diff --git a/Comics/settings.py b/Comics/settings.py index e8a0ac0..079e815 100644 --- a/Comics/settings.py +++ b/Comics/settings.py @@ -45,7 +45,7 @@ RETRY_HTTP_CODES = [408, 401] CONCURRENT_REQUESTS_PER_DOMAIN = 16 CONCURRENT_REQUESTS_PER_IP = 16 PROXY_LIST = [ - "http://127.0.0.1:7890", +# "http://127.0.0.1:7890", # "http://10.0.10.117:8123", ] # Disable cookies (enabled by default) diff --git a/Comics/spiders/rm_comic.py b/Comics/spiders/rm_comic.py index f6662aa..f2ea203 100644 --- a/Comics/spiders/rm_comic.py +++ b/Comics/spiders/rm_comic.py @@ -11,7 +11,7 @@ class RmComicSpider(scrapy.Spider): main_url = 'https://'+allowed_domains[0] start_urls = main_url+'/books' - # 遍历网站页数 + # 遍历网站页数数据 def start_requests(self): for x in range(0,60): yield scrapy.Request(self.start_urls+"?&page="+str(x), callback=self.books_comic) @@ -30,8 +30,7 @@ class RmComicSpider(scrapy.Spider): for chapter, link in zip(comic_item.get_chapters(), comic_item.get_chapter_href()): item = comic_item.load_item() cbz_path = ComicPath().get_file_path(item=item, result_type="cbz", convert=True, chapter=chapter) - #if not checkUtils().is_error(item) and os.path.exists(cbz_path): - if os.path.exists(cbz_path): + if not checkUtils().is_error(item) and os.path.exists(cbz_path): logging.info(f"漫画 {cbz_path} 已存在, 跳过中...") yield item else: