您好：
參考書本範例，並有修改一些小問題
pttbeauty.json是有擷取資料
但images內沒有圖檔
請問，是圖檔有權限，還是還有哪邊設定需要再處理(範本較舊)
謝謝

import scrapy
from Ch9_4a.items import BeautyItem
from datetime import datetime

class PptbeautySpider(scrapy.Spider):
    name = "pttbeauty"    
    allowed_domains = ["ptt.cc"]
    start_urls = ["https://www.ptt.cc/bbs/Beauty/index.html"]

    def __init__(self):
        self.max_pages = 2        # 最大頁數
        self.num_of_pages = 0       # 目前已爬取的頁數

    
    def parse(self, response):
        for href in response.css(".r-ent > div.title > a::attr(href)"):
            url = response.urljoin(href.extract())
            #print("-------------------url-AA--------------------------",url)      
            yield scrapy.Request(url, callback=self.parse_post)

        #print("-------------------parse---------------------------")            
        self.num_of_pages = self.num_of_pages + 1    
        #print("-------------------parse------self.num_of_pages---------------------", self.num_of_pages)            
        
        # 是否已經到達最大頁數
        if self.num_of_pages < self.max_pages:
            
            prev_page = response.xpath('//div[@id="action-bar-container"]//a[contains(text(), "上頁")]/@href')
            
            if prev_page:    # 是否有上一頁
              #  print("-------------------prev_page[0]---------------------------",prev_page[0])            
                url = response.urljoin(prev_page[0].extract())
              #  print("-------------------url---------------------------",url)      
                yield scrapy.Request(url, self.parse)
            else:
                
                print("已經是最後一頁, 總共頁數: ", self.num_of_pages)
        else:
            print("已經到達最大頁數: ", self.max_pages)


    def parse_post(self, response):
        
            #print("-------------------parse_post---------------------------")
            item = BeautyItem()
            
        
            #item["author"] = response.css(".article-metaline:nth-child(1) .article-meta-value::text").extract_first()    
            item["author"] = response.css(".article-metaline:nth-child(1) .article-meta-value::text").extract_first()    
            
            
            item["title"] = response.css(".article-metaline-right+ .article-metaline .article-meta-value::text").extract_first()
            #article-metaline-right+ 下一個
            print( item["author"],  item["title"])
        
            datetime_str = response.css(".article-metaline+ .article-metaline .article-meta-value::text").extract_first()
            item["date"] = datetime.strptime(datetime_str, '%a %b %d %H:%M:%S %Y')
    
            score = 0
            num_of_pushes = 0
            comments = response.xpath('//div[@class="push"]')
            for comment in comments:
                push = comment.css("span.push-tag::text")[0].extract()
                if "推" in push:
                    score = score + 1
                    num_of_pushes = num_of_pushes + 1
                elif "噓" in push:
                    score = score - 1
    
            item["score"] = score
            item["pushes"] = num_of_pushes
            item["comments"] = len(comments)
            item["url"] = response.url
            img_urls = response.xpath('//a[contains(@href, "imgur.com")]/@href').extract()
            if img_urls:
                img_urls = [url for url in img_urls if url.endswith(".jpg")]
                item["images"] = len(img_urls)
                item["file_urls"] = img_urls
            else:
                item["images"] = 0
                item["file_urls"] = []
    
            yield item           

items

import scrapy


class BeautyItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    author = scrapy.Field()
    date = scrapy.Field()
    score = scrapy.Field()
    pushes = scrapy.Field()
    comments = scrapy.Field()
    url = scrapy.Field()
    images = scrapy.Field()
    file_urls = scrapy.Field()

pipelines.py

from itemadapter import ItemAdapter


class Ch94APipeline:
    def process_item(self, item, spider):
        return item

settings.py

BOT_NAME = 'Ch9_4a'

SPIDER_MODULES = ['Ch9_4a.spiders']
NEWSPIDER_MODULE = 'Ch9_4a.spiders'

# 輸出 JSON 資料
#FEED_FORMAT = "json"
#FEED_URI = "pttbeauty.json"
#FEED_EXPORT_ENCODING = "utf-8"

FEEDS = {
    'pttbeauty.json': {
        'format': 'json',
        'encoding': 'utf8',
        'store_empty': False,
        'fields': None,
        'indent': 4,
    },
}


ITEM_PIPELINES = {
   'scrapy.pipelines.files.FilesPipeline': 1
}
FILES_STORE = 'images'

CONCURRENT_REQUESTS_PER_DOMAIN = 1
DOWNLOAD_DELAY = 5

pttbeauty.json
其中一段
{
"author": "tactics2100 (Ose)",
"title": "[正妹] 岡田さりお 開球",
"date": "2024-12-07 15:34:37",
"score": 46,
"pushes": 53,
"comments": 90,
"url": "https://www.ptt.cc/bbs/Beauty/M.1733556879.A.F3E.html",
"images": 2,
"file_urls": [
"http://i.imgur.com/SzEH8BS.jpg",
"http://i.imgur.com/KTiZOUy.jpg"
]
}

且在專案底下，也有自動產生images 資料夾
但就是沒有圖片

不知道是否真這些EXCEPTION有關

--- <exception caught here> ---
C:\ProgramData\anaconda3\Lib\site-packages\twisted\internet\defer.py:1075:_runCallbacks
C:\ProgramData\anaconda3\Lib\site-packages\scrapy\pipelines\files.py:459:media_failed
]
NoneType: None
2024-12-09 22:39:02 [scrapy.pipelines.media] ERROR: [Failure instance: Traceback: <class 'scrapy.pipelines.files.FileException'>:
C:\ProgramData\anaconda3\Lib\site-packages\twisted\internet\defer.py:533:addCallbacks
C:\ProgramData\anaconda3\Lib\site-packages\twisted\internet\defer.py:1075:_runCallbacks
C:\ProgramData\anaconda3\Lib\site-packages\scrapy\pipelines\media.py:197:_check_media_to_download
C:\ProgramData\anaconda3\Lib\site-packages\twisted\internet\defer.py:533:addCallbacks