python之scrapy爬取某集团招聘信息

1、创建工程

scrapy startproject gosuncn

2、创建项目

cd gosuncn
 scrapy genspider gaoxinxing gosuncn.zhiye.com

3、运行项目

 crawl gaoxinxing

4、gaoxinxing.py代码

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

logger = logging.getLogger(__name__)
#引入日志
class GaoxinxingSpider(scrapy.Spider):
    name = 'gaoxinxing'
    allowed_domains = ['gosuncn.zhiye.com']
    start_urls = ['http://gosuncn.zhiye.com/Social']
    next_page_num = 1
    def parse(self, response):
        tr_list = response.xpath("//table[@class='jobsTable']/tr")[1:]
        #print(tr_list)
        for tr in tr_list:
            item = {}
            item["position"]=tr.xpath(".//td[1]/a/text()").extract_first()
            item["platform"] = tr.xpath(".//td[3]/text()").extract_first()
            item["num"] = tr.xpath(".//td[4]/text()").extract_first()
            item["time"] = tr.xpath(".//td[6]/text()").extract_first()
            logger.warning(item) #打印日志
            yield item

        #next_page_url = response.xpath("//div[@class='pager2']//a[@class='next']/@href").extract_first()
        #print(next_page_url)
        self.next_page_num = self.next_page_num+1
        if self.next_page_num<=4:
            next_url = "http://gosuncn.zhiye.com/social/?PageIndex=" + str(self.next_page_num)
            print(next_url)
            yield scrapy.Request(
                next_url,
                callback=self.parse
            )

View Code

5、settings.py文件

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

# Scrapy settings for gosuncn 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 = 'gosuncn'

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

LOG_LEVEL="WARNING"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'gosuncn (+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 = {
#    'gosuncn.middlewares.GosuncnSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'gosuncn.middlewares.GosuncnDownloaderMiddleware': 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 = {
   'gosuncn.pipelines.GosuncnPipeline': 300,
}
LOG_LEVEL ="WARNING"
LOG_FILE = "./log.log"
# 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'

View Code

6、pipelines.py文件

# -*- 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


class GosuncnPipeline(object):
    def process_item(self, item, spider):
        print(item)
        return item

View Code