利用Scrapy框架爬取LOL皮肤站高清壁纸

# -*- coding: utf-8 -*-
import scrapy
from practice.items import PracticeItem
from urllib import parse


class LolskinSpider(scrapy.Spider):
    name = 'lolskin'
    allowed_domains = ['lolskin.cn']
    start_urls = ['https://lolskin.cn/champions.html']

    # 获取所有英雄链接
    def parse(self, response):
        item = PracticeItem()
        item['urls'] = response.xpath('//div[2]/div[1]/div/ul/li/a/@href').extract()
        for url in item['urls']:
            self.csurl = 'https://lolskin.cn'
            yield scrapy.Request(url=parse.urljoin(self.csurl, url), dont_filter=True, callback=self.bizhi)
        return item

    # 获取所有英雄皮肤链接
    def bizhi(self, response):
        skins = (response.xpath('//td/a/@href').extract())
        for skin in skins:
            yield scrapy.Request(url=parse.urljoin(self.csurl, skin), dont_filter=True, callback=self.get_bzurl)

    # 采集每个皮肤的壁纸，获取壁纸链接
    def get_bzurl(self, response):
        item = PracticeItem()
        image_urls = response.xpath('//body/div[1]/div/a/@href').extract()
        image_name = response.xpath('//h1/text()').extract()
        yield {
            'image_urls': image_urls,
            'image_name': image_name
        }
        return item

# -*- 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 PracticeItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    # titles = scrapy.Field()
    # yxpngs = scrapy.Field()
    urls = scrapy.Field()
    skin_name = scrapy.Field()  # 皮肤名
    image_urls = scrapy.Field()  # 皮肤壁纸url
    images = scrapy.Field()

# -*- 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 os
import re
from scrapy.pipelines.images import ImagesPipeline
import scrapy


# class PracticePipeline(object):
#     def __init__(self):
#         self.file = open('text.csv', 'a+')
#
#     def process_item(self, item, spider):
#         # os.chdir('lolskin')
#         # for title in item['titles']:
#         #     os.makedirs(title)
#         skin_name = item['skin_name']
#         skin_jpg = item['skin_jpg']
#         for i in range(len(skin_name)):
#             self.file.write(f'{skin_name[i]},{skin_jpg}
')
#         self.file.flush()
#         return item
#
#     def down_bizhi(self, item, spider):
#         self.file.close()


class LoLPipeline(ImagesPipeline):
    def get_media_requests(self, item, info):
        for image_url in item['image_urls']:
            yield scrapy.Request(image_url, meta={'image_name': item['image_name']})

    # 修改下载之后的路径以及文件名
    def file_path(self, request, response=None, info=None):
        image_name = re.findall('/skin/(.*?)/', request.url)[0] + "/" + request.meta[f'image_name'][0] + '.jpg'
        return image_name

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

# Scrapy settings for practice 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
import os

BOT_NAME = 'practice'

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

# Crawl responsibly by identifying yourself (and your website) on the user-agent
# USER_AGENT = 'practice (+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
# 设置延时
DOWNLOAD_DELAY = 1
# 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 = {
#    'practice.middlewares.PracticeSpiderMiddleware': 543,
# }

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#    'practice.middlewares.PracticeDownloaderMiddleware': 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 = {
    # 'practice.pipelines.PracticePipeline': 300,
    # 'scrapy.pipelines.images.ImagesPipeline': 1，
    'practice.pipelines.LoLPipeline': 1
}
# 设置采集文件夹路径
IMAGES_STORE = 'E:PythonscrapypracticepracticeLOLskin'
# 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'

from scrapy.cmdline import execute

execute(['scrapy', 'crawl', 'lolskin'])