scrapy startproject dongguang

# -*- coding: utf-8 -*-
import scrapy
class NewdongguanItem(scrapy.Item):
  # define the fields for your item here like:
  # name = scrapy.Field()
  # pass
  # 每頁的帖子鏈接
  url = scrapy.Field()
  # 帖子標題
  title = scrapy.Field()
  # 帖子編號
  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rule規(guī)則同時執(zhí)行。另外，如果發(fā)現(xiàn)web服務器有反爬蟲機制如返回一個假的url，則可以使用Rule里面的參數(shù)process_links調(diào)用一個自編函數(shù)來處理url后返回一個真的url
  rules = (
    # 每個url都有一個獨一無二的指紋，每個爬蟲項目都有一個去重隊列
    # Rule里面沒有回調(diào)函數(shù)，則默認對匹配的鏈接要跟進，就是對匹配的鏈接在進行請求獲取響應后對響應里面匹配的鏈接繼續(xù)跟進，只不過沒有回調(diào)函數(shù)對響應數(shù)據(jù)進行處理
    # Rule(LinkExtractor(allow="page="))如果設置為follow=False,則不會跟進，只顯示當前頁面匹配的鏈接。如設置為follow=True，則會對每個匹配的鏈接發(fā)送請求獲取響應進而從每個響應里面再次匹配跟進，直至沒有。python遞歸深度默認為不超過1000，否則會報異常
    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]
     # 對帖子里面有圖片的處理，發(fā)現(xiàn)沒有圖片時則沒有class="contentext"的div標簽，以此作為標準獲取帖子內(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日志文件默認保存在當前目錄，下面為日志級別，當大于或等于INFO時將被保存
LOG_FILE = 'dongguan.log'
LOG_LEVEL = 'INFO'
# 爬取深度設置
# 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):
    # 每頁的帖子鏈接
    url = scrapy.Field()
    # 帖子標題
    title = scrapy.Field()
    # 帖子編號
    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'
  # 設置爬取的域名范圍，可寫可不寫，不寫則表示爬取時候不限域名，結(jié)果有可能會導致爬蟲失控。
  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:
      # 對每頁的帖子發(fā)送請求，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)
      # 對指定分頁發(fā)送請求，響應交給parse函數(shù)處理
      yield scrapy.Request(url,callback=self.parse)

  # 從每個分頁帖子內(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寫文件，直接設置文件內(nèi)容編碼格式，省去每次都要對內(nèi)容進行編碼
    self.file = codecs.open('newdongguan.json','w',encoding = 'utf-8')
    # 以前文件寫法
    # 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