"]/div/table[2]//tr/td/table//tr')
    for tr in tr_list:
      title = tr.xpath('./td[2]/a[2]/text()').extract_first()
      net_friend = tr.xpath('./td[4]/text()').extract_first()
      item = SunlinecrawlItem()
      item['title'] = title
      item['net_friend'] = net_friend

      yield item

  # 解析出新闻的内容
  def parse_detail(self,response):
    content = response.xpath('/html/body/div[9]/table[2]//tr[1]/td/div[2]//text()').extract()
    content = ''.join(content)
    item = ContentItem()
    item['content'] = content

    yield item
--------------------------------------------------------------------------------
# 2.items文件

import scrapy

class SunlinecrawlItem(scrapy.Item):
  title = scrapy.Field()
  net_friend = scrapy.Field()

class ContentItem(scrapy.Item):
  content = scrapy.Field()
--------------------------------------------------------------------------------
# 3.pipelines文件

class SunlinecrawlPipeline(object):
  def process_item(self, item, spider):
    # 确定接受到的item是什么类型（Content/Sunlinecrawl）
    if item.__class__.__name__ == 'SunlinecrawlItem':
      print(item['title'],item['net_friend'])

    else:
      print(item['content'])

    return item
--------------------------------------------------------------------------------
# 4.setting文件

BOT_NAME = 'sunLineCrawl'

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

LOG_LEVEL = 'ERROR'

USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'

ROBOTSTXT_OBEY = False

ITEM_PIPELINES = {
  'sunLineCrawl.pipelines.SunlinecrawlPipeline': 300,
}