南京落尘

README.md

@@ -88,4 +88,11 @@
     采集命令: scrapy crawl xiwen
     更新命令: scrapy crawl xiwenupdate
     更新完结状态: scrapy crawl xiwenbookinfo
-    覆盖命令： scrapy crawl xiwenfix -a bid=bid1,bid2
+    覆盖命令： scrapy crawl xiwenfix -a bid=bid1,bid2
+
+## 南京落尘:
+文件目录: content_spider/spiders/nanjingluochen
+    采集命令: scrapy crawl nanjingluochen
+    更新命令: scrapy crawl nanjingluochenupdate
+    更新完结状态: scrapy crawl nanjingluochenbookinfo
+    覆盖命令： scrapy crawl nanjingluochenfix -a bid=bid1,bid2

content_spider/spiders/nanjingluochen/nanjingluochen.py

@@ -0,0 +1,163 @@
+# -*- coding: utf-8 -*-
+
+from content_spider.baseSpider import baseSpider
+from content_spider.baseSpider import baseUpdateSpider
+from content_spider.baseSpider import fixChapterSpider
+from content_spider.baseSpider import baseUpdateBookStatusSpider
+import time
+import json
+
+
+name = 'nanjingluochen'
+allowed_domains = ['cp.api.luochen.com']
+source = 'zy_nanjingluochen'
+source_name = '南京落尘'
+source_id = 46
+base_url = 'http://cp.api.luochen.com/interface/Zhuishuyun/{}'
+
+
+
+
+
+def get_category(channel,sort_name):
+
+    if int(channel) == 0:
+        if sort_name in ['玄幻','修真','仙侠','武侠','科幻']:
+            return {'channel_id':1,'category_id':'武侠仙侠','category_id':21}
+        if sort_name in ['都市','职场','豪门','总裁','青春','纯爱','乡土']:
+            return {'channel_id':1,'category_id':'都市爱情','category_id':54}
+        if sort_name in ['架空','穿越','历史','军事']:
+            return {'channel_id':1,'category_id':'历史穿越','category_id':14}
+        if sort_name in ['宫斗','宅斗','同人','短篇']:
+            return {'channel_id':1,'category_id':'其他','category_id':127}
+        if sort_name == '游戏':
+            return {'channel_id':1,'category_id':'游戏竞技','category_id':19}
+        if sort_name == '灵异' or sort_name == '悬疑':
+            return {'channel_id':1,'category_id':'灵异恐怖','category_id':81}    
+           
+        return {'channel_id':1,'category_id':'都市爱情','category_id':54}
+    else:
+        if sort_name in ['婚恋','职场','豪门','总裁']:
+            return {'channel_id':2,'category_id':'婚恋情感','category_id':98}
+        
+        if sort_name in ['架空','穿越']:
+            return {'channel_id':2,'category_id':'穿越重生','category_id':83}
+        
+        if sort_name in ['宫斗','宅斗']:
+            return {'channel_id':2,'category_id':'宫斗宅斗','category_id':120}
+        
+        if sort_name in ['仙侠','修真','玄幻','武侠']:
+            return {'channel_id':2,'category_id':'东方玄幻','category_id':96}
+        
+        if sort_name in ['灵异','悬疑']:
+            return {'channel_id':2,'category_id':'悬疑探险','category_id':113}
+        
+        if sort_name in ['青春','乡土','纯爱']:
+            return {'channel_id':2,'category_id':'青春纯爱','category_id':103}
+        
+        if sort_name in ['历史','同人','短篇']:
+            return {'channel_id':2,'category_id':'其他','category_id':107}
+        
+        return {'channel_id':2,'category_id':'婚恋情感','category_id':98}
+
+
+class nanjingluochenProcess():
+    name = name
+    allowed_domains = allowed_domains
+    source = source
+    source_name = source_name
+    source_id = source_id
+
+
+    def get_start_url(self):
+        return base_url.format('booklist')
+
+    def bid_list_result(self, response):
+        result = json.loads(response.text)
+        if result is None or result.get('books') is None:
+            return []
+        result_list = []
+        for item in result['books']:
+            result_list.append({'id': item['bid']})
+        return result_list
+
+    def get_book_info_url(self, bid):
+        return base_url.format('bookInfo/') + '?bid={}'.format(bid)
+
+    def book_info_result(self, response):
+        result = json.loads(response.text)
+        category_info = get_category(result['channel'],result['category']);
+        return {
+            'bid': result['id'], 'name': result['title'], 'author': result['author'],
+            'intro': result['summary'], 'cover': result['cover'], 'keyword': result['tag'],
+            'status':  result['isFull'], 'category': category_info['category_name'],'category_id':category_info['category_id'],
+            'channel': category_info['channel_id']
+        }
+
+    def get_chapter_list_url(self, bid):
+        return base_url.format('chapterList/') + '?bid={}'.format(bid)
+
+    def chapter_list_result(self, response):
+        result = json.loads(response.text)
+        if result is None or result.get('chapters') is None:
+            return []
+
+        result_list = []
+        i = 0
+        for chapter_item in result['chapters']:
+            i = i+1
+            result_list.append({
+                'source_chapter_id': chapter_item['id'], 'name': chapter_item['title'],
+                'sequence': chapter_item['chapterOrder'], 'is_vip': chapter_item['isVip'],
+                'size': chapter_item['chapterLength'], 'recent_update_at': chapter_item['updatetime']
+            })
+        return result_list
+
+    def get_chapter_content_url(self, bid, cid):
+        return base_url.format('chapterContent/') + '?bid={}&cid={}'.format(bid, cid)
+
+    def chapter_content_result(self, response):
+        result = json.loads(response.text)
+        if result is None:
+            return {'content': ''}
+
+        return {
+            'content': result['content']
+        }
+
+    
+class nanjingluochenSpider(nanjingluochenProcess,baseSpider):
+    name = name
+    custom_settings = {
+        'DOWNLOAD_DELAY': 0.1,
+        'SOURCE': source,
+        'LOG_FILE': 'content_spider/log/' + name + time.strftime("%Y-%m-%d", time.localtime()) + '.log'
+    }
+
+
+class nanjingluochenUpdateSpider(nanjingluochenProcess,baseUpdateSpider):
+    name = name + "update"
+    custom_settings = {
+        'DOWNLOAD_DELAY': 0.1,
+        'SOURCE': source,
+        'LOG_FILE': 'content_spider/log/' + name + time.strftime("%Y-%m-%d", time.localtime()) + '.log'
+    }
+
+
+    
+class nanjingluochenFixSpider(nanjingluochenProcess,fixChapterSpider):
+    name = name + 'fix'
+    custom_settings = {
+        'DOWNLOAD_DELAY': 0.1,
+        'SOURCE': source,
+        'LOG_FILE': 'content_spider/log/' + name + time.strftime("%Y-%m-%d", time.localtime()) + '.log'
+    }
+
+
+class xingheyueduBookInfoSpider(xingheyueduProcess,baseUpdateBookStatusSpider):
+    name = name + "bookinfo"
+    custom_settings = {
+        'DOWNLOAD_DELAY': 0.1,
+        'SOURCE': source,
+        'LOG_FILE': 'content_spider/log/' + name + time.strftime("%Y-%m-%d", time.localtime()) + '.log'
+    }