首先执行如下命令创建一个scrapy项目
scrapy startproject kaijiang
主要有如下几个核心文件：
items.py: 在项目的根目录
middlewares.py: 在项目的根目录
pipelines.py: 在项目的根目录
kaijiang.py: 在spiders目录
settings.py: 在项目的根目录
我的实例是爬取和讯人物信息，一个实例地址为：http://kaijiang.500.com
项目目标是：根据几个初始的url，爬取到html源码，并从源码中提取出同样的url，进行迭代爬取
我们还要创建一个数据库,因为要把提取到的内容存储到数据库中
创建库的命令:
create database shuangseqiu charset=utf8;
选中库命令:
use shuangseqiu;
创建表的命令:
create table kaijiang(times varchar(100),hong varchar(100),lan varchar(100));
然后就看下面的操作就可以了
第一，item.py文件的内容如下：
# -*- 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 ShuangseqiuItem(scrapy.Item):
# define the fields for your item here like:
url = scrapy.Field()
times = scrapy.Field()
hong = scrapy.Field()
lan = scrapy.Field()
该文件的作用是：定义需要从html中抽取出来的字段名称
第二，spiders目录下的kaijiang.py文件内容，我的名字是叫kaijiang.py
# -*- coding: utf-8 -*-
import scrapy
from ShuangSeqiu.items import ShuangseqiuItem
class KaijiangSpider(scrapy.Spider):
name = 'kaijiang'
allowed_domains = ['kaijiang.500.com']
start_urls = ['http://kaijiang.500.com/shtml/ssq/19002.shtml']
def parse(self, response):
# item = ShuangseqiuItem()
se_url = response.xpath('//div[@class="iSelectList"]//a/@href').extract()
for url in se_url:
yield scrapy.Request(url=url,callback=self.zhongjiang)
def zhongjiang(self,response):
# item = response.meta.get('item')
item = ShuangseqiuItem()
times = response.xpath('//span[@class="span_right"]/text()').extract_first('')
hong = ','.join(response.xpath('//div[@class="ball_box01"]/ul//li/text()').extract())[:-3]
lan = ','.join(response.xpath('//div[@class="ball_box01"]/ul//li/text()').extract())[-2:]
item['times'] = times
item['hong'] = hong
item['lan'] = lan
yield item
该文件的作用，是定义初始url
第三，pipilines.py
# -*- 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 pymysql
class ShuangseqiuPipeline(object):
def __init__(self, host, port, user, pwd, db):
self.client = pymysql.Connect(host, user, pwd, db, port, charset='utf8')
self.cursor = self.client.cursor()
@classmethod
def from_crawler(cls, crawler):
host = crawler.settings['MYSQL_HOST']
port = crawler.settings['MYSQL_PORT']
user = crawler.settings['MYSQL_USER']
pwd = crawler.settings['MYSQL_PWD']
db = crawler.settings['MYSQL_DB']
return cls(host, port, user, pwd, db)
def process_item(self, item, spider):
insert_sql = """
insert into kaijiang(times,hong,lan)
VALUE (%s, %s, %s)
"""
try:
self.cursor.execute(insert_sql, (item['times'], item['hong'], item['lan']))
self.client.commit()
except Exception as err:
print(err)
self.client.rollback()
return item
第二步中parse和zhongjiang方法返回的内容，这里可以获取到，可以在这里将爬取到的内容写到文件中
第四， middlewares.py文件内容如下
# -*- coding: utf-8 -*-
# Define here the models for your spider middleware
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
class ShuangseqiuSpiderMiddleware(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(self, 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(self, 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(self, 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(self, 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)
class ShuangseqiuDownloaderMiddleware(object):
# Not all methods need to be defined. If a method is not defined,
# scrapy acts as if the downloader 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_request(self, request, spider):
# Called for each request that goes through the downloader
# middleware.
# Must either:
# - return None: continue processing this request
# - or return a Response object
# - or return a Request object
# - or raise IgnoreRequest: process_exception() methods of
# installed downloader middleware will be called
return None
def process_response(self, request, response, spider):
# Called with the response returned from the downloader.
# Must either;
# - return a Response object
# - return a Request object
# - or raise IgnoreRequest
return response
def process_exception(self, request, exception, spider):
# Called when a download handler or a process_request()
# (from other downloader middleware) raises an exception.
# Must either:
# - return None: continue processing this exception
# - return a Response object: stops process_exception() chain
# - return a Request object: stops process_exception() chain
pass
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
第五， settings.py文件
# -*- coding: utf-8 -*-
# Scrapy settings for ShuangSeqiu 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 = 'ShuangSeqiu'
SPIDER_MODULES = ['ShuangSeqiu.spiders']
NEWSPIDER_MODULE = 'ShuangSeqiu.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 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 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 = {
# 'ShuangSeqiu.middlewares.ShuangseqiuSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'ShuangSeqiu.middlewares.ShuangseqiuDownloaderMiddleware': 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 = {
'ShuangSeqiu.pipelines.ShuangseqiuPipeline': 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
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
MONGODB_HOST = '127.0.0.1'
MONGODB_PORT= 27017
MONGODB_DBNAME = "shuangseqiu"
MONGODB_SHEETNAME= "kaijiang"
#关于数据库的相关配置
MYSQL_HOST = '127.0.0.1'
MYSQL_PORT = 3306
MYSQL_USER = 'root'
MYSQL_PWD = '1'
MYSQL_DB = 'shuangseqiu'
大功告成咯
接下来就启动爬虫吧：
scrapy crawl kaijiang
步骤总结:
爬取数据：
scrapy的基本用法
- 通过命令创建项目
scrapy startproject 项目名称 - 用pycharm打开项目
- 通过命令创建爬虫
scrapy genspider 爬虫名称 域名 - 配置settings
robots_obey=False
Download_delay=0.5
Cookie_enable=False - 自定义UserAgentMiddleWare
可以直接粘现成的
或者自己通过研究源码实现 - 开始解析数据
- 先大致规划一下需要几个函数
- 函数1跳转到函数2使用 yield scrapy.Request(url,callback,meta,dont_filter)
- 将数据封装到items,记得yield item
- 自定义pipelines将数据存储到数据库/文件中