scrapy爬取智联招聘，MongoDB存储数据

一.项目目录结构

二.模块划分

1.settings

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

# Scrapy settings for zhilian project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'zhilian'

SPIDER_MODULES = ['zhilian.spiders']
NEWSPIDER_MODULE = 'zhilian.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'zhilian (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://docs.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

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'zhilian.middlewares.ZhilianSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'zhilian.middlewares.ZhilianDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'zhilian.pipelines.ZhilianPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

2.main

from scrapy import cmdline

cmdline.execute(['scrapy','crawl','zhilian'])

3.items

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

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

import scrapy


class ZhilianItem(scrapy.Item):
    # define the fields for your item here like:
    position = scrapy.Field()
    company = scrapy.Field()
    city = scrapy.Field()
    salary = scrapy.Field()

4.ZhilianSpider

import scrapy
from ..items import ZhilianItem
import json

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36',
}

class Zhilian_Spider(scrapy.Spider):
    name = 'zhilian'

    def start_requests(self):
        for i in range(0,1080,90):
            url = 'https://fe-api.zhaopin.com/c/i/sou?start={}&pageSize=90&cityId=601&salary=0,0&workExperience=-1&education=-1&companyType=-1&employmentType=-1&jobWelfareTag=-1&kw=%E9%94%80%E5%94%AE&kt=3&=0&_v=0.41352509&x-zp-page-request-id=fabc345dbbae4931a317f751a3952ec5-1572513651825-763363&x-zp-client-id=2a5a1b79-d92c-486f-e0e7-85a94b7837b2'.format(i)

            yield scrapy.Request(url=url,headers=headers)

    def parse(self, response):
        res = response.text
        datas = json.loads(res)['data']['results']

        # print(datas)
        # print(type(datas))
        # print(len(datas))
        for data in datas:
            try:
                info = ZhilianItem()

                jobname = data.get('jobName')
                salary = data.get('salary')
                company = data.get('company').get('name')
                city = data.get('city').get('items')[0].get('name')

                print(jobname,salary,company,city)

                # 对info字典进行赋值
                info['position'] = jobname
                info['company'] = company
                info['city'] = city
                info['salary'] = salary


                yield info
            except:
                pass

5.pipelines

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

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

#建立一个连接
# conn = pymongo.MongoClient("mongodb://localhost:27017")
conn = pymongo.MongoClient(host='localhost',port=27017)

#选择使用哪个数据库
mydb = conn['test']

#使用哪个集合
myset = mydb['info']

class ZhilianPipeline(object):
    def process_item(self, item, spider):

        infomations = {
            'position':item['position'],
            'company':item['company'],
            'city':item['city'],
            'salary':item['salary'],
        }

        myset.insert(infomations)
        return item

注意：智联招聘url变化的是cityid，每个城市下有12页(不一定)，页数start利用循环每次加90