SCrapy

由于说到Python爬虫一定绕不过Scrapy框架，所以这次也就尝试将之前的爬虫用Scrapy框架爬取拉勾网,这个要感谢Mr_Cxy的代码。
普通版：Python爬虫作业 | 爬取拉勾职位信息

文件目录

文件目录

直接上代码

IDE调试入口

entrypoint.py

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

from scrapy.cmdline import execute
execute(['scrapy', 'crawl', 'lagouscrapy'])

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 LagouscrapyItem(scrapy.Item, scrapy.Field):
    # define the fields for your item here like:
    # name = scrapy.Field()
    positionName = scrapy.Field()
    companyFullName = scrapy.Field()
    workYear = scrapy.Field()
    salary = scrapy.Field()
    district = scrapy.Field()

默认创建项目生成 middlewares.py

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

# Define here the models for your spider middleware
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals


class LagouscrapySpiderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.
        for i in result:
            yield i

    def process_spider_exception(response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Response, dict
        # or Item objects.
        pass

    def process_start_requests(start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

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 MySQLdb


class LagouscrapyPipeline(object):
    def process_item(self, item, spider):
        conn = MySQLdb.Connection(host='172.16.110.163', user='lagou', passwd='', db='lagou', charset='utf8')
        cursor = conn.cursor()
        cursor.execute("insert into jobinfo(positionname,companyfullname,workyear,salary,district) values(%s,%s,%s,%s,%s)",(item['positionName'], item['companyFullName'], item['workYear'], item['salary'], item['district'],))
        conn.commit()
        cursor.close()
        conn.close()
        return item

settings.py

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

# Scrapy settings for lagouscrapy 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 = 'lagouscrapy'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.81 Safari/537.36'

# 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)
#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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'lagouscrapy.middlewares.LagouscrapySpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'lagouscrapy.middlewares.ProxyMiddleware': 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 = {
    'lagouscrapy.pipelines.LagouscrapyPipeline': 300,
}

# 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'

scrapy.cfg

# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html

[settings]
default = lagouscrapy.settings

[deploy]
#url = http://localhost:6800/
project = lagouscrapy

lagouscrapy.py

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

import sys
import json
import requests
import scrapy
from lxml import  etree
from scrapy.http import FormRequest
reload(sys)
sys.path.append('..')
sys.setdefaultencoding('utf-8')

class lagouscrapy(scrapy.Spider):
    name = 'lagouscrapy'
    city_list = ['北京', '上海', '广州', '深圳', '青岛','杭州']
    position_list = ['Python工程师', '大数据', '云计算', 'docker', '中间件', 'Node.js', '数据挖掘', \
           '自然语言处理', '搜索算法', '精准推荐', '全栈工程师', '图像处理','机器学习', '语音识别']
    base_url = 'https://www.lagou.com/jobs/list_%s?px=default&city=%s'
    cookies={
        'user_trace_token':'20170426104536-43eecce9f0d84710a63c6cfc34534d3d',
        'LGUID':'20170426104536-6d56bd01-2a2a-11e7-beac-525400f775ce',
        'showExpriedIndex':1,
        'showExpriedCompanyHome':1,
        'showExpriedMyPublish':1,
        'hasDeliver':80,
        'index_location_city':'%E6%9D%AD%E5%B7%9E',
        'JSESSIONID':'D4E8E92335902847EAFC290EECC581CB',
        'TG-TRACK-CODE':'search_code',
        'SEARCH_ID':'b642e683bb424e7f8622b0c6a17ffeeb',
        'Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6':'1493177918,1493192358,1493867575,1494227146',
        'Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6':'1494310035',
        '_ga':'GA1.2.605883278.1493174738',
        'LGSID':'20170509140720-c2ed1f62-347d-11e7-bcb7-525400f775ce',
        'LGRID':'20170509140720-c2ed2205-347d-11e7-bcb7-525400f775ce',
        '_putrc':''
    }
    headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36',
            'Cookie':'user_trace_token=20170426104536-43eecce9f0d84710a63c6cfc34534d3d; LGUID=20170426104536-6d56bd01-2a2a-11e7-beac-525400f775ce; index_location_city=%E6%9D%AD%E5%B7%9E; showExpriedIndex=1; showExpriedCompanyHome=1; showExpriedMyPublish=1; hasDeliver=80; login=false; unick=""; _putrc=""; TG-TRACK-CODE=search_code; JSESSIONID=D4E8E92335902847EAFC290EECC581CB; _gid=GA1.2.167447017.1494310035; _gat=1; _ga=GA1.2.605883278.1493174738; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1493177918,1493192358,1493867575,1494227146; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1494310035; LGSID=20170509140720-c2ed1f62-347d-11e7-bcb7-525400f775ce; PRE_UTM=; PRE_HOST=; PRE_SITE=; PRE_LAND=https%3A%2F%2Fwww.lagou.com%2Fjobs%2Flist_python%25E5%25B7%25A5%25E7%25A8%258B%25E5%25B8%2588%3Fcity%3D%25E6%259D%25AD%25E5%25B7%259E; LGRID=20170509140720-c2ed2205-347d-11e7-bcb7-525400f775ce; SEARCH_ID=403ecbaea5d24a2a9abec368e74a8984',
            'Host':'www.lagou.com',
            'Origin':'https://www.lagou.com'
    }
    def get_complete_list(self):
        complete_list = []
        for position in self.position_list:
            position = position.decode('utf-8')
            for city in self.city_list:
                city = city.decode('utf-8')
                dict = {}
                url = self.base_url % (position, city)
                html = requests.get(url, headers=self.headers).content
                selector = etree.HTML(html)
                total_page = selector.xpath('//ul[@id="order"]/li/div[4]/div[3]/span[2]/text()')[0]
                dict['city'] = city
                dict['position'] = position
                dict['total_page'] = total_page
                complete_list.append(dict)
                print complete_list
        return complete_list

    def start_requests(self):
        complete_list = self.get_complete_list()
        json_url = 'https://www.lagou.com/jobs/positionAjax.json?px=default&city=%s&needAddtionalResult=false'
        for dict in complete_list:
            city = dict['city']
            position = dict['position']
            total_page = int(dict['total_page'])
            url = json_url % city
            for page in range(1,total_page+1):
                post_data = {
                    'first': 'true',
                    'pn': str(page),
                    'kd': position
                }
                yield FormRequest(url, formdata=post_data, cookies=self.cookies, callback=self.parse_json)

    def parse_json(self, response):
        json_data = json.loads(response.text.decode('utf-8'))
        position_data = json_data["content"]["positionResult"]['result']
        for position in position_data:
            item = {}
            item['positionName'] = position['positionName'].decode()
            item['companyFullName'] = position['companyFullName'].decode()
            item['workYear'] = position['workYear'].decode()
            item['salary'] = position['salary'].decode()
            if position['district'] is not None:
                item['district'] = position['city'].decode() + position['district'].decode()
            else:
                item['district'] = position['city'].decode()
        yield item

入库结果

image.png

待解决:

middlewares.py中关于代理的使用，提高爬取的效率跟数据量

参考资料：

scrapy-chinese
https://stevenzhao.gitbooks.io/scrapy-chinese/content/index.html

Scrapy 1.3 documentation
https://doc.scrapy.org/en/latest/