360图片网站批量抓取

闲着无聊，最近刚好看完scrapy框架，想着找个网站练练手，想来想去，把书中的360图片抓取拓展为批量抓取各版块图片，并分类保存，该网站为动态加载网站（Ajax），基本上没有什么反爬措施，因此抓取起来很顺利。这个小项目重点在于重写图片保存路径，各模块代码具体为：

1、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 Images360Item(scrapy.Item):
    image_urls = scrapy.Field()
    image_path = scrapy.Field()

2、images360.py

# -*- coding: utf-8 -*-
import scrapy
from ..items import Images360Item
import json


class Images360Spider(scrapy.Spider):
    name = 'images360'
    allowed_domains = ['image.so.com']
    type_list = ['beauty', 'video', 'wallpaper', 'design', 'funny', 'art', 'car', 'photography', 'food', 'home', 'pet']
    page_number = 50

    def start_requests(self):
        base_url = 'http://image.so.com/zjl?ch={}&sn={}'
        for type in self.type_list:
            for i in range(0, self.page_number * 30, 30):
                item = Images360Item()
                item['image_path'] = type
                url = base_url.format(type, i)
                yield scrapy.Request(
                    url=url,
                    meta={'item': item},
                    callback=self.get_image,
                )

    def get_image(self, response):
        item = response.meta['item']
        image_list = [image['qhimg_url'] for image in json.loads(response.text)['list']]
        item['image_urls'] = image_list
        yield item

3、pipelines.py（重点）

# -*- 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
from scrapy.pipelines.images import ImagesPipeline
from scrapy import Request


class Images360Pipeline(object):
    def process_item(self, item, spider):
        return item


class MyImages360Pipeline(ImagesPipeline):
    def get_media_requests(self, item, info):
        for image in item['image_urls']:
            yield Request(
                url=image,
                meta={'image_path': item['image_path']}
            )

    def file_path(self, request, response=None, info=None):
        image_name = request.url.split('/')[-1]
        image_path = request.meta['image_path']
        filename = '{}{}'.format(image_path, image_name)
        return filename

4、settings.py

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

# Scrapy settings for Images360 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 = 'Images360'

SPIDER_MODULES = ['Images360.spiders']
NEWSPIDER_MODULE = 'Images360.spiders'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
# USER_AGENT = 'Images360 (+http://www.yourdomain.com)'

# 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://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 = {
#    'Images360.middlewares.Images360SpiderMiddleware': 543,
# }

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#     'Images360.middlewares.Images360DownloaderMiddleware': 543,
#     'Images360.middlewares.RandomUserAgentDownloaderMiddleware': 200,
#     'Images360.middlewares.RandomProxyDownloaderMiddleware': 250,
# }

# 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 = {
    # 'Images360.pipelines.Images360Pipeline': 300,
    'Images360.pipelines.MyImages360Pipeline': 200,
}

# 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'

IMAGES_STORE = r'E:360图片'

REDIS_HOST = '127.0.0.1'
REDIS_PORT = 6379
REDIS_DB = 0
REDIS_PWD = '123456'
REDIS_PROXY_KEY = 'proxy'

LOG_LEVEL = 'WARNING'

最后附上抓取结果截图：