Python3爬虫爬取英雄联盟高清桌面壁纸功能示例【基于Scrapy框架】

scrapy startproject loldesk

import scrapy
class LoldeskItem(scrapy.Item):
  name = scrapy.Field()
  ImgUrl = scrapy.Field()
  pass

import scrapy
from loldesk.items import LoldeskItem
class loldeskpiderSpider(scrapy.Spider):
  name = "loldesk"
  allowed_domains = ["www.win4000.com"]
  # 抓取链接
  start_urls = [
    'http://www.win4000.com/zt/lol.html'
  ]
  def parse(self, response):
    list = response.css(".Left_bar ul li")
    for img in list:
      imgurl = img.css("a::attr(href)").extract_first()
      imgurl2 = str(imgurl)
      next_url = response.css(".next::attr(href)").extract_first()
      if next_url is not None:
        # 下一页
        yield response.follow(next_url, callback=self.parse)
      yield scrapy.Request(imgurl2, callback=self.content)
  def content(self, response):
    item = LoldeskItem()
    item['name'] = response.css(".pic-large::attr(title)").extract_first()
    item['ImgUrl'] = response.css(".pic-large::attr(src)").extract()
    yield item
    # 判断页码
    next_url = response.css(".pic-next-img a::attr(href)").extract_first()
    allnum = response.css(".ptitle em::text").extract_first()
    thisnum = next_url[-6:-5]
    if int(allnum) > int(thisnum):
      # 下一页
      yield response.follow(next_url, callback=self.content)

from scrapy.pipelines.images import ImagesPipeline
from scrapy.exceptions import DropItem
from scrapy.http import Request
import re
class MyImagesPipeline(ImagesPipeline):
  def get_media_requests(self, item, info):
    for image_url in item['ImgUrl']:
      yield Request(image_url,meta={'item':item['name']})
  def file_path(self, request, respOnse=None, info=None):
    name = request.meta['item']
    name = re.sub(r'[？\\*|“<>:/()0123456789]', '', name)
    image_guid = request.url.split('/')[-1]
    filename = u'full/{0}/{1}'.format(name, image_guid)
    return filename
  def item_completed(self, results, item, info):
    image_path = [x['path'] for ok, x in results if ok]
    if not image_path:
      raise DropItem('Item contains no images')
    item['image_paths'] = image_path
    return item

# 设置图片存储路径
IMAGES_STORE = 'F:/python/loldesk'
#启动pipeline中间件
ITEM_PIPELINES = {
  'loldesk.pipelines.MyImagesPipeline': 300,
}

scrapy crawl loldesk