zhiyu_content_spider/content_spider/spiders/nanjingluochen/nanjingluochen.py

# -*- 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_name':'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_name':'都市爱情','category_id':54}
        if sort_name in ['架空','穿越','历史','军事']:
            return {'channel_id':1,'category_name':'历史穿越','category_id':14}
        if sort_name in ['宫斗','宅斗','同人','短篇']:
            return {'channel_id':1,'category_name':'其他','category_id':127}
        if sort_name == '游戏':
            return {'channel_id':1,'category_name':'游戏竞技','category_id':19}
        if sort_name == '灵异' or sort_name == '悬疑':
            return {'channel_id':1,'category_name':'灵异恐怖','category_id':81}    
           
        return {'channel_id':1,'category_name':'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_name':'婚恋情感','category_id':98}
        
        if sort_name in ['架空','穿越']:
            return {'channel_id':2,'category_name':'穿越重生','category_id':83}
        
        if sort_name in ['宫斗','宅斗']:
            return {'channel_id':2,'category_name':'宫斗宅斗','category_id':120}
        
        if sort_name in ['仙侠','修真','玄幻','武侠']:
            return {'channel_id':2,'category_name':'东方玄幻','category_id':96}
        
        if sort_name in ['灵异','悬疑']:
            return {'channel_id':2,'category_name':'悬疑探险','category_id':113}
        
        if sort_name in ['青春','乡土','纯爱']:
            return {'channel_id':2,'category_name':'青春纯爱','category_id':103}
        
        if sort_name in ['历史','同人','短篇']:
            return {'channel_id':2,'category_name':'其他','category_id':107}
        
        return {'channel_id':2,'category_name':'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 nanjingluochenBookInfoSpider(nanjingluochenProcess,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'
    }