1. Create Project
scrapy startproject tencent
2. Create a project
scrapy genspider mahuateng
3, since saved to the database, naturally you want to install pymsql
pip install pymysql
4, settings files, configuration information, including databases, etc.
# -*- coding: utf-8 -*- # Scrapy settings for tencent 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 = 'tencent' SPIDER_MODULES = ['tencent.spiders'] NEWSPIDER_MODULE = 'tencent.spiders' LOG_LEVEL="WARNING" LOG_FILE="./qq.log" # Crawl responsibly by identifying yourself (and your website) on the user-agent 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' # 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 = { # 'tencent.middlewares.TencentSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html #DOWNLOADER_MIDDLEWARES = { # 'tencent.middlewares.TencentDownloaderMiddleware': 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 = { 'tencent.pipelines.TencentPipeline': 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 #= True HTTPCACHE_ENABLED # HTTPCACHE_EXPIRATION_SECS = 0 # HTTPCACHE_DIR = 'HttpCache' # HTTPCACHE_IGNORE_HTTP_CODES = [] # HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage' # connection data the MySQL # database address MYSQL_HOST = ' localhost ' # database Username: mysql_user = ' root ' # database password MYSQL_PASSWORD = ' yang156122 ' # database port MYSQL_PORT = 3306 # database name MYSQL_DBNAME = ' the Test ' # Database encoding MYSQL_CHARSET = ' UTF8 '
5, items.py file defines the data fields
# -*- 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 TencentItem(scrapy.Item): """ 数据字段定义 """ postId = scrapy.Field() recruitPostId = scrapy.Field() recruitPostName = scrapy.Field() countryName = scrapy.Field() locationName = scrapy.Field() categoryName = scrapy.Field() lastUpdateTime = scrapy.Field() pass
6, mahuateng.py document was crawling data
# -*- coding: utf-8 -*- import scrapy import json import logging class MahuatengSpider(scrapy.Spider): name = 'mahuateng' allowed_domains = ['careers.tencent.com'] start_urls = ['https://careers.tencent.com/tencentcareer/api/post/Query?timestamp=1561688387174&countryId=&cityId=&bgIds=&productId=&categoryId=&parentCategoryId=40003&attrId=&keyword=&pageIndex=1&pageSize=10&language=zh-cn&area=cn'] pageNum = 1 def parse(self, response): """ 数据获取 :param response: :return: """ content = response.body.decode() content = json.loads(content) content=content['Data']['Posts'] #删除空字典 for con in content: #print(con) for key in list(con.keys()): if not con.get(key): del con[key] #记录每一个岗位信息 # for con in content: # yield con #print(type(con)) yield con #logging.warning(con) #####翻页###### self.pageNum = self.pageNum+1 if self.pageNum<=118: next_url = "https://careers.tencent.com/tencentcareer/api/post/Query?timestamp=1561688387174&countryId=&cityId=&bgIds=&productId=&categoryId=&parentCategoryId=40003&attrId=&keyword=&pageIndex="+str(self.pageNum)+"&pageSize=10&language=zh-cn&area=cn" yield scrapy.Request( next_url, callback=self.parse )
7, pipelines.py document was to process data, including storing data in mysql
# -*- 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 # from tencent.settings import MYSQL_HOST # from tencent.settings import MYSQL_USER # from tencent.settings import MYSQL_PASSWORD # from tencent.settings import MYSQL_PORT #Import MYSQL_DBNAME tencent.settings from # # from tencent.settings Import MYSQL_CHARSET Import Copy class TencentPipeline (Object): # function initializes DEF the __init__ (Self, db_pool): self.db_pool = db_pool @classmethod DEF from_settings (CLS, Settings): "" " class method, loaded only once, database initialization " "" db_params = dict ( Host = Settings [ ' MYSQL_HOST ' ], User = Settings [ ' mysql_user '], Password = Settings [ ' MYSQL_PASSWORD ' ], Port = Settings [ ' the MYSQL_PORT ' ], Database = Settings [ ' MYSQL_DBNAME ' ], charset = Settings [ ' MYSQL_CHARSET ' ], use_unicode = True, # the cursor type cursorClass = Cursors. DictCursor ) # Create a connection pool db_pool the adbapi.ConnectionPool = ( ' pymysql ', ** db_params) # Returns a pipeline objects return CLS (db_pool) DEF process_item (Self, Item, Spider): "" " Data processing : param Item: : param Spider: : return: " "" myItem = {} myItem [ " postId " ] Item = [ " the postID " ] myItem [ " recruitPostId " ] = Item [ " RecruitPostId " ] myItem [ "recruitPostName"] = item["RecruitPostName"] myItem["countryName"] = item["CountryName"] myItem["locationName"] = item["LocationName"] myItem["categoryName"] = item["CategoryName"] myItem["lastUpdateTime"] = item["LastUpdateTime"] logging.warning(myItem) #Copy of the object, a deep copy --- here is to solve the problem of duplication of data! ! ! = asynItem copy.deepcopy (myItem) # to be executed into sql connection pool Query = self.db_pool.runInteraction (self.insert_into, asynItem) # If sql performs transmission error, automatic callback addErrback () function query.addErrback (self .handle_error, myItem, Spider) return myItem # handling sql function DEF insert_into (Self, the Cursor, Item): # create sql statement sql = " INSERT INTO tencent (postId, recruitPostId, recruitPostName, countryName, locationName, categoryName, LastUpdateTime) VALUES ( '{}', '{}', '{}', '{}', '{}', '{}', '{}') " .postId ' ], Item [ ' recruitPostId ' ], Item [ ' recruitPostName ' ], Item [ ' countryName ' ], Item [ ' locationName ' ], Item [ ' categoryName ' ], Item [ ' LastUpdateTime ' ]) # execute sql statement cursor.execute (SQL) # error function DEF the handle_error (Self, failure, Item, Spider): # # output an error message Print ( " failure ", failure)
8, create a database table
Navicat MySQL Data Transfer Source Server : 本机 Source Server Version : 50519 Source Host : localhost:3306 Source Database : test Target Server Type : MYSQL Target Server Version : 50519 File Encoding : 65001 Date: 2019-06-28 12:47:06 */ SET FOREIGN_KEY_CHECKS=0; -- ---------------------------- -- Table structure for tencent -- ---------------------------- DROP TABLE IF EXISTS `tencent`; CREATE TABLE `tencent` ( `id` int(10) NOT NULL AUTO_INCREMENT, `postId` varchar(100) DEFAULT NULL, `recruitPostId` varchar(100) DEFAULT NULL, `recruitPostName` varchar(100) DEFAULT NULL, `countryName` varchar(100) DEFAULT NULL, `locationName` varchar(100) DEFAULT NULL, `categoryName` varchar(100) DEFAULT NULL, `lastUpdateTime` varchar(100) DEFAULT NULL, PRIMARY KEY (`id`) ) ENGINE=InnoDB AUTO_INCREMENT=1181 DEFAULT CHARSET=utf8;
Perfect ending!