scrapy startproject dongguang
          

            
# -*- coding: utf-8 -*-
import scrapy
class NewdongguanItem(scrapy.Item):
  # define the fields for your item here like:
  # name = scrapy.Field()
  # pass
  # 每頁(yè)的帖子鏈接
  url = scrapy.Field()
  # 帖子標(biāo)題
  title = scrapy.Field()
  # 帖子編號(hào)
  number = scrapy.Field()
  # 帖子內(nèi)容
  content = scrapy.Field()
          

            
# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from dongguan.items import DongguanItem
class SunSpider(CrawlSpider):
  name = 'dg'
  allowed_domains = ['wz.sun0769.com']
  start_urls = ['http://wz.sun0769.com/html/top/report.shtml']
  # rules是Rule的集合，每個(gè)rule規(guī)則同時(shí)執(zhí)行。另外，如果發(fā)現(xiàn)web服務(wù)器有反爬蟲(chóng)機(jī)制如返回一個(gè)假的url，則可以使用Rule里面的參數(shù)process_links調(diào)用一個(gè)自編函數(shù)來(lái)處理url后返回一個(gè)真的url
  rules = (
    # 每個(gè)url都有一個(gè)獨(dú)一無(wú)二的指紋，每個(gè)爬蟲(chóng)項(xiàng)目都有一個(gè)去重隊(duì)列
    # Rule里面沒(méi)有回調(diào)函數(shù)，則默認(rèn)對(duì)匹配的鏈接要跟進(jìn)，就是對(duì)匹配的鏈接在進(jìn)行請(qǐng)求獲取響應(yīng)后對(duì)響應(yīng)里面匹配的鏈接繼續(xù)跟進(jìn)，只不過(guò)沒(méi)有回調(diào)函數(shù)對(duì)響應(yīng)數(shù)據(jù)進(jìn)行處理
    # Rule(LinkExtractor(allow="page="))如果設(shè)置為follow=False,則不會(huì)跟進(jìn)，只顯示當(dāng)前頁(yè)面匹配的鏈接。如設(shè)置為follow=True，則會(huì)對(duì)每個(gè)匹配的鏈接發(fā)送請(qǐng)求獲取響應(yīng)進(jìn)而從每個(gè)響應(yīng)里面再次匹配跟進(jìn)，直至沒(méi)有。python遞歸深度默認(rèn)為不超過(guò)1000，否則會(huì)報(bào)異常
    Rule(LinkExtractor(allow="page=")),

    Rule(LinkExtractor(allow='http://wz.sun0769.com/html/question/\d+/\d+.shtml'),callback='parse_item')

  )

  def parse_item(self, response):
    print(response.url)
    item = DongguanItem()
    item['url'] = response.url
    item['title'] = response.xpath('//div[@class="pagecenter p3"]//strong/text()').extract()[0]
    item['number'] = response.xpath('//div[@class="pagecenter p3"]//strong/text()').extract()[0].split(' ')[-1].split(':')[-1]
     # 對(duì)帖子里面有圖片的處理，發(fā)現(xiàn)沒(méi)有圖片時(shí)則沒(méi)有class="contentext"的div標(biāo)簽，以此作為標(biāo)準(zhǔn)獲取帖子內(nèi)容
    if len(response.xpath('//div[@class="contentext"]')) == 0:
      item['content'] = ''.join(response.xpath('//div[@class="c1 text14_2"]/text()').extract())
    else:
      item['content'] = ''.join(response.xpath('//div[@class="contentext"]/text()').extract())
    yield item
          

            
# -*- coding: utf-8 -*-
import json
class DongguanPipeline(object):
  def __init__(self):
    self.file = open('dongguan.json','w')
  def process_item(self, item, spider):
    content = json.dumps(dict(item),ensure_ascii=False).encode('utf-8') + '\n'
    self.file.write(content)
    return item
  def closespider(self):
    self.file.close()
          

            
# -*- coding: utf-8 -*-
BOT_NAME = 'dongguan'
SPIDER_MODULES = ['dongguan.spiders']
NEWSPIDER_MODULE = 'dongguan.spiders'
# log日志文件默認(rèn)保存在當(dāng)前目錄，下面為日志級(jí)別，當(dāng)大于或等于INFO時(shí)將被保存
LOG_FILE = 'dongguan.log'
LOG_LEVEL = 'INFO'
# 爬取深度設(shè)置
# DEPTH_LIMIT = 1
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'dongguan (+http://www.yourdomain.com)'
# Obey robots.txt rules
# ROBOTSTXT_OBEY = True
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
  'dongguan.pipelines.DongguanPipeline': 300,
}
          

            
scrapy crawl dg
          

            
scrapy startproject newdongguan
          

            
# -*- coding: utf-8 -*-
  import scrapy
  class NewdongguanItem(scrapy.Item):
    # 每頁(yè)的帖子鏈接
    url = scrapy.Field()
    # 帖子標(biāo)題
    title = scrapy.Field()
    # 帖子編號(hào)
    number = scrapy.Field()
    # 帖子內(nèi)容
    content = scrapy.Field()
          

            
# -*- coding: utf-8 -*-
import scrapy
from newdongguan.items import NewdongguanItem
class NewsunSpider(scrapy.Spider):
  name = 'ndg'
  # 設(shè)置爬取的域名范圍，可寫(xiě)可不寫(xiě)，不寫(xiě)則表示爬取時(shí)候不限域名，結(jié)果有可能會(huì)導(dǎo)致爬蟲(chóng)失控。
  allowed_domains = ['wz.sun0769.com']
  offset = 0
  url = 'http://wz.sun0769.com/index.php/question/report?page=' + str(offset)
  start_urls = [url]
  def parse(self, response):
    link_list = response.xpath("http://a[@class='news14']/@href").extract()
    for each in link_list:
      # 對(duì)每頁(yè)的帖子發(fā)送請(qǐng)求，獲取帖子內(nèi)容里面指定數(shù)據(jù)返回給管道文件
      yield scrapy.Request(each,callback=self.deal_link)
    self.offset += 30
    if self.offset <= 124260:
      url = 'http://wz.sun0769.com/index.php/question/report?page=' + str(self.offset)
      # 對(duì)指定分頁(yè)發(fā)送請(qǐng)求，響應(yīng)交給parse函數(shù)處理
      yield scrapy.Request(url,callback=self.parse)

  # 從每個(gè)分頁(yè)帖子內(nèi)容獲取數(shù)據(jù)，返回給管道
  def deal_link(self,response):
    item = NewdongguanItem()
    item['url'] = response.url
    item['title'] = response.xpath("http://div[@class='pagecenter p3']//strong[@class='tgray14']/text()").extract()[0]
    item['number'] = response.xpath("http://div[@class='pagecenter p3']//strong[@class='tgray14']/text()").extract()[0].split(' ')[-1].split(':')[-1]

    if len(response.xpath("http://div[@class='contentext']")) == 0:
      item['content'] = ''.join(response.xpath("http://div[@class='c1 text14_2']/text()").extract())
    else:
      item['content'] = ''.join(response.xpath("http://div[@class='contentext']/text()").extract())
    yield item
          

            
# -*- coding: utf-8 -*-
import codecs
import json
class NewdongguanPipeline(object):

  def __init__(self):
    # 使用codecs寫(xiě)文件，直接設(shè)置文件內(nèi)容編碼格式，省去每次都要對(duì)內(nèi)容進(jìn)行編碼
    self.file = codecs.open('newdongguan.json','w',encoding = 'utf-8')
    # 以前文件寫(xiě)法
    # self.file = open('newdongguan.json','w')

  def process_item(self, item, spider):
    print(item['title'])
    content = json.dumps(dict(item),ensure_ascii=False) + '\n'
    # 以前文件寫(xiě)法
    # self.file.write(content.encode('utf-8'))
    self.file.write(content)
    return item

  def close_spider(self):
    self.file.close()
          

            
# -*- coding: utf-8 -*-
BOT_NAME = 'newdongguan'
SPIDER_MODULES = ['newdongguan.spiders']
NEWSPIDER_MODULE = 'newdongguan.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'newdongguan (+http://www.yourdomain.com)'
USER_AGENT = 'User-Agent:Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;'
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
  'newdongguan.pipelines.NewdongguanPipeline': 300,
}
          

            
srapy crawl ndg