Scrapy 下载多层请求、多页图片(下载使用urllib.request.urlretrieve方法)

思路

  	1. 确定数据结构 item
  	2. 写爬虫程序 spider
  		① 每一页的每一个详情页 url
  		② 翻页
  		③ 详情页匹配目标数据
  	3. 管道处理数据 piplines
  		① 保存到 excel
  		② 下载图片
  	4. 配置设置 settings

①items.py

import scrapy

class Ftb2Item(scrapy.Item):
    game_title = scrapy.Field()  # 比赛详情标题
    name_1 = scrapy.Field()  # 主队球队名称
    logo_src_1 = scrapy.Field()  # 主队球队logo
    name_2 = scrapy.Field()  # 客队球队名称
    logo_src_2 = scrapy.Field()  # 客队球队logo
    

② ftb.py (spiders)

import scrapy
from ..items import Ftb2Item


class FtbSpider(scrapy.Spider):
    name = 'ftb'
    allowed_domains = ['mynba.tv']

    domain = 'http://www.mynba.tv'
    base_page_url = 'http://www.mynba.tv/video/?page='
    page = 1

    # start_urls = ['http://www.mynba.tv/video/?page=1']
    # 重写start_requests
    def start_requests(self):
        url = "http://www.mynba.tv/video/?page=1"
        yield scrapy.Request(url, callback=self.parse)

    def parse(self, response):
        detail_urls = response.xpath('/html/body/div[1]/div[2]/div[2]/div[1]/div/a/@href').extract()

        # 进一步请求每一页的比赛详情页
        for detail_url in detail_urls:
            detail_url = FtbSpider.domain + detail_url
            print("请求 " + detail_url + '详情页...')
            yield scrapy.Request(url=detail_url, callback=self.parse_detail_info)  # 一页的每个比赛

        # 请求多页(前10页)
        if self.page < 11:
            self.page += 1
            page_url = base_page_url = 'http://www.mynba.tv/video/?page=' + str(self.page)
            print('切换页面至:', page_url)
            yield scrapy.Request(url=page_url,callback=self.parse)

    # 解析详情页数据
    def parse_detail_info(self, response):
        # 匹配数据
        game_title = response.xpath('//*[@id="app"]/div/div[4]/div/div[2]/p[1]/text()').extract_first()
        name_1 = response.xpath('//*[@id="app"]/div/div[4]/div/div[1]/p/a/text()').extract_first()
        logo_src_1 = response.xpath('//*[@id="app"]/div/div[4]/div/div[1]/img/@src').extract_first()
        name_2 = response.xpath('//*[@id="app"]/div/div[4]/div/div[3]/a/text()').extract_first()
        logo_src_2 = response.xpath('//*[@id="app"]/div/div[4]/div/div[3]/img/@src').extract_first()
        # 推送给管道
        yield Ftb2Item(game_title=game_title, name_1=name_1, logo_src_1=logo_src_1, name_2=name_2,
                        logo_src_2=logo_src_2)

③ piplines.py

import xlwt


class Ftb2Pipeline:
    def open_spider(self, spider):
        self.workbook = xlwt.Workbook()
        self.worksheet = self.workbook.add_sheet('sheet1')
        self.line_cnt = 0
        self.col_name = ['game_title', 'name_1', 'logo_src_1', 'name_2', 'logo_src_2']
        # 写入表头
        for i in range(4):
            self.worksheet.write(self.line_cnt, i, self.col_name[i])
        self.line_cnt += 1

    def process_item(self, item, spider):
        try:
            # 写入数据
            for i in range(4):
                self.worksheet.write(self.line_cnt, i, item[self.col_name[i]])
            self.line_cnt += 1
            self.workbook.save('football_data.xls')

            return item  # 必须加,否则其他管道就无法获得item了！
        except Exception as e:
            print('写入失败！有残缺数据！已自动跳过！')



import urllib.request  # 用于下载图片
class Ftb2Pipeline_2:
    def process_item(self, item, spider):
        try:
            img_src_1 = item['logo_src_1']
            img_src_2 = item['logo_src_2']
            name_1 = img_src_1.split('/')[-1]
            name_2 = img_src_2.split('/')[-1]
            urllib.request.urlretrieve(img_src_1,filename=f'img/{
      
      name_1}')  # 此方法对于此页面请求下载不太稳定
            urllib.request.urlretrieve(img_src_2,filename=f'img/{
      
      name_2}')
            print('over!!')
            return item
        except Exception as e:
            print(e)
            print('下载失败！队徽或队名内容不存在！已自动跳过！')

④ settings.py

BOT_NAME = 'ftb_2'

SPIDER_MODULES = ['ftb_2.spiders']
NEWSPIDER_MODULE = 'ftb_2.spiders'

ROBOTSTXT_OBEY = False

DOWNLOAD_DELAY = 3
RANDOMIZE_DOWNLOAD_DELAY = True

ITEM_PIPELINES = {
    
    
   'ftb_2.pipelines.Ftb2Pipeline': 300,
   'ftb_2.pipelines.Ftb2Pipeline_2': 300,
}

⑤ start.py (启动文件)

from scrapy import cmdline
cmdline.execute('scrapy crawl ftb'.split(' '))

Scrapy 基础链接: Python爬虫|Scrapy 基础用法