Python Scrapy框架第一個入門程序示例

scrappy start project maitian

import scrapy
class MaitianItem(scrapy.Item):
  # define the fields for your item here like:
  # name = scrapy.Field()
  title = scrapy.Field()
  price = scrapy.Field()
  area = scrapy.Field()
  district = scrapy.Field()

import scrapy
from maitian.items import MaitianItem
class MaitianSpider(scrapy.Spider):
  name = "zufang"
  start_urls = ['http://bj.maitian.cn/zfall/PG1']
  def parse(self, response):
    for zufang_itme in response.xpath('//div[@class="list_title"]'):
      yield {
        'title': zufang_itme.xpath('./h2/a/text()').extract_first().strip(),
        'price': zufang_itme.xpath('./div[@class="the_price"]/ol/strong/span/text()').extract_first().strip(),
        'area': zufang_itme.xpath('./p/span/text()').extract_first().replace('㎡', '').strip(),
        'district': zufang_itme.xpath('./p//text()').re(r'昌平|朝陽|東城|大興|豐臺|海淀|石景山|順義|通州|西城')[0],
      }
    next_page_url = response.xpath(
      '//div[@id="paging"]/a[@class="down_page"]/@href').extract_first()
    if next_page_url is not None:
      yield scrapy.Request(response.urljoin(next_page_url))

.
.
.
ITEM_PIPELINES = {'maitian.pipelines.MaitianPipeline': 300,}
MONGODB_HOST = '127.0.0.1'
MONGODB_PORT = 27017
MONGODB_DBNAME = 'maitian'
MONGODB_DOCNAME = 'zufang'

import pymongo
from scrapy.conf import settings
class MaitianPipeline(object):
  def __init__(self):
    host = settings['MONGODB_HOST']
    port = settings['MONGODB_PORT']
    db_name = settings['MONGODB_DBNAME']
    client = pymongo.MongoClient(host=host, port=port)
    db = client[db_name]
    self.post = db[settings['MONGODB_DOCNAME']]
  def process_item(self, item, spider):
    zufang = dict(item)
    self.post.insert(zufang)
    return item