zhiyu_content_spider/content_spider/spiders/judian/judian.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
from content_spider.Util import md5
import time
import json


name = 'judian'
allowed_domains = ['www.judianbook.com']
source = 'zy_judian'
source_name = 'judian据点'
source_id = 30
base_url = 'http://www.judianbook.com/index/api/{}?token=d5957e72f7711fd001ea29ddf0cff977e58c6342'


category = [{'type': 9, 'name': '武侠', 'channel_id': 1, 'category_name': '武侠仙侠', 'category_id': 21},
 {'type': 10, 'name': '仙侠', 'channel_id': 1, 'category_name': '武侠仙侠', 'category_id': 21},
 {'type': 11, 'name': '都市', 'channel_id': 1, 'category_name': '都市爱情', 'category_id': 54},
 {'type': 13, 'name': '历史', 'channel_id': 1, 'category_name': '特种军旅', 'category_id': 51},
 {'type': 14, 'name': '游戏', 'channel_id': 1, 'category_name': '游戏竞技', 'category_id': 19},
 {'type': 21, 'name': '玄幻', 'channel_id': 1, 'category_name': '玄幻奇幻', 'category_id': 23},
 {'type': 38, 'name': '科幻', 'channel_id': 1, 'category_name': '玄幻奇幻', 'category_id': 23},
 {'type': 44, 'name': '同人', 'channel_id': 1, 'category_name': '衍生同人', 'category_id': 125},
 {'type': 49, 'name': '短篇男', 'channel_id': 1, 'category_name': '其他作品', 'category_id': 127},
 {'type': 2, 'name': '古代言情', 'channel_id': 2, 'category_name': '穿越重生', 'category_id': 83},
 {'type': 3, 'name': '现代言情', 'channel_id': 2, 'category_name': '婚恋情感', 'category_id': 98},
 {'type': 4, 'name': '校 园言情', 'channel_id': 2, 'category_name': '青春校园', 'category_id': 104},
 {'type': 5, 'name': '幻想言情', 'channel_id': 2, 'category_name': '东方玄幻', 'category_id': 96},
 {'type': 22, 'name': '穿越重生', 'channel_id': 2, 'category_name': '穿越重生', 'category_id': 83},
 {'type': 45, 'name': '耽美', 'channel_id': 2, 'category_name': '耽美同人', 'category_id': 106},
 {'type': 46, 'name': '百合', 'channel_id': 2, 'category_name': '其他', 'category_id': 107},
 {'type': 47, 'name': '无cp', 'channel_id': 2, 'category_name': '其他', 'category_id': 107},
 {'type': 48, 'name': '短篇', 'channel_id': 2, 'category_name': '其他', 'category_id': 107},
 {'type': 20, 'name': '推理悬念', 'channel_id': 1, 'category_name': '灵异恐 怖', 'category_id': 81},
 {'type': 40, 'name': '恐怖惊悚', 'channel_id': 1, 'category_name': '灵异恐怖', 'category_id': 81},
 {'type': 41, 'name': '灵异鬼怪', 'channel_id': 1, 'category_name': '灵异恐怖', 'category_id': 81},
 {'type': 42, 'name': '风水秘术', 'channel_id': 1, 'category_name': '灵异恐怖', 'category_id': 81},
 {'type': 43, 'name': '探险异闻', 'channel_id': 1, 'category_name': '灵异恐怖', 'category_id': 81},
 {'type': 24, 'name': '励志', 'channel_id': 2, 'category_name': '其他', 'category_id': 107},
 {'type': 25, 'name': '职场', 'channel_id': 2, 'category_name': '其他', 'category_id': 107},
 {'type': 26, 'name': '生活', 'channel_id': 2, 'category_name': '其他', 'category_id': 107},
 {'type': 28, 'name': ' 婚姻', 'channel_id': 2, 'category_name': '其他', 'category_id': 107},
 {'type': 29, 'name': '教育', 'channel_id': 2, 'category_name': '其他', 'category_id': 107},
 {'type': 35, 'name': '心理学', 'channel_id': 2, 'category_name': '其他', 'category_id': 107},
 {'type': 36, 'name': '管理', 'channel_id': 2, 'category_name': '其他', 'category_id': 107}]

  

def get_category(type):
    for item in category:
        if int(type) == item['type']:
            return item
    return category[0]


class judianProcess(object):
    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') + '&site=500'

    def bid_list_result(self, response):
        result = json.loads(response.text)
        if result is None or result.get('data') is None:
            return []
        result_list = []
        for item in result['data']:
            result_list.append({'id': item['bookid']})
        return result_list

    def get_book_info_url(self, bid):
        return base_url.format('BookInfo') + '&book_id={}'.format(bid)

    def book_info_result(self, response):
        result = json.loads(response.text)
        result = result['data']
        category_info = get_category(result['type']);
        return {
            'bid': result['book_id'], 'name': result['book_name'], 'author': result['author'],
            'intro': result['describe'], 'cover': result['cover'], 'keyword': result['tag'],
            'status':result['state'], '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('BookChapters') + '&book_id={}&size=3000'.format(bid)

    def chapter_list_result(self, response):
        result = json.loads(response.text)
        if result is None or result.get('data') is None:
            return []

        result_list = []
        i = 0
        for chapter_item in result['data']:
            i = i+1
            result_list.append({
                'source_chapter_id': chapter_item['chapnum'], 'name': chapter_item['name'],
                'sequence': chapter_item['chapnum'], 'is_vip':chapter_item['is_pay'],
                'size': chapter_item['word_count'], 'recent_update_at': ''
            })
        return result_list

    def get_chapter_content_url(self, bid, cid):
        return base_url.format('BookChapterInfo') + '&book_id={}&chapnum={}&type=json'.format(bid, cid)

    def chapter_content_result(self, response):
        result = json.loads(response.text)
        if result is None:
            return {'content': ''}

        return {
            'content': "\r\n".join(result['content'])
        }

    
class judianSpider(judianProcess,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 judianUpdateSpider(judianProcess,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 judianFixSpider(judianProcess,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 judianBookInfoSpider(judianProcess,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'
    }