Scrapy框架 之某网站产品采集案例

一、创建项目

第一步：scrapy startproject boyuan

第二步：cd boyuan

　　　　scrapy genspider product -t crawl  boyuan.com

如图：

二、代码编写

1、item.py

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html

import scrapy

class BoyuanItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    name = scrapy.Field()
    address = scrapy.Field()
    company = scrapy.Field()
    img = scrapy.Field()
    time = scrapy.Field()

2、product.py爬虫文件

# -*- coding: utf-8 -*-
import scrapy
from scrapy.spiders import Rule, CrawlSpider
from scrapy.linkextractors import LinkExtractor
from ..items import BoyuanItem

class ProductSpider(CrawlSpider):
    name = 'product'
    allowed_domains = ['boyuan.com']
    offset = 1
    url = "http://www.boyuan.com/sell/?page={0}"
    start_urls = [url.format(str(offset))]

    page_link = LinkExtractor(allow=("\?page=\d+"))

    rules = [
        Rule(page_link, callback="parse_content", follow=True)
    ]

    def parse_content(self, response):
        for each in response.xpath("//div[@class='list']//tr"):
            item = BoyuanItem()
            item['name'] = each.xpath("./td[4]//strong/text()").extract()[0]
            item['company'] = each.xpath("./td[4]//li[4]/a/text()").extract()[0]
            address = each.xpath("./td[4]//li[3]/text()").extract()[0]
            item['address'] = str(address).strip("[").strip("]")
            time = each.xpath("./td[4]//li[3]/span/text()").extract()[0]
            item['time'] = str(time).strip()
            item['img'] = each.xpath("./td[2]//img/@original").extract()[0]
            yield item

3、pipelines.py 管道文件

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
import json
import pymongo
from scrapy.conf import settings

class BoyuanPipeline(object):

    def __init__(self):
        host = settings.get("MONGO_HOST")
        port = settings.get("MONGO_PORT")
        db_name = settings.get("MONGO_DB")
        collection = settings.get("MONGO_COLLECTION")
        self.client = pymongo.MongoClient(host=host, port=int(port))
        db = self.client.get_database(db_name)
        if collection not in db.list_collection_names():
            db.create_collection(collection)
        self.col = db[collection]

    def process_item(self, item, spider):
        # 保存到mongodb中
        self.col.insert(dict(item))
        return item

    def close_spider(self, spider):
        self.client.close()

3、settings.py 配置文件

# mongodb数据库参数
MONGO_HOST = "localhost"
MONGO_PORT = ""
MONGO_DB = "boyuan"
MONGO_COLLECTION = "product"

4、start.py 启动文件

from scrapy import cmdline

if __name__ == '__main__':
    cmdline.execute("scrapy crawl product".split())

采集结果如图：