# 用框架爬取腾讯招聘首页
# tencent.py
# -*- coding: utf-8 -*- import scrapy from ..items import JobItem from datetime import datetime class TencentSpider(scrapy.Spider): name = 'tencent' allowed_domains = ['tencent.com'] start_urls = ['https://hr.tencent.com/position.php/'] def parse(self, response): job_list = response.xpath('.//tr')[1:-2] for job in job_list: item = JobItem() p_name = job.xpath('.//td[1]/a/text()').extract()[0] p_type = job.xpath('.//td[2]/text()').extract() if p_type: p_type = p_type[0] else: p_type = '' p_number = job.xpath('.//td[3]/text()').extract()[0] p_location = job.xpath('.//td[4]/text()').extract()[0] p_date = job.xpath('.//td[5]/text()').extract()[0] item['p_name'] = p_name item['p_type'] = p_type item['p_number'] = p_number item['p_location'] = p_location item['p_date'] = p_date item['crawl_time'] = datetime.now().strftime('%Y-%m-%d %H:%M:%S') item['spider_name'] = self.name yield item print(p_name,p_type,p_number,p_location,p_date) # 构造请求对象 next_cls = response.xpath('.//a[@id="next"]/@class').extract_first() if next_cls is None: next_url = response.xpath('.//a[@id="next"]/@href').extract_first() next_url = 'https://hr.tencent.com/' + next_url # callback 回调函数 指定解析函数 yield scrapy.Request(next_url,callback=self.parse)
# 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 # 明确爬取数据项 类似django models class JobItem(scrapy.Item): p_name = scrapy.Field() p_type = scrapy.Field() p_number = scrapy.Field() p_location = scrapy.Field() p_date = scrapy.Field() crawl_time = scrapy.Field() # 数据来源 spider_name = scrapy.Field()
# 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 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()
# 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 = 32 # 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' } # 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, } # 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'
# main.py
from scrapy import cmdline cmdline.execute('scrapy crawl tencent'.split())
# 爬取部分结果如下:
2018-04-10 14:52:45 [scrapy.core.scraper] DEBUG: Scraped from <200 https://hr.tencent.com/position.php?&start=310> {'crawl_time': '2018-04-10 14:52:45', 'p_date': '2018-04-10', 'p_location': '深圳', 'p_name': '26564-游戏内容编辑(深圳)', 'p_number': '2', 'p_type': '内容编辑类', 'spider_name': 'tencent'} 2018-04-10 14:52:45 [scrapy.core.scraper] DEBUG: Scraped from <200 https://hr.tencent.com/position.php?&start=310> {'crawl_time': '2018-04-10 14:52:45', 'p_date': '2018-04-10', 'p_location': '深圳', 'p_name': '15570-御龙在天端游运营商业化策划(深圳)', 'p_number': '1', 'p_type': '产品/项目类', 'spider_name': 'tencent'} 15614-天刀3D角色设计师(上海) 设计类 1 上海 2018-04-10 26564-游戏内容编辑(深圳) 内容编辑类 2 深圳 2018-04-10 15570-御龙在天端游运营商业化策划(深圳) 产品/项目类 1 深圳 2018-04-10 2018-04-10 14:52:45 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://hr.tencent.com/position.php?&start=320#a> (referer: https://hr.tencent.com/position.php?&start=310) MIG08-产品经理(上海) 产品/项目类 1 上海 2018-04-10 25663-腾讯云AI行业方案专家(北京) 产品/项目类 1 北京 2018-04-10 2018-04-10 14:52:45 [scrapy.core.scraper] DEBUG: Scraped from <200 https://hr.tencent.com/position.php?&start=320>
兄弟连学python
Python学习交流、资源共享群:563626388 QQ