fix

Comics/exporters.py

@@ -1,5 +1,4 @@
 import os.path,json,ast
-
 from Comics.settings import COMIC_INFO_FIELDS_TO_EXPORT
 from scrapy.exporters import XmlItemExporter
 from scrapy.exporters import PythonItemExporter
@@ -11,6 +10,16 @@ from Comics.utils.Constant import ComicPath
 from scrapy.utils.python import is_listlike, to_bytes, to_unicode
 from itemadapter import ItemAdapter
 
+class ItemImport():
+    def import_obj(self, file):
+        if os.path.exists(file):
+            with open(file, "r", encoding="utf-8") as fs:
+                result = fs.read() 
+                fs.close()
+                return result
+        else:
+            return []
+    
 class CommonExporter():
     def getPath(self, file , sufix=None):
         sufix = "."+sufix

Comics/items.py

@@ -9,20 +9,14 @@ from Comics.utils.FileUtils import imageUtils
 from itemloaders.processors import TakeFirst, MapCompose, Join
 from scrapy.spiders import Spider
 
-def current_project():
-    return Spider.name
+def current_project(): return Spider.name
     
-def serialize_to_chinese(value):
-    return ComicPath.chinese_convert(value)
+def serialize_to_chinese(value): return ComicPath.chinese_convert(value)
 
-def serialize_to_fix_file(value):
-    file = ComicPath.chinese_convert(value)
-    return ComicPath.fix_file_name(file)
+def serialize_to_fix_file(value): return ComicPath.fix_file_name(ComicPath.chinese_convert(value))
 
 def _serialize_to_images(value, result_type=None):
-    count = 1
-    images_item = []
-    image_urls = []
+    (count, images_item, image_urls) = [1,[],[]]
     for image in value:
         try:
             (image_src, scramble) = [image.get("src"), image.get("scramble")]
@@ -52,12 +46,6 @@ def serialize_to_images(value): return _serialize_to_images(value)
 
 def serialize_to_image_urls(value): return _serialize_to_images(value, result_type="image_urls") 
 
-
-class ListComicItem(Item):
-    name = Field()
-    link = Field()
-    
-
 class ComicItem(Item):
     # 工程
     current_project = Field()
@@ -103,8 +91,7 @@ class ImagesItem(Item):
     comic = Field()
 
 def serializer_info_writer(value):
-    list_value = []
-    value = str(value).replace("&", " ")
+    (list_value, value) = [[], str(value).replace("&", " ")]
     for v in set(str(value).split(" ")):
         list_value.append(v)
     return ",".join(list_value)
@@ -139,11 +126,9 @@ def serializer_info_images(value): return _serialize_info_images(value)
 
 def serializer_info_images_count(value): return _serialize_info_images(value, "count")
 
-def serializer_info_images_completed(value):
-    return _serialize_info_images(value, result_type='name')
+def serializer_info_images_completed(value): return _serialize_info_images(value, result_type='name')
 
-def serializer_info_images_count(value):
-    return _serialize_info_images(value, result_type='len')
+def serializer_info_images_count(value): return _serialize_info_images(value, result_type='len')
     
 
 class ComicInfoItem(Item):

Comics/pipelines.py

@@ -11,10 +11,11 @@ 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,ItemExporter
+from Comics.exporters import ComicInfoXmlItemExporter,JsonExport,ItemExporter, ItemImport
 from Comics.utils.FileUtils import CBZUtils
 from Comics.utils.FileUtils import fileUtils as fu 
 from Comics.loader import ComicEntity
+from Comics.utils.ComicUtils import checkUtils
 
 class ComicsPipeline:
     def open_spider(self, spider):
@@ -22,6 +23,9 @@ class ComicsPipeline:
 
     # item就是yield后面的对象
     def process_item(self, item, spider):
+        
+        checkUtils().export_error(item)
+        
         if isinstance(item, ComicItem):
             # 'output/rm_comic/json/壞X/第1話 壞X'
             if os.path.exists(ComicPath.CBZ(item=item)):
@@ -112,7 +116,9 @@ class ImgDownloadPipeline(ImagesPipeline):
                                      comic_info_images= comic_info['Pages'], remove=True):
                 self.update_icon(item)
                 self.pack_icon(item)
-        
+            # CBZ校验失败
+            else:
+                checkUtils().export_error(item)
             #sleep_time = random.randint(3,15)
             #print(f'等待{sleep_time}秒后进行下一章节')
             #time.sleep(int(sleep_time))

Comics/spiders/rm_comic.py

@@ -1,10 +1,8 @@
 import scrapy,logging,time,os
 from Comics.items import ComicItem
 from Comics.loader import ComicLoader
-from Comics.items import ListComicItem
 from Comics.utils.Constant import ComicPath
-from Comics.settings import PROJECT_KEY
-import skip
+from Comics.utils.ComicUtils import checkUtils
 
 class RmComicSpider(scrapy.Spider):
     name = 'rm_comic'
@@ -47,11 +45,12 @@ class RmComicSpider(scrapy.Spider):
             comic_item.chapter(value=chapter)
             item = comic_item.load_item()
             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...")
-                yield item
-            else:
-                yield scrapy.Request(self.main_url+link, meta={'item': item}, callback=self.parse_chapter)
+            if not checkUtils().is_error(item):
+                if os.path.exists(cbz_path):
+                    logging.info(f"漫画 {cbz_path} 已存在, 跳过中...")
+                    yield item
+                else:
+                    yield scrapy.Request(self.main_url+link, meta={'item': item}, callback=self.parse_chapter)
 
 
     # 读取某章节下的所有图片

Comics/spiders/yh_comic.py

@@ -1,7 +1,6 @@
 import scrapy,logging,time,os
 from Comics.items import ComicItem
 from Comics.loader import ComicLoader
-from Comics.items import ListComicItem
 from Comics.utils.Constant import ComicPath
 from Comics.settings import PROJECT_KEY
 import skip

Comics/utils/ComicUtils.py

@@ -0,0 +1,32 @@
+import os,json
+from Comics.settings import CBZ_EXPORT_PATH,OUTPUT_DIR,PROJECT_KEY
+from Comics.utils.Constant import ComicPath
+from Comics.exporters import ComicInfoXmlItemExporter,JsonExport,ItemExporter, ItemImport
+from Comics.utils.FileUtils import fileUtils as fu 
+from Comics.loader import ComicEntity
+
+class checkUtils:
+    # 
+    # 检测某一章节是否连续错误
+    def export_error(self, item):
+        file = os.path.join(OUTPUT_DIR, item[PROJECT_KEY][0], "error_comics.json")
+        error_comic = ItemImport().import_obj(file)
+        error_comic.append({ "name" : item['name'], "chapter" : item['chapter'], "date" : ComicPath().getYearMonthDay()})
+        fu.save_file(file, json.dumps(error_comic))
+        
+    def is_error(self, item):
+        file = os.path.join(OUTPUT_DIR, item[PROJECT_KEY][0], "error_comics.json")
+        error_comic = ItemImport().import_obj(file)
+        try:
+            for error_c in eval(error_comic):
+                (name, chatper, date) = [error_c['name'], error_c['chapter'], error_c['date']]
+                if item['name'] == name and item['chapter'] == chatper:
+                    return True
+                else:
+                    return False
+        except:
+            return False
+
+        
+
+        

Comics/utils/Constant.py

@@ -1,9 +1,16 @@
 import os.path,logging
 import re,requests,time
+from datetime import date
 from Comics import settings
 from opencc import OpenCC
 class ComicPath:
     PREFIX_SCRAMBLE = "scramble="
+    
+    @classmethod
+    def getYearMonthDay(cls):
+        today = date.today()
+        # 格式化为年-月-日
+        return today.strftime("%Y%m%d")
 
     @classmethod
     def getDirComicChapter(cls):

Comics/utils/FileUtils.py

@@ -10,9 +10,9 @@ from Comics.utils.Constant import ntfy
 class fileUtils:
     @classmethod
     def save_file(cls,path,data):
-        dir = os.path.dirname(path)
-        if not os.path.exists(dir):
-            os.makedirs(dir)
+        root_dir = os.path.dirname(path)
+        if not os.path.exists(root_dir):
+            os.makedirs(root_dir)
         with open(path,'w',encoding='utf-8') as fs:
             fs.write(str(data))
             fs.close()