Scrapy实战篇（四）爬取京东商城文胸信息

创建scrapy项目

scrapy startproject jingdong

填充 item.py文件

在这里定义想要存储的字段信息

import scrapy
class JingdongItem(scrapy.Item):
    content = scrapy.Field()
    creationTime = scrapy.Field()
    productColor = scrapy.Field()
    productSize = scrapy.Field()
    userClientShow = scrapy.Field()
    userLevelName = scrapy.Field()
class IdItem(scrapy.Item):
    id = scrapy.Field()

填充middlewares.py文件

中间件主要实现添加随机user-agent的作用。

import random
from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware
class RandomUserAgent(UserAgentMiddleware):
    def __init__(self, agents):
        self.agents = agents
    @classmethod
    def from_crawler(cls, crawler):
        return cls(crawler.settings.getlist("USER_AGENTS"))
    def process_request(self, request, spider):
        request.headers.setdefault('User-Agent', random.choice(self.agents))

填充pipelines.py文件

将我们爬取到的结果存储在mongo数据库中

from pymongo import MongoClient
class JingdongPipeline(object):
    collection = 'jingdong_cup'
    def __init__(self, mongo_uri, mongo_db):
        self.mongo_uri = mongo_uri
        self.mongo_db = mongo_db
    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            mongo_uri=crawler.settings.get('MONGO_RUI'),
            mongo_db=crawler.settings.get('MONGO_DB')
        )
    # 爬虫启动将会自动执行下面的方法
    def open_spider(self,spider):
        self.client = MongoClient(self.mongo_uri)
        self.db = self.client[self.mongo_db]
    # 爬虫项目关闭调用的方法
    def close_spider(self, spider):
        self.client.close()
    def process_item(self, item, spider):
        table = self.db[self.collection]
        data = dict(item)
        table.insert_one(data)
        return "OK!"

设置settings.py文件

下面的这些信息需要简单的修改，其他的信息不动即可

BOT_NAME = 'jingdong'
SPIDER_MODULES = ['jingdong.spiders']
NEWSPIDER_MODULE = 'jingdong.spiders'
ROBOTSTXT_OBEY = False
DOWNLOAD_DELAY = 2
COOKIES_ENABLED = False
USER_AGENTS = [
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
"Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
"Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
"Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
]
DOWNLOADER_MIDDLEWARES = {
    'scrapy.downloadermiddleware.useragent.UserAgentMiddleware': None,
    'jingdong.middlewares.RandomUserAgent': 400
}
ITEM_PIPELINES = {
   'jingdong.pipelines.JingdongPipeline': 300,
}
MONGO_URI = 'mongodb://localhost:27017'
MONGO_DB = 'JD'

最后在创建jingdong_spider.py文件，来实现我们的逻辑

主要的逻辑是这样的，在京东首页输入商品信息之后，第一步需要做的就是将每一页的商品id爬取下来，商品的id是一串数字，我们只要将这一串数字加入到url中，就可以拿到每件商品的评论页，评论信息是josn形式返回，当然这里还需要实现翻页的功能，代码如下。

from scrapy import Spider,Request
from jingdong.items import JingdongItem,IdItem
import json
import re
class JingdongSpider(Spider):
    name = 'jingdong'
    allowed_domains = []
    def start_requests(self):
        start_urls = ['https://search.jd.com/Search?keyword=%E6%96%87%E%83%B8&enc=utf-8&qrst=1&rt=1&stop=1&vt=2&suggest=1.his.0.0&page={}&s=1&click=0'.format(str(i)) for i in range(1,150,2)]
        for url in start_urls:
            yield Request(url=url, callback=self.parse)
    # 获取商品的id
    def parse(self, response):
        selector = response.xpath('//ul[@class="gl-warp clearfix"]/li')
        id_list = []
        for info in selector:
            try:
                id = info.xpath('@data-sku').extract_first()
                if id not in id_list:
                    id_list.append(id)
                    item = IdItem()
                    item['id'] = id
                    comment_url = 'https://sclub.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98vv6&productId={}&score=0&sortType=5&page=0&pageSize=10&isShadowSku=0&fold=1'.format(str(id))
                    yield Request(url=comment_url, meta={'item':item}, headers=self.headers, callback=self.parseurl)
            except IndexError:
                continue
    # 拿到评论页信息，解析出页面总数，针对每一个页面再次请求
    def parseurl(self,response):
        t = re.findall('^fetchJSON_comment98vv\d*\((.*)\);', response.text)
        json_data = json.loads(t[0])  # 字符串格式格式化成json格式
        page = json_data['maxPage']
        item = response.meta['item']
        id = item['id']
        urls = ['https://sclub.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98vv6&productId={}&score=0&sortType=5&page={}&pageSize=10&isShadowSku=0&fold=1'.format(str(id), str(i)) for i in range(0, int(page))]
        for path in urls:
            yield Request(url=path, headers=self.headers, callback=self.parsebody)
    # 解析评论信息
    def parsebody(self,response):
        t = re.findall('^fetchJSON_comment98vv\d*\((.*)\);', response.text)  # 去掉json的头信息,变成一个单一的列表
        json_data = json.loads(t[0])
        for comment in json_data['comments']:  # 列表套字典格式
            item = JingdongItem()
            try:
                item['content'] = comment['content']
                item['creationTime'] = comment['creationTime']
                item['productColor'] = comment['productColor']
                item['productSize'] = comment['productSize']
                item['userClientShow'] = comment['userClientShow']
                item['userLevelName'] = comment['userLevelName']
                yield item
            except:
                continue

整体的代码可以去github下载：https://github.com/cnkai/jingdong-cup