建立爬蟲專案douban

scrapy startproject douban

設定items.py檔案，儲存要儲存的資料型別和欄位名稱

# -*- coding: utf-8 -*-
import scrapy
class DoubanItem(scrapy.Item):
 title = scrapy.Field()
 # 內容
 content = scrapy.Field()
 # 評分
 rating_num = scrapy.Field()
 # 簡介
 quote = scrapy.Field()

設定爬蟲檔案doubanmovies.py

# -*- coding: utf-8 -*-
import scrapy
from douban.items import DoubanItem
class DoubanmoviesSpider(scrapy.Spider):
 name = 'doubanmovies'
 allowed_domains = ['movie.douban.com']
 offset = 0
 url = 'https://movie.douban.com/top250?start='
 start_urls = [url + str(offset)]
 def parse(self,response):
  # print('*'*60)
  # print(response.url)
  # print('*'*60)
  item = DoubanItem()
  info = response.xpath("//div[@class='info']")
  for each in info:
   item['title'] = each.xpath(".//span[@class='title'][1]/text()").extract()
   item['content'] = each.xpath(".//div[@class='bd']/p[1]/text()").extract()
   item['rating_num'] = each.xpath(".//span[@class='rating_num']/text()").extract()
   item['quote'] = each .xpath(".//span[@class='inq']/text()").extract()
   yield item
   # print(item)
  self.offset += 25
  if self.offset <= 250:
   yield scrapy.Request(self.url + str(self.offset),callback=self.parse)

設定管道檔案，使用mongodb資料庫來儲存爬取的資料。重點部分

# -*- coding: utf-8 -*-
from scrapy.conf import settings
import pymongo
class DoubanPipeline(object):
 def __init__(self):
  self.host = settings['MONGODB_HOST']
  self.port = settings['MONGODB_PORT']
 def process_item(self,item,spider):
  # 建立mongodb客戶端連線物件，該例從settings.py檔案裡面獲取mongodb所在的主機和埠引數，可直接書寫主機和埠
  self.client = pymongo.MongoClient(self.host,self.port)
  # 建立資料庫douban
  self.mydb = self.client['douban']
  # 在資料庫douban裡面建立表doubanmovies
  # 把類似字典的資料轉換為phthon字典格式
  content = dict(item)
  # 把資料新增到表裡面
  self.mysheetname.insert(content)
  return item

設定settings.py檔案

# -*- coding: utf-8 -*-
BOT_NAME = 'douban'
SPIDER_MODULES = ['douban.spiders']
NEWSPIDER_MODULE = 'douban.spiders'
USER_AGENT = 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;'
# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
COOKIES_ENABLED = False
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
 'douban.pipelines.DoubanPipeline': 300,}
# mongodb資料庫設定變數
MONGODB_HOST = '127.0.0.1'
MONGODB_PORT = 27017

終端測試

scrapy crawl douban

這部落格園的程式碼片段縮排，難道要用4個空格才可以搞定？我發現只能使用4個空格才能解決如上圖的程式碼塊的縮排

以上就是本文的全部內容，希望對大家的學習有所幫助，也希望大家多多支援我們。