scrapy爬虫案例数据存入MongoDB

Posted 2021-03-16 圣诞。

爬虫py文件

# -*- coding: utf-8 -*-
import scrapy
from ..items import RtysItem


class RtSpider(scrapy.Spider):
    name = 'rt'      #爬虫名，启动项目时用
    # allowed_domains = ['www.baidu.com']     #定义爬虫范围  注释掉就可以
    start_urls = ['https://www.woyaogexing.com/touxiang/']    #起始url 项目启动时，会自动向url发起请求
    def parse(self, response):  # response直接代替响应
        div_list=response.xpath('//div[@class="list-left z"]/div[2]/div')  #解析数据
        for i in div_list:
            name = i.xpath('./a/text()').extract_first() #变量名 要与items.py中实例化的变量名一样
            img_url = i.xpath('./a/img/@src').extract_first()
            lianjie_url = i.xpath('./a/@href').extract_first()
            items = RtysItem()  #实例化items
            items['name']=name    #将实例化的字段存进字典中
            items['img_url']=img_url
            items['lianjie_url']=lianjie_url
            yield items  #发送给管道

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://docs.scrapy.org/en/latest/topics/item-pipeline.html
import pymongo

class RtysPipeline(object):
    def process_item(self, item, spider):
        coon = pymongo.MongoClient('localhost',27017)  #连接mongodb数据库
        db = coon.rtys  #创建数据库 有的话就直接用 没有就相当于创建
        table = db.rt   #创建表 有的话就直接用 没有就相当于创建
        table.insert_one(dict(item))  #查入一条数据 转化成字典
        return item

存入Mongo时要注意settings.py的配置 注释部分需要打开

settings.py文件

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

# Scrapy settings for rtys project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'rtys'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent

USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False   #False 爬的网站不受限制   True爬的网站受限制

# 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://docs.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://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'rtys.middlewares.RtysSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html


篡改ip的时候需要打开中间件
#DOWNLOADER_MIDDLEWARES = {
#    'rtys.middlewares.RtysDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {     #需要注开
   'rtys.pipelines.RtysPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.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://docs.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'

items.py

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

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class RtysItem(scrapy.Item):
    # define the fields for your item here like:
    name = scrapy.Field()  #设置要爬取的字段名 爬几个就写几个
    img_url = scrapy.Field()
    lianjie_url = scrapy.Field()
    pass