python之scrapy爬取jingdong招聘信息到mysql数据库

1、创建工程

scrapy startproject jd

2、创建项目

scrapy genspider jingdong

3、安装pymysql

pip install pymysql

4、settings.py文件，主要是全局字段的定义，包括数据库信息

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

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

BOT_NAME = 'jd'

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

LOG_LEVEL="WARNING"
LOG_FILE="./jingdong1.log"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'jd (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# 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://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

# 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://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'jd.middlewares.JdSpiderMiddleware': 543,
#}

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

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

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

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.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://doc.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'

# 连接数据MySQL
# 数据库地址
MYSQL_HOST = 'localhost'
# 数据库用户名:
MYSQL_USER = 'root'
# 数据库密码
MYSQL_PASSWORD = 'yang156122'
# 数据库端口
MYSQL_PORT = 3306
# 数据库名称
MYSQL_DBNAME = 'test'
# 数据库编码
MYSQL_CHARSET = 'utf8'

5、items.py文件定义数据库字段

# -*- 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 JdItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    appTime = scrapy.Field()
    applicantErp = scrapy.Field()
    formatPublishTime = scrapy.Field()
    jobType = scrapy.Field()
    positionName = scrapy.Field()
    positionNameOpen = scrapy.Field()
    publishTime = scrapy.Field()
    qualification= scrapy.Field()
    pass

6、jingdong.py文件主要是爬取所需数据

# -*- coding: utf-8 -*-
import scrapy

import logging
import json
logger = logging.getLogger(__name__)
class JingdongSpider(scrapy.Spider):
    name = 'jingdong'
    allowed_domains = ['zhaopin.jd.com']
    start_urls = ['http://zhaopin.jd.com/web/job/job_list?page=1']
    pageNum = 1
    def parse(self, response):
        content  = response.body.decode()
        content = json.loads(content)
        ##########去除列表中字典集中的空值###########
        for i in range(len(content)):
            #list(content[i].keys()获取当前字典中的key
            # for key in list(content[i].keys()): #content[i]为字典
            #     if not content[i].get(key):#content[i].get(key)根据key获取value
            #         del content[i][key] #删除空值字典
            yield content[i]
        # for i in range(len(content)):
        #     logging.warning(content[i])

        self.pageNum = self.pageNum+1
        if self.pageNum<=355:
            next_url = "http://zhaopin.jd.com/web/job/job_list?page="+str(self.pageNum)
            yield scrapy.Request(
                next_url,
                callback=self.parse
            )
        pass

7、pipelines.py文件主要是对爬取的数据进行清洗和处理，包括数据的入库操作

　　这里和tencent相比，主要是增加了时间处理

# -*- 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 logging
from pymysql import cursors
from twisted.enterprise import adbapi
import time
import copy
class JdPipeline(object):
    # 函数初始化
    def __init__(self, db_pool):
        self.db_pool = db_pool

    @classmethod
    def from_settings(cls, settings):
        """类方法，只加载一次，数据库初始化"""
        db_params = dict(
            host=settings['MYSQL_HOST'],
            user=settings['MYSQL_USER'],
            password=settings['MYSQL_PASSWORD'],
            port=settings['MYSQL_PORT'],
            database=settings['MYSQL_DBNAME'],
            charset=settings['MYSQL_CHARSET'],
            use_unicode=True,
            # 设置游标类型
            cursorclass=cursors.DictCursor
        )
        # 创建连接池
        db_pool = adbapi.ConnectionPool('pymysql', **db_params)
        # 返回一个pipeline对象
        return cls(db_pool)

    def process_item(self, item, spider):
        myItem = {}
        myItem["appTime"]=item["appTime"]
        myItem["applicantErp"] = item["applicantErp"]
        myItem["formatPublishTime"] = item["formatPublishTime"]
        myItem["jobType"] = item["jobType"]
        myItem["positionName"] = item["positionName"]
        #时间转换
        publishTime = item["publishTime"]
        publishTime = time.localtime(int(str(publishTime)[:10])) #时间格式转换
        myItem["publishTime"] = time.strftime("%Y-%m-%d %H:%M:%S", publishTime)

        myItem["positionNameOpen"]=item["positionNameOpen"]
        myItem["qualification"] = item["qualification"]

        logging.warning(item)
        # 对象拷贝，深拷贝  --- 这里是解决数据重复问题！！！
        asynItem = copy.deepcopy(myItem)
        # 把要执行的sql放入连接池
        query = self.db_pool.runInteraction(self.insert_into, asynItem)
        # 如果sql执行发送错误,自动回调addErrBack()函数
        query.addErrback(self.handle_error, myItem, spider)
        return myItem

        # 处理sql函数
    def insert_into(self, cursor, item):
        # 创建sql语句
        sql = "INSERT INTO jingdong (appTime,applicantErp,formatPublishTime,jobType,positionName,publishTime,positionNameOpen,qualification) " \
              "VALUES ('{}','{}','{}','{}','{}','{}','{}','{}')".format(
            item['appTime'], item['applicantErp'],item['formatPublishTime'] , item['jobType'],
            item['positionName'], item['publishTime'], item['positionNameOpen'],item['qualification'])
        # 执行sql语句
        cursor.execute(sql)

        # 错误函数
    def handle_error(self, failure, item, spider):
        # #输出错误信息
        print("failure", failure)

完美收官！！！