scraper2-hj3415 0.0.3__py3-none-any.whl → 0.1.0__py3-none-any.whl

scraper2_hj3415/nfscrapy/nfs/pipelines.py

@@ -1,26 +1,104 @@
 from itemadapter import ItemAdapter
 from pymongo import errors
+from pprint import pprint
+from util_hj3415 import mongo
 
+import logging
+logger = logging.getLogger(__name__)
+formatter = logging.Formatter('%(levelname)s: [%(name)s] %(message)s')
+ch = logging.StreamHandler()
+ch.setFormatter(formatter)
+logger.addHandler(ch)
+logger.setLevel(logging.DEBUG)
 
-class MongoPipeline:
 
-    collection_name = 'c101'
+class ValidationPipeline:
+    def process_item(self, item, spider):
+        print(f"\tIn the {self.__class__.__name__}...", end="")
+        if spider.name == 'c101':
+            print(f" Manual calculating EPS, BPS, PER, PBR")
+            logger.debug('*** Start c101 pipeline ***')
+            logger.debug(f"Raw data - EPS:{item['EPS']} BPS:{item['BPS']} PER:{item['PER']} PBR:{item['PBR']}")
+            # eps, bps, per, pbr을 직접 계산해서 바꾸기 위해 c104 page를 찾는다.
+            try:
+                logger.debug('Try to get c104 page for calculate values..')
+                c104 = mongo.C104(spider.mongo_client, item['코드'], 'c104q')
+                d, eps = c104.sum_recent_4q('EPS')  # 최근 4분기 eps값을 더한다.
+                d, bps = c104.latest_value('BPS')  # 마지막 분기 bps값을 찾는다.
 
-    def open_spider(self, spider):
-        self.client = spider.mongo_client
+                # per, pbr을 구하는 람다함수
+                cal_ratio = (lambda eps_bps, pprice:
+                             None if eps_bps is None or eps_bps == 0 else round(int(pprice) / int(eps_bps), 2))
+                cal_per = cal_ratio(eps, item['주가'])
+                cal_pbr = cal_ratio(bps, item['주가'])
+                logger.debug(f"After calc data - EPS:{eps} BPS:{bps} PER:{cal_per} PBR:{cal_pbr}")
+                logger.debug(f"*** End c101 calculation pipeline {item['코드']} ***")
+            except:
+                logger.warning("Error on calculating custom EPS, BPS, PER, PBR, maybe DB hasn't c104q collection.")
+                logger.warning(
+                    f"We will use default scraped values -  EPS:{item['EPS']} BPS:{item['BPS']} PER:{item['PER']} PBR:{item['PBR']}")
+                return item
+            item['EPS'], item['BPS'], item['PER'], item['PBR'] = eps, bps, cal_per, cal_pbr
+        if 'c103' in spider.name:
+            # pprint(item)
+            print(" Nothing special working")
+        if 'c104' in spider.name:
+            #pprint(item)
+            print(" Nothing special working")
+        if spider.name == 'c106':
+            pprint(item)
+            print(" Nothing special working")
+        return item
 
+
+class MongoPipeline:
     def process_item(self, item, spider):
-        print("In the MongoPipeline...", end="")
-        if self.client is None:
-            print("Skip the save to mongoDB.")
+        print(f"\tIn the {self.__class__.__name__}...", end="")
+        if spider.mongo_client is None:
+            print(f"Skipping to save the data... code : {item['코드']} / spider : {spider.name}")
         else:
-            print("Save data to mongoDB.")
-            my_collection = self.client[item['코드']][self.collection_name]
-            try:
-                my_collection.create_index('date', unique=True)
-                my_collection.insert_one(ItemAdapter(item).asdict())
-            except errors.DuplicateKeyError:
-                # 스크랩한 데이터가 이미 데이터베이스에 있을경우 지우고 저장
-                my_collection.delete_many({'date': {"$gte": item['date']}})
-                my_collection.insert_one(ItemAdapter(item).asdict())
+            print(f"Saving the {spider.name} to mongoDB...", end="")
+            if spider.name == 'c101':
+                page = spider.name
+                print(f" code : {item['코드']} / page : {page}")
+                c101_col = spider.mongo_client[item['코드']][page]
+                try:
+                    c101_col.create_index('date', unique=True)
+                    c101_col.insert_one(ItemAdapter(item).asdict())
+                except errors.DuplicateKeyError:
+                    # 스크랩한 데이터가 이미 데이터베이스에 있을경우 지우고 저장
+                    c101_col.delete_many({'date': {"$gte": item['date']}})
+                    c101_col.insert_one(ItemAdapter(item).asdict())
+            elif 'c103' in spider.name:
+                page = ''.join(['c103', item['title']])
+                print(f" code : {item['코드']} / page : {page}")
+                #logging.debug(item['df'].to_dict('records'))
+                #r = mongo2.C103(self.client, item['코드'], page).save(item['df'])
+            elif 'c104' in spider.name:
+                if item['title'].endswith('y'):
+                    page = 'c104y'
+                elif item['title'].endswith('q'):
+                    page = 'c104q'
+                else:
+                    raise ValueError
+                print(f" code : {item['코드']} / page : {page}({item['title']})")
+                logging.debug(item['df'].to_dict('records'))
+                r = mongo.C104(spider.mongo_client, item['코드'], page).save_df(item['df'])
+            elif spider.name == 'c106':
+                page = ''.join(['c106', item['title']])
+                print(f" code : {item['코드']} / page : {page}")
+                #logging.debug(item['df'].to_dict('records'))
+                #if page == 'c106y':
+                #    r = mongo2.C106Y(self.client, item['코드']).save(item['df'])
+                #elif page == 'c106q':
+                #    r = mongo2.C106Q(self.client, item['코드']).save(item['df'])
+                #else:
+                #    raise
+            """
+            elif spider.name == 'c108':
+                page = spider.name
+                print(f" code : {item['코드']} / page : {page}")
+                logging.debug(item['df'].to_dict('records'))
+                r = mongo2.C108(self.client, item['코드']).save(item['df'])
+            """
         return item

scraper2_hj3415/nfscrapy/nfs/settings.py

@@ -65,7 +65,8 @@ COOKIES_ENABLED = False
 # Configure item pipelines
 # See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
 ITEM_PIPELINES = {
-    "nfs.pipelines.MongoPipeline": 300,
+    "nfs.pipelines.ValidationPipeline": 300,
+    "nfs.pipelines.MongoPipeline": 400,
 }
 
 # Enable and configure the AutoThrottle extension (disabled by default)

scraper2_hj3415/nfscrapy/nfs/spiders/_c108.py

@@ -0,0 +1,95 @@
+import scrapy
+import pandas as pd
+
+from nfs import items
+from nfs.spiders import common
+
+
+class C108Spider(scrapy.Spider):
+    """
+    네이버에서 더 이상 제공하지 않는 서비스임. 비활성화시킴
+    """
+    name = 'c108'
+    allowed_domains = ['navercomp.wisereport.co.kr']    # https 주소
+
+    def __init__(self, code, mongo_client, *args, **kwargs):
+        super(C108Spider, self).__init__(*args, **kwargs)
+        self.codes = common.adjust_arg_type(code)
+        self.mongo_client = mongo_client
+
+    def start_requests(self):
+        total_count = len(self.codes)
+        print(f'Start scraping {self.name}, {total_count} items...')
+        self.logger.info(f'entire codes list - {self.codes}')
+        for i, one_code in enumerate(self.codes):
+            print(f'{i + 1}/{total_count}. Parsing {self.name}...{one_code}')
+            # reference from https://docs.scrapy.org/en/latest/topics/request-response.html
+            yield scrapy.Request(url=f'https://navercomp.wisereport.co.kr/v2/company/c1080001.aspx?cmp_cd={one_code}',
+                                 callback=self.parse_c108,
+                                 cb_kwargs=dict(code=one_code)
+                                 )
+
+    def parse_c108(self, response, code):
+        """
+            C108 분석한 XPATH
+            date_XPATH = f'//*[@id="tableCmpDetail"]/tr[{(i * 2) + 1}]/td[1]'               # 날짜
+            content_XPATH = f'//*[@id="td{i}"]/@data-content'                               # 제목과내용
+            author_XPATH = f'//*[@id="tableCmpDetail"]/tr[{(i * 2) + 1}]/td[3]/div'         # 작성자
+            company_XPATH = f'//*[@id="tableCmpDetail"]/tr[{(i * 2) + 1}]/td[4]/div'        # 제공처
+            opinion_XPATH = f'//*[@id="tableCmpDetail"]/tr[{(i * 2) + 1}]/td[5]/div[1]'     # 투자의견
+            hprice_XPATH = f'//*[@id="tableCmpDetail"]/tr[{(i * 2) + 1}]/td[6]/div[1]'      # 목표가
+        """
+        # c108페이지가 아직 만들어진 경우 빈테이블을 만들어 저장한다.
+        title = response.xpath('/html/head/title/text()').get()
+        if title == '기업재무정보 접속장애':
+            self.logger.warning(f'{code}: None C108 data...We will make empty table..')
+            # make item to yield
+            item = items.C108items()
+            item['코드'] = code
+            item['df'] = pd.DataFrame(columns=['날짜', '제목', '작성자', '제공처', '투자의견', '목표가', '내용'])
+            yield item
+            return
+
+        # reference from http://hleecaster.com/python-pandas-creating-and-loading-dataframes/(데이터프레임 만들기)
+        opinions = []
+        # 표의 아이템 갯수는 최대 20개
+        for i in range(20):
+            one_opinion = list()
+            # 1. 날짜추가
+            one_opinion.append(response.xpath(f'//*[@id="tableCmpDetail"]/tr[{(i * 2) + 1}]/td[1]/text()').get())
+            # 제목과 내용을 추출한 리스트에서 제목따로 내용따로 추출
+            try:
+                title_and_contents = response.xpath(f'//*[@id="td{i}"]/@data-content').get()\
+                    .replace("<br/><span class='comment_text'>▶</span>", '▶').split('\n')
+                self.logger.debug(title_and_contents)
+            except AttributeError:
+                break
+            # 2. 제목을 추출하고 리스트에서 지움
+            one_opinion.append(title_and_contents[0])
+            del title_and_contents[0]
+            # 3. 작성자, 제공처, 투자의견, 목표가를 차례로 추출하고 리스트에 추가
+            for j in range(3, 7):
+                one_opinion.append(response.xpath(f'//*[@id="tableCmpDetail"]/tr[{(i * 2) + 1}]/td[{j}]/div/text()')
+                                   .get().replace('\t', '').replace('\r\n', ''))
+            # 4. 내용을 추출하고 개행문자를 첨가함
+            contents = ''
+            for item in title_and_contents:
+                contents += item
+            one_opinion.append(contents)
+            self.logger.debug(one_opinion)
+            # 5. 완성된 row를 opinions리스트에 넣는다.
+            opinions.append(one_opinion)
+        self.logger.info(f'\ttotal {len(opinions)} opinions.. {code}')
+
+        df = pd.DataFrame(data=opinions, columns=['날짜', '제목', '작성자', '제공처', '투자의견', '목표가', '내용'])
+        df['내용'] = df['내용'].str.replace('\r', '')
+
+        self.logger.debug(df)
+        # make item to yield
+        item = items.C108items()
+        item['코드'] = code
+        item['df'] = df
+        yield item
+
+    def __str__(self):
+        return 'C108 Spider'

scraper2_hj3415/nfscrapy/nfs/spiders/c101.py

@@ -1,8 +1,6 @@
 import scrapy
 from nfs import items
-#from nfs.spiders import common
-
-# cmd usage : scrapy crawl c101 -a codes=005930
+from nfs.spiders import common
 
 # 여러 잡다한 기호를 없어거나 교체하는 람다함수
 cleaning = lambda s: (
@@ -18,15 +16,9 @@ class C101Spider(scrapy.Spider):
     name = 'c101'
     allowed_domains = ['navercomp.wisereport.co.kr']    # https 주소
 
-    def __init__(self, codes, mongo_client, *args, **kwargs):
+    def __init__(self, code, mongo_client, *args, **kwargs):
         super(C101Spider, self).__init__(*args, **kwargs)
-        # 커맨드 라인에서 입력은 항상 문자열로만 받을수 있어서 리스트로 변환이 필요함.
-        if type(codes) == str:
-            self.codes = [codes, ]
-        elif type(codes) == list:
-            self.codes = codes
-        else:
-            raise TypeError
+        self.codes = common.adjust_arg_type(code)
         self.mongo_client = mongo_client
 
     def start_requests(self):

scraper2_hj3415/nfscrapy/nfs/spiders/c103.py

@@ -0,0 +1,174 @@
+import time
+import scrapy
+from util_hj3415 import utils
+from scrapy.selector import Selector
+from abc import *
+
+from nfs import items
+from nfs.spiders import common
+
+
+class C103Spider(scrapy.Spider, metaclass=ABCMeta):
+    name = 'c103'
+    allowed_domains = ['navercomp.wisereport.co.kr']
+    WAIT = 1.5
+
+    def __init__(self, code, mongo_client, title, *args, **kwargs):
+        """
+        C103페이지의 기반 클래스. 세부 페이지에서 상속해서 사용한다.
+
+        :param code:
+        :param title: 상속된 C103 클래스에서 입력함
+        :param mongo_client:
+        :param args:
+        :param kwargs:
+        """
+        super(C103Spider, self).__init__(*args, **kwargs)
+        self.codes = common.adjust_arg_type(code)
+        self.mongo_client = mongo_client
+        self.driver = utils.get_driver()
+        self.title = title  # ex- 재무상태표q
+
+    def start_requests(self):
+        # reference from https://docs.scrapy.org/en/latest/topics/request-response.html
+        total_count = len(self.codes)
+        print(f'Start scraping {self.name}, {total_count} codes...')
+        self.logger.info(f'entire codes list - {self.codes}')
+
+        # 실제로 페이지를 스크랩하기위해 호출
+        for i, one_code in enumerate(self.codes):
+            print(f'{i + 1}/{total_count}. Parsing {self.title}...{one_code}')
+            yield scrapy.Request(
+                url=f'https://navercomp.wisereport.co.kr/v2/company/c1030001.aspx?cmp_cd={one_code}',
+                callback=getattr(self, f'parse_c103'),
+                cb_kwargs=dict(code=one_code)
+            )
+
+    def parse_c103(self, response, code):
+        # 페이지를 먼저 한번 호출하여 버튼을 눌러 세팅한다.
+        self.setting_page(response.url)
+
+        # html에서 table을 추출하여 dataframe생성
+        self.driver.get(response.url)
+        time.sleep(self.WAIT)
+        html = Selector(text=self.driver.page_source)
+        table_xpath = '//table[2]'
+        df = common.get_df_from_html(html, table_xpath, 1)
+        self.logger.debug(df)
+
+        # make item to yield
+        item = items.C103items()
+        item['코드'] = code
+        item['title'] = self.title
+        item['df'] = df
+        yield item
+
+    @abstractmethod
+    def setting_page(self, url: str):
+        pass
+
+    def __del__(self):
+        if self.driver is not None:
+            print(f'Retrieve {self.name} chrome driver...')
+            self.driver.quit()
+
+
+'''
+# XPATH 상수
+손익계산서 = '//*[@id="rpt_tab1"]'
+재무상태표 = '//*[@id="rpt_tab2"]'
+현금흐름표 = '//*[@id="rpt_tab3"]'
+연간 = '//*[@id="frqTyp0"]'
+분기 = '//*[@id="frqTyp1"]'
+검색 = '//*[@id="hfinGubun"]'
+'''
+
+
+class C103BQ(C103Spider):
+    name = 'c103_bq'
+
+    def __init__(self, code, mongo_client):
+        super(C103BQ, self).__init__(code, mongo_client, title='재무상태표q')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('재무상태표', '//*[@id="rpt_tab2"]'),
+            ('분기', '//*[@id="frqTyp1"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)
+
+
+class C103CQ(C103Spider):
+    name = 'c103_cq'
+
+    def __init__(self, code, mongo_client):
+        super().__init__(code, mongo_client, title='현금흐름표q')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('현금흐름표', '//*[@id="rpt_tab3"]'),
+            ('분기', '//*[@id="frqTyp1"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)
+
+
+class C103IQ(C103Spider):
+    name = 'c103_iq'
+
+    def __init__(self, code, mongo_client):
+        super().__init__(code, mongo_client, title='손익계산서q')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('손익계산서', '//*[@id="rpt_tab1"]'),
+            ('분기', '//*[@id="frqTyp1"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)
+
+
+class C103BY(C103Spider):
+    name = 'c103_by'
+
+    def __init__(self, code, mongo_client):
+        super().__init__(code, mongo_client, title='재무상태표y')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('재무상태표', '//*[@id="rpt_tab2"]'),
+            ('연간', '//*[@id="frqTyp0"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)
+
+
+class C103CY(C103Spider):
+    name = 'c103_cy'
+
+    def __init__(self, code, mongo_client):
+        super().__init__(code, mongo_client, title='현금흐름표y')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('현금흐름표', '//*[@id="rpt_tab3"]'),
+            ('연간', '//*[@id="frqTyp0"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)
+
+
+class C103IY(C103Spider):
+    name = 'c103_iy'
+
+    def __init__(self, code, mongo_client):
+        super().__init__(code, mongo_client, title='손익계산서y')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('손익계산서', '//*[@id="rpt_tab1"]'),
+            ('연간', '//*[@id="frqTyp0"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)

scraper2_hj3415/nfscrapy/nfs/spiders/c104.py

@@ -0,0 +1,228 @@
+import time
+import scrapy
+from util_hj3415 import utils
+from scrapy.selector import Selector
+from abc import *
+
+from nfs import items
+from nfs.spiders import common
+
+
+class C104Spider(scrapy.Spider, metaclass=ABCMeta):
+    name = 'c104'
+    allowed_domains = ['navercomp.wisereport.co.kr']
+    WAIT = 1.5
+
+    def __init__(self, code, mongo_client, title, *args, **kwargs):
+        """
+        C104페이지의 기반 클래스. 세부 페이지에서 상속해서 사용한다.
+
+        :param code:
+        :param title: 상속된 C104 클래스에서 입력함
+        :param mongo_client:
+        :param args:
+        :param kwargs:
+        """
+        super(C104Spider, self).__init__(*args, **kwargs)
+        self.codes = common.adjust_arg_type(code)
+        self.mongo_client = mongo_client
+        self.driver = utils.get_driver()
+        self.title = title  # ex- 수익성q
+
+    def start_requests(self):
+        # reference from https://docs.scrapy.org/en/latest/topics/request-response.html
+        total_count = len(self.codes)
+        print(f'Start scraping {self.name}, {total_count} codes...')
+        self.logger.info(f'entire codes list - {self.codes}')
+
+        # 실제로 페이지를 스크랩하기위해 호출
+        for i, one_code in enumerate(self.codes):
+            print(f'{i + 1}/{total_count}. Parsing {self.title}...{one_code}')
+            yield scrapy.Request(
+                url=f'https://navercomp.wisereport.co.kr/v2/company/c1040001.aspx?cmp_cd={one_code}',
+                callback=getattr(self, f'parse_c104'),
+                cb_kwargs=dict(code=one_code)
+            )
+
+    def parse_c104(self, response, code):
+        # 페이지를 먼저 한번 호출하여 버튼을 눌러 세팅한다.
+        self.setting_page(response.url)
+
+        # html에서 table을 추출하여 dataframe생성
+        self.driver.get(response.url)
+        time.sleep(self.WAIT)
+        html = Selector(text=self.driver.page_source)
+        table_xpath = '//table[@class="gHead01 all-width data-list"]'
+
+        # 테이블명을 _을 기준으로 나눠 리스트를 만든다.
+        title_list = self.title.split('_')
+        self.logger.debug(title_list)
+
+        # dataframe 리스트를 만든다.
+        df_list = []
+        for i in range(2):
+            # 상위테이블 0, 하위테이블 1
+            df_list.append(common.get_df_from_html(html, table_xpath, i))
+        self.logger.debug(df_list)
+
+        # 테이블명리스트와 df리스트를 매치하여 데이터베이스에 저장하기 위해 yield시킴
+        for title, df in list(zip(title_list, df_list)):
+            # df를 log로 출력한다.
+            self.logger.info(title)
+            self.logger.debug(df)
+            # make item to yield
+            item = items.C104items()
+            item['코드'] = code
+            item['title'] = title
+            item['df'] = df
+            yield item
+
+    @abstractmethod
+    def setting_page(self, url: str):
+        pass
+
+    def __del__(self):
+        if self.driver is not None:
+            print(f'Retrieve {self.name} chrome driver...')
+            self.driver.quit()
+
+
+'''
+# XPATH 상수
+수익성 = '//*[ @id="val_tab1"]'
+성장성 = '//*[ @id="val_tab2"]'
+안정성 = '//*[ @id="val_tab3"]'
+활동성 = '//*[ @id="val_tab4"]'
+
+연간 = '//*[@id="frqTyp0"]'
+분기 = '//*[@id="frqTyp1"]'
+검색 = '//*[@id="hfinGubun"]'
+
+가치분석연간 = '//*[@id="frqTyp0_2"]'
+가치분석분기 = '//*[@id="frqTyp1_2"]'
+가치분석검색 = '//*[@id="hfinGubun2"]'
+'''
+
+
+class C104AQ(C104Spider):
+    name = 'c104_aq'
+
+    def __init__(self, code, mongo_client):
+        super(C104AQ, self).__init__(code, mongo_client, title='수익성q_가치분석q')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('수익성', '//*[ @id="val_tab1"]'),
+            ('분기', '//*[@id="frqTyp1"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+            ('가치분석분기', '//*[@id="frqTyp1_2"]'),
+            ('가치분석검색', '//*[@id="hfinGubun2"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)
+
+
+class C104BQ(C104Spider):
+    name = 'c104_bq'
+
+    def __init__(self, code, mongo_client):
+        super(C104BQ, self).__init__(code, mongo_client, title='성장성q')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('성장성', '//*[ @id="val_tab2"]'),
+            ('분기', '//*[@id="frqTyp1"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)
+
+
+class C104CQ(C104Spider):
+    name = 'c104_cq'
+
+    def __init__(self, code, mongo_client):
+        super(C104CQ, self).__init__(code, mongo_client, title='안정성q')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('안정성', '//*[ @id="val_tab3"]'),
+            ('분기', '//*[@id="frqTyp1"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)
+
+
+class C104DQ(C104Spider):
+    name = 'c104_dq'
+
+    def __init__(self, code, mongo_client):
+        super(C104DQ, self).__init__(code, mongo_client, title='활동성q')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('활동성', '//*[ @id="val_tab4"]'),
+            ('분기', '//*[@id="frqTyp1"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)
+
+
+class C104AY(C104Spider):
+    name = 'c104_ay'
+
+    def __init__(self, code, mongo_client):
+        super(C104AY, self).__init__(code, mongo_client, title='수익성y_가치분석y')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('수익성', '//*[ @id="val_tab1"]'),
+            ('연간', '//*[@id="frqTyp0"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+            ('가치분석연간', '//*[@id="frqTyp0_2"]'),
+            ('가치분석검색', '//*[@id="hfinGubun2"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)
+
+
+class C104BY(C104Spider):
+    name = 'c104_by'
+
+    def __init__(self, code, mongo_client):
+        super(C104BY, self).__init__(code, mongo_client, title='성장성y')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('성장성', '//*[ @id="val_tab2"]'),
+            ('연간', '//*[@id="frqTyp0"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)
+
+
+class C104CY(C104Spider):
+    name = 'c104_cy'
+
+    def __init__(self, code, mongo_client):
+        super(C104CY, self).__init__(code, mongo_client, title='안정성y')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('안정성', '//*[ @id="val_tab3"]'),
+            ('연간', '//*[@id="frqTyp0"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)
+
+
+class C104DY(C104Spider):
+    name = 'c104_dy'
+
+    def __init__(self, code, mongo_client):
+        super(C104DY, self).__init__(code, mongo_client, title='활동성y')
+
+    def setting_page(self, url: str):
+        buttons = [
+            ('활동성', '//*[ @id="val_tab4"]'),
+            ('연간', '//*[@id="frqTyp0"]'),
+            ('검색', '//*[@id="hfinGubun"]'),
+        ]
+        common.click_buttons(self.driver, url, buttons, self.WAIT)