python Scrapy网络爬虫实战（存Json文件以及存到mysql数据库）

1-Scrapy建立新工程

在开始爬取之前，您必须创建一个新的 Scrapy 项目。 进入您打算存储代码的目录中【工作目录】，运行下列命令，如下是我创建的一个爬取豆瓣的工程douban【存储路径为：C:\python27\web】:

命令： scrapy startproject douban

2-目录如下

3--items的编写

首先，文件中有items.py，这个里面这要是用来封装爬虫所要爬的字段，如爬豆瓣电影，需要爬电影的ID，url，电影名称等。

# -*- coding:utf-8 -*-
import scrapy
class MovieItem(scrapy.Item):
    rank = scrapy.Field()
    title = scrapy.Field()
    link = scrapy.Field()
    rate = scrapy.Field()
    quote = scrapy.Field()

4-spider_movie250.py 的编写

# -*- coding:utf-8 -*-
import scrapy
from douban.items import MovieItem
class Movie250Spider(scrapy.Spider):
  # 定义爬虫的名称，主要main方法使用
  name = 'doubanmovie'
  allowed_domains = ["douban.com"]
  start_urls = [
    "http://movie.douban.com/top250/"
  ]
  # 解析数据
  def parse(self, response):
    items = []
    for info in response.xpath('//div[@class="item"]'):
      item = MovieItem()
      item['rank'] = info.xpath('div[@class="pic"]/em/text()').extract()
      item['title'] = info.xpath('div[@class="pic"]/a/img/@alt').extract()
      item['link'] = info.xpath('div[@class="pic"]/a/@href').extract()
      item['rate'] = info.xpath('div[@class="info"]/div[@class="bd"]/div[@class="star"]/span/text()').extract()
      item['quote'] = info.xpath('div[@class="info"]/div[@class="bd"]/p[@class="quote"]/span/text()').extract()
      items.append(item)
      yield item
    # 翻页
    next_page = response.xpath('//span[@class="next"]/a/@href')
    if next_page:
      url = response.urljoin(next_page[0].extract())
      #爬每一页
      yield scrapy.Request(url, self.parse)

5-编写pipelines

# -*- coding: utf-8 -*-
import json
import codecs
#以Json的形式存储
class JsonWithEncodingCnblogsPipeline(object):
    def __init__(self):
        self.file = codecs.open('douban.json', 'w', encoding='utf-8')
    def process_item(self, item, spider):
        line = json.dumps(dict(item), ensure_ascii=False) + "\n"
        self.file.write(line)
        return item
    def spider_closed(self, spider):
        self.file.close()

#将数据存储到mysql数据库
from twisted.enterprise import adbapi
import MySQLdb
import MySQLdb.cursors
class MySQLStorePipeline(object):
    #数据库参数
    def __init__(self):
        dbargs = dict(
             host = '127.0.0.1',
             db = '数据库名',
             user = 'root',
             passwd = 'root',
             cursorclass = MySQLdb.cursors.DictCursor,
             charset = 'utf8',
             use_unicode = True
            )
        self.dbpool = adbapi.ConnectionPool('MySQLdb',**dbargs)

    '''
    The default pipeline invoke function
    '''
    def process_item(self, item,spider):
        res = self.dbpool.runInteraction(self.insert_into_table,item)
        return item
    #插入的表，此表需要事先建好
    def insert_into_table(self,conn,item):
            conn.execute('insert into douban(rank,title,rate,qute,link) values(%s,%s,%s,%s,%s)', (
                item['rank'][0],
                item['title'][0],
                 item['rate'][0],
                 item['quote'][0],
                 item['link'][0])
                )

6-settings的编写

USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1) XXXXXXX) Chrome/70.0.3538.67 Safari/537.36'
# start MySQL database configure setting
MYSQL_HOST = '127.0.0.1'
MYSQL_DBNAME = '数据库名'
MYSQL_USER = 'root'
MYSQL_PASSWD = 'root'
# end of MySQL database configure setting

ITEM_PIPELINES = {
    'douban.pipelines.JsonWithEncodingCnblogsPipeline': 300,
    'douban.pipelines.MySQLStorePipeline': 300,
}

7-main 的编写

from scrapy import cmdline
cmdline.execute("scrapy crawl doubanmovie".split())

python Scrapy网络爬虫实战（存Json文件以及存到mysql数据库）

猜你喜欢