# 用框架爬取腾讯招聘信息并保存到数据库
# main.py
from scrapy import cmdline cmdline.execute('scrapy crawl tencent_new'.split())
# tencent_new.py
# -*- coding: utf-8 -*- import scrapy from urllib import request,parse from ..items import JobItem from datetime import datetime class TencentNewSpider(scrapy.Spider): name = 'tencent_new' allowed_domains = ['tencent.com'] start_urls = ['http://hr.tencent.com'] base_url = 'https://hr.tencent.com/position.php?start=%d' def parse(self, response): # 构造分页请求 for i in range(0,100 + 1,10): fullurl = self.base_url % i yield scrapy.Request(fullurl,callback=self.parse_list) # 解析列表页 def parse_list(self,response): # print(response.url) detail_list = response.xpath('//td[@class="l square"]/a/@href').extract() for link in detail_list: link = request.urljoin(self.base_url,link) yield scrapy.Request(link,callback=self.parse_detail) # 解析详情页 def parse_detail(self,response): item = JobItem() p_name = response.xpath('//td[@id="sharetitle"]/text()').extract_first() p_location = response.xpath('//tr[@class="c bottomline"]/td[1]/text()').extract_first() p_type = response.xpath('//tr[@class="c bottomline"]/td[2]/text()').extract_first() p_number = response.xpath('//tr[@class="c bottomline"]/td[3]/text()').extract_first() # print(p_name,p_location,p_type,p_number) p_info = response.xpath('//ul[@class="squareli"]') p_duty = p_info[0] p_require = p_info[1] p_duty = p_duty.xpath('.//li/text()').extract() p_require = p_require.xpath('.//li/text()').extract() p_duty = '-'.join(p_duty) p_require = '-'.join(p_require) item['p_name'] = p_name item['p_type'] = p_type item['p_number'] = p_number.strip('人') item['p_location'] = p_location item['p_duty'] = p_duty item['p_require'] = p_require item['crawl_time'] = datetime.now().strftime('%Y-%m-%d %H:%M:%S') item['p_date'] = datetime.now().strftime('%Y-%m-%d') item['spider_name'] = self.name yield item
# items.py
# -*- coding: utf-8 -*- # Define here the models for your scraped items # # See documentation in: # http://doc.scrapy.org/en/latest/topics/items.html import scrapy class Day11Item(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() pass # 定义数据模型 class JobItem(scrapy.Item): p_name = scrapy.Field() p_type = scrapy.Field() p_number = scrapy.Field() p_location = scrapy.Field() p_date = scrapy.Field() p_duty = scrapy.Field() p_require = scrapy.Field() crawl_time = scrapy.Field() spider_name = scrapy.Field() def get_sql(self): sql = 'insert into py07_tencent_new(p_name,p_type,p_number,p_location,p_date,p_duty,p_require,crawl_time,spider_name) ' \ 'values(%s,%s,%s,%s,%s,%s,%s,%s,%s) on duplicate key update p_number=values(p_number)' data = (self['p_name'],self['p_type'],self['p_number'],self['p_location'],self['p_date'],self['p_duty'],self['p_require'],self['crawl_time'],self['spider_name']) return sql,data
# pipelines.py
# -*- coding: utf-8 -*- # Define your item pipelines here # # Don't forget to add your pipeline to the ITEM_PIPELINES setting # See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html import json import pymysql class Day11Pipeline(object): def process_item(self, item, spider): return item class JobPipeline(object): def __init__(self): self.f = open('job.json','w',encoding='utf-8') def process_item(self,item, spider): self.f.write(json.dumps(dict(item),ensure_ascii=False) + '\n') return item # 爬虫结束调用 def close_spider(self,spider): self.f.close() class JobMysqlPipeline(object): def __init__(self): self.conn = pymysql.connect('127.0.0.1','root','123456','han',charset='utf8') self.cursor = self.conn.cursor() def process_item(self,item,spider): # 插入数据库 sql ,data = item.get_sql() self.cursor.execute(sql,data) self.conn.commit() return item def close_spider(self,spider): self.cursor.close() self.conn.close()
# settings.py
# -*- coding: utf-8 -*- # Scrapy settings for day11 project # # For simplicity, this file contains only settings considered important or # commonly used. You can find more settings consulting the documentation: # # http://doc.scrapy.org/en/latest/topics/settings.html # http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html # http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html BOT_NAME = 'day11' SPIDER_MODULES = ['day11.spiders'] NEWSPIDER_MODULE = 'day11.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent #USER_AGENT = 'day11 (+http://www.yourdomain.com)' # Obey robots.txt rules ROBOTSTXT_OBEY = False # Configure maximum concurrent requests performed by Scrapy (default: 16) CONCURRENT_REQUESTS = 64 # Configure a delay for requests for the same website (default: 0) # See http://scrapy.readthedocs.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) # 默认是True # COOKIES_ENABLED = False # Disable Telnet Console (enabled by default) #TELNETCONSOLE_ENABLED = False # Override the default request headers: # 默认请求头 生效范围 所有爬虫 DEFAULT_REQUEST_HEADERS = { 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Language': 'en', # 'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36' } # Enable or disable spider middlewares # See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # 'day11.middlewares.Day11SpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html DOWNLOADER_MIDDLEWARES = { # 数字越小 越先经过 范围 1-999 # 'day11.middlewares.MyCustomDownloaderMiddleware': 543, } # Enable or disable extensions # See http://scrapy.readthedocs.org/en/latest/topics/extensions.html #EXTENSIONS = { # 'scrapy.extensions.telnet.TelnetConsole': None, #} # Configure item pipelines # See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html ITEM_PIPELINES = { 'day11.pipelines.JobPipeline': 1, 'day11.pipelines.JobMysqlPipeline': 2, } # Enable and configure the AutoThrottle extension (disabled by default) # See http://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 http://scrapy.readthedocs.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'
# 爬取结果如下:
兄弟连学python
Python学习交流、资源共享群:563626388 QQ