From e4ac2cc6310a8156148bf357b9c69d0e02749bb2 Mon Sep 17 00:00:00 2001
From: caiwx86 <caiwenxiu0806@163.com>
Date: Wed, 6 Sep 2023 02:50:16 +0800
Subject: [PATCH] fix

---
 Comics/pipelines.py        | 32 +++++++++++++++++++++-----------
 Comics/spiders/rm_comic.py |  2 +-
 2 files changed, 22 insertions(+), 12 deletions(-)

diff --git a/Comics/pipelines.py b/Comics/pipelines.py
index 3e8f8ee..9fd8845 100644
--- a/Comics/pipelines.py
+++ b/Comics/pipelines.py
@@ -11,7 +11,7 @@ from Comics.settings import CBZ_EXPORT_PATH,OUTPUT_DIR,PROJECT_KEY
 from Comics.utils.Constant import ComicPath
 from Comics.items import ComicItem
 from scrapy.pipelines.images import ImagesPipeline
-from Comics.exporters import ComicInfoXmlItemExporter,JsonExport
+from Comics.exporters import ComicInfoXmlItemExporter,JsonExport,ItemExporter
 from Comics.utils.FileUtils import CBZUtils
 from Comics.utils.FileUtils import fileUtils as fu 
 
@@ -24,12 +24,17 @@ class ComicsPipeline:
     def process_item(self, item, spider):
         if isinstance(item, ComicItem):
             # 'output/rm_comic/json/壞X/第1話 壞X'
-            file = os.path.join(OUTPUT_DIR, spider.name, "json", item['name'], item['chapter'])
-            item['count'] = len(item['images'])
-            item['index'] = item['chapters'].index(item['chapter']) + 1
+            cbz_path = ComicPath.get_file_path(item, result_type="cbz", convert=True)
+            if os.path.exists(cbz_path):
+                item['image_urls'] = []
+                item['images'] = []
+                return ItemExporter().export_obj(item)
+            else:
+                file = os.path.join(OUTPUT_DIR, spider.name, "json", item['name'], item['chapter'])
+                item['count'] = len(item['images'])
+                item['index'] = item['chapters'].index(item['chapter']) + 1
 
-            data = JsonExport(file=file).export_json(item, if_return=True)
-        return data 
+                return JsonExport(file=file).export_json(item, if_return=True)
         # image解析
 
     def close_spider(self, spider):
@@ -99,14 +104,19 @@ class ImgDownloadPipeline(ImagesPipeline):
 
     def item_completed(self, results, item, info):
         # return item
-        # ComicInfoXml 生成
-        comic_info = ComicInfoXmlItemExporter(dir=self.get_file_path(item=item, result_type="comic_info")).export_xml(item)
         # 打包
-        if CBZUtils.packComicChapterCBZ(src_dir= self.get_file_path(item, result_type="images_dir"),
-                                        dts_path= self.get_file_path(item, result_type="cbz"),
-                                     comic_info_images= comic_info['Pages'], remove=True):
+        cbz_path = self.get_file_path(item, result_type="cbz")
+        if os.path.exists(cbz_path):
             self.update_icon(item)
             self.pack_icon(item)
+        else:
+            # ComicInfoXml 生成
+            comic_info = ComicInfoXmlItemExporter(dir=self.get_file_path(item=item, result_type="comic_info")).export_xml(item)
+            if CBZUtils.packComicChapterCBZ(src_dir= self.get_file_path(item, result_type="images_dir"),
+                                        dts_path= cbz_path,
+                                     comic_info_images= comic_info['Pages'], remove=True):
+                self.update_icon(item)
+                self.pack_icon(item)
         
 #        sleep_time = random.randint(5,30)
 #        print(f'等待{sleep_time}秒后进行下一章节')
diff --git a/Comics/spiders/rm_comic.py b/Comics/spiders/rm_comic.py
index 370ba8b..bfb4451 100644
--- a/Comics/spiders/rm_comic.py
+++ b/Comics/spiders/rm_comic.py
@@ -49,7 +49,7 @@ class RmComicSpider(scrapy.Spider):
             cbz_path = ComicPath.get_file_path(item=item, result_type="cbz", convert=True)
             if os.path.exists(cbz_path):
                 logging.info(f"漫画 {cbz_path} 已存在, 跳过中...")
-                return
+                yield item
             else:
                 yield scrapy.Request(self.main_url+link, meta={'item': item}, callback=self.parse_chapter)