clear

Comics/_utils/ComicInfo.py

@@ -1,9 +1,9 @@
 import xml.etree.ElementTree as ET
 from xml.dom import minidom
 from typing import List
-import json,os
+import os
 from lxml import etree
-from Comics.settings import COMIC_INFO_XML_FILE,COMIC_INFO_XSD_FILE,OUTPUT_DIR,PROJECT_KEY
+from Comics.settings import COMIC_INFO_XSD_FILE
 
 # Define the ComicInfo and ComicPageInfo classes
 class ComicInfo:

Comics/items.py

@@ -104,58 +104,3 @@ class BooksItem(Item):
     current_project = Field()
     names = Field()
     urls = Field()
-
-class ImageItem(Item):
-    image_url  = Field()
-    image_name = Field()
-    image_path = Field()
-    image_type = Field()
-    isScramble = Field()
-
-class Image():
-    def setImage(self, url, scramble): return { "src" : url, "scramble": scramble}
-        
-# 序列化-作者
-def serializer_info_writer(value):
-    (list_value, value) = [[], str(value).replace("&", " ")]
-    for v in set(str(value).split(" ")):
-        list_value.append(v)
-    return ",".join(list_value)
-
-# (私有)序列化-图像
-def _serialize_info_images(value, result_type=None):
-    images = []
-    for image in value:
-        if os.sep not in image:
-            images.append(ComicPath().getFileScrambleImageSave(image,True,False))
-    if result_type == "count":
-        return len(images)
-    else:
-        return images
-    
-# 序列化-图像    
-def serializer_info_images(value): return _serialize_info_images(value)
-
-# 序列化-合计
-def serializer_info_images_count(value): return _serialize_info_images(value, "count")
-
-class ComicInfoItem(Item):
-    Title       = Field(desc="章节名", info='chapter')
-    Series      = Field(desc="漫画名", info='name')
-    Number      = Field(desc="编号", info='index')
-    SeriesGroup = Field(desc="别名")
-    Summary     = Field(desc="概述", info='dep')
-    Year        = Field(desc="年")
-    Month       = Field(desc="月")
-    Day         = Field(desc="日")
-    Writer      = Field(desc="作者", info='author',serializer=serializer_info_writer)
-    Publisher   = Field(desc="出版社")
-    Genre       = Field(desc="流派", info='genre')
-    Tags        = Field(desc="标签", info='tags')
-    Web         = Field(desc="主页")
-    PageCount   = Field(desc="总页数", info='count')
-    LanguageISO = Field(desc="语言")
-    AgeRating   = Field(desc="年龄分级", info='age_rating')
-    Pages       = Field(desc="页码", info='images', serializer=serializer_info_images)
-    # ComicInfo.xml and ComicChapter.json end
-    

Comics/loader.py

@@ -183,6 +183,8 @@ class ComicLoader(BaseLoader):
         self.save_sname_schapter()
         return super().load_item()
     
+    def setImageItem(self, url, scramble): return { "src" : url, "scramble": scramble}
+         
     def set_image_item(self, image_url, image_path, image_name, image_scramble="False", image_type="Image"):
         return { "image_url" : image_url, "image_path" : image_path, "image_name" : image_name, "image_scramble" : image_scramble , "image_type" : image_type}
         

Comics/pipelines.py

@@ -7,7 +7,7 @@
 # useful for handling different item types with a single interface
 import os,scrapy,logging,shutil
 from Comics import settings
-from Comics.items import ComicItem,ImageItem
+from Comics.items import ComicItem
 from Comics.loader import ComicLoader
 from Comics.utils import CBZUtils,fileUtils as fu
 from Comics.utils import ComicPath

Comics/spiders/rm_comic.py

@@ -1,5 +1,5 @@
-import scrapy,logging,os,skip,json,re
+import scrapy,logging,os,skip,re
-from Comics.items import ComicItem,Image
+from Comics.items import ComicItem
 from Comics.items import BooksItem
 from Comics.loader import ComicLoader
 from Comics.loader import BooksLoader
@@ -72,7 +72,7 @@ class RmComicSpider(scrapy.Spider):
                 sr = sr_value.group(1) # group(1) 返回第一个捕获组，即数字部分
             else:
                 print("No match found")
-            images_urls.append(Image().setImage(url=link, scramble=sr.replace("0", "False").replace("1", "True")))
+            images_urls.append(ci.setImageItem(url=link, scramble=sr.replace("0", "False").replace("1", "True")))
         ci.image_urls(value=images_urls)
         yield ci.load_item()