fix

Comics/spiders/rm_comic.py

@@ -4,6 +4,7 @@ from Comics.loader import ComicLoader
 from Comics.items import ListComicItem
 from Comics.utils.Constant import ComicPath
 from Comics.settings import PROJECT_KEY
+import skip
 
 class RmComicSpider(scrapy.Spider):
     name = 'rm_comic'
@@ -14,15 +15,14 @@ class RmComicSpider(scrapy.Spider):
     def start_requests(self):
         yield scrapy.Request(self.start_urls, callback=self.books_comic)
 
+    # 获取多个漫画信息 
     def books_comic(self, response):
-        #books_comic = ComicLoader(item=ListComicItem(), response=response)
-        books_comic = ComicLoader(item=ComicItem(), response=response)
-        data = books_comic.get_xpath('//script[@id="__NEXT_DATA__"]/text()')[0]
-        str_exec = "props.pageProps.books"
-        books = books_comic.get_exec(data, str_exec=str_exec)
-        for book in  books:
-            books_comic.add_value('link', self.start_urls+"/"+book['id'])
-            yield scrapy.Request(url=self.start_urls+"/"+book['id'], callback=self.parse_comic)
+        comics = ComicLoader(item=ComicItem(), response=response)
+        data = comics.get_xpath('//script[@id="__NEXT_DATA__"]/text()')[0]
+        for book in comics.get_exec(data, str_exec="props.pageProps.books"):
+            comics.add_value('link', self.start_urls+"/"+book['id'])
+            if not book['name'] in skip.skip_comic:
+                yield scrapy.Request(url=self.start_urls+"/"+book['id'], callback=self.parse_comic)
 
     # 获取某个漫画的相关数据
     # 获取到多个章节链接后进入下个流程

skip.py

@@ -0,0 +1,3 @@
+skip_comic=[
+    "千絲萬縷的遊戲人生"
+]