41.配置完善爬虫代码文件及图片下载文件重命名问题-2

Posted 2021-01-14 lvjing

解决图片下载重命名保存本地,直接上代码（在原来代码做了一定的修改）。
总结：主要就是添加配置一个内置的函数，对保存的东西进行修改再存储，主要问题还是再piplines的设置里面。

效果如图：

hm5988.py


# -*- coding: utf-8 -*-
import scrapy
from hm5988_web.items import Hm5988WebItem

class Hm5988Spider(scrapy.Spider):
    name = ‘hm5988‘
    allowed_domains = [‘www.hm5988.com‘]
    start_urls = [‘http://www.hm5988.com/goods/CATE0.html?page=1‘]
    custom_settings = {
        ‘DOWNLOAD_DELAY‘: 0.5,
        "ITEM_PIPELINES": {
            ‘hm5988_web.pipelines.ImagePipeline‘: 300,
            ‘hm5988_web.pipelines.mysqlPipeline‘: 302,
        },
        "DOWNLOADER_MIDDLEWARES": {
            ‘hm5988_web.middlewares.Hm5988WebDownloaderMiddleware‘: 500,
        },
    }
    def parse(self, response):
        # 获取页码
        p_url = response.xpath("//li[@class=‘last‘]/a/@href").extract_first()
        page_num = p_url.split(‘=‘)[1]
        # print(page_num)
        for i in range(2, int(page_num)+1):
            url = ‘http://www.hm5988.com/goods/CATE0.html?page={}‘.format(i)
            yield scrapy.Request(url=url, callback=self.parse_detail)

    def parse_detail(self,response):
        link_urls = response.xpath("//li[@class=‘mr10 mb20‘]/a/@href").extract()
        for link_url in link_urls:
            # print(link_url)
            yield scrapy.Request(url=link_url, callback=self.parse_detail2)

    def parse_detail2(self, response):

        item = Hm5988WebItem()
        # 所属分类
        _type = response.xpath("//div[@class=‘current‘]/a[6]/text()").extract_first()
        item[‘_type‘] = _type
        # 产品名称
        name = response.xpath("//div[@class=‘txt-t fl‘]/li[@class=‘fs22 gc3 fw‘]/text()").extract_first()
        item[‘name‘] = name
        # 详情图片
        pic = response.xpath("//div[@class=‘pic-box fl p10‘]/img[@class=‘pic-big‘]/@src").extract_first()
        item[‘pic‘] = pic

        yield item

        print(‘*‘*100)

items.py

# -*- 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 Hm5988WebItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()

    # 所属分类
    _type = scrapy.Field()
    # 产品名称
    name = scrapy.Field()
    # 详情图片
    pic = scrapy.Field()

middlewares.py


# -*- 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 Hm5988WebSpiderMiddleware(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 Hm5988WebDownloaderMiddleware(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)

piplines.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
from scrapy.conf import settings
from scrapy import Request
from scrapy.exceptions import DropItem
from scrapy.pipelines.images import ImagesPipeline
import pymysql

class Hm5988WebPipeline(object):
    def process_item(self, item, spider):
        return item

# 数据保存mysql
class MysqlPipeline(object):

    def open_spider(self, spider):
        self.host = settings.get(‘MYSQL_HOST‘)
        self.port = settings.get(‘MYSQL_PORT‘)
        self.user = settings.get(‘MYSQL_USER‘)
        self.password = settings.get(‘MYSQL_PASSWORD‘)
        self.db = settings.get((‘MYSQL_DB‘))
        self.table = settings.get(‘TABLE‘)
        self.client = pymysql.connect(host=self.host, user=self.user, password=self.password, port=self.port, db=self.db, charset=‘utf8‘)

    def process_item(self, item, spider):
        item_dict = dict(item)
        cursor = self.client.cursor()
        values = ‘,‘.join([‘%s‘] * len(item_dict))
        keys = ‘,‘.join(item_dict.keys())
        sql = ‘INSERT INTO {table}({keys}) VALUES ({values})‘.format(table=self.table, keys=keys, values=values)
        try:
            if cursor.execute(sql, tuple(item_dict.values())):  # 第一个值为sql语句第二个为 值 为一个元组
                print(‘数据入库成功!‘)
                self.client.commit()
        except Exception as e:
            print(e)

            self.client.rollback()
        return item

    def close_spider(self, spider):

        self.client.close()

class ImagePipeline(ImagesPipeline):

    def item_completed(self, results, item, info):
        image_paths = [x[‘path‘] for ok, x in results if ok]
        if not image_paths:
            raise DropItem(‘Image Downloaded Failed‘)
        return item

    def get_media_requests(self, item, info):
        yield Request(item[‘pic‘], meta={‘item‘:item})

    def file_path(self, request, response=None, info=None):
        item = request.meta[‘item‘]
        filename = u‘full/{}.jpg‘.format(item[‘name‘])
        return filename

settings.py


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

# Scrapy settings for hm5988_web 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 = ‘hm5988_web‘

SPIDER_MODULES = [‘hm5988_web.spiders‘]
NEWSPIDER_MODULE = ‘hm5988_web.spiders‘

IMAGES_STORE = ‘./images‘

# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = ‘hm5988_web (+http://www.yourdomain.com)‘

# Obey robots.txt rules
# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# mysql配置参数
MYSQL_HOST = "172.16.10.157"
MYSQL_PORT = 3306
MYSQL_USER = "root"
MYSQL_PASSWORD = "123456"
MYSQL_DB = ‘web_datas‘
TABLE = "hm5988_2"

# 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 = {
#    ‘hm5988_web.middlewares.Hm5988WebSpiderMiddleware‘: 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   ‘hm5988_web.middlewares.Hm5988WebDownloaderMiddleware‘: 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 = {
   ‘hm5988_web.pipelines.ImagePipeline‘: 300,
   ‘hm5988_web.pipelines.Hm5988WebPipeline‘: 302,
}

# 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‘