무회blog

200624-파이썬_004.010_headless_결측치제거_ddf_yoyag_cnt추가_news 본문

Python

200624-파이썬_004.010_headless_결측치제거_ddf_yoyag_cnt추가_news

최무회 2020. 6. 30. 08:31
200624-파이썬_004.010_headless_결측치제거_ddf_yoyag_cnt추가_news
In [1]:
# 200624-파이썬_004.010_headless_결측치제거
# parameter 변경 후 테스트 
# No parts
# ToDayURL   ->    https://news.naver.com/main/list.nhn?mode=LSD&mid=sec&sid1=001&date=20200612&page=1

# Multiprocessing으로 병렬 크롤링하기
from newspaper import Article
from multiprocessing import Pool
import time ,re , timeit ,os
import pandas as pd
import requests as rq
import selenium as se
from selenium import webdriver
from bs4 import BeautifulSoup
from bs4 import SoupStrainer
from selenium import webdriver
from datetime import datetime

td = datetime.today().strftime("%Y%m%d")
tdd = datetime.today().strftime("%m%d")
now = datetime.now()
tdnow = now.strftime('%Y%m%d%H%M%S')


options = webdriver.ChromeOptions()
options.add_argument('headless')
options.add_argument('window-size=1920x1080')
options.add_argument("disable-gpu")
# 혹은 options.add_argument("--disable-gpu")
driver  = webdriver.Chrome("C:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe", options = options) 

############ 폴더 생성 및 체크 
checkFolder = os.path.isdir('./news001/'+'20'+tdd + '/')
checkFolder00 = os.path.isdir('./news002/yibufen/'+'20'+tdd + '/')
checkFolder01 = os.path.isdir('./news002/quanbu/'+'20'+tdd + '/')

creatFolder_in = './news001/'+'20'+tdd + '/'
creatFolder_out00 = './news002/yibufen/'+'20'+tdd + '/'
creatFolder_out01 = './news002/quanbu/'+'20'+tdd + '/'


if checkFolder == True:
    pass
else:
    os.mkdir(creatFolder_in)
    
if checkFolder00 == True:
    pass
else:
    os.mkdir(creatFolder_out00)
    
if checkFolder01 == True:
    pass
else:
    os.mkdir(creatFolder_out01)
In [2]:
# 요약봇 selector -> #main_content > div.article_header > div.article_info > div > div.article_btns > div.article_btns_right > div.media_end_head_autosummary._auto_summary_wrapper > a
slc_yoyag = '#main_content > div.article_header > div.article_info > div > div.article_btns > div.article_btns_right > div.media_end_head_autosummary._auto_summary_wrapper > a'
slc_yoyag_text = '#main_content > div.article_header > div.article_info > div > div.article_btns > div.article_btns_right > div.media_end_head_autosummary._auto_summary_wrapper > div > div.media_end_head_autosummary_layer_body > div._contents_body'


pd_link = [
 'https://news.naver.com/main/list.nhn?mode=LSD&mid=sec&sid1=001'        # 전체     
,'https://news.naver.com/main/list.nhn?mode=LSD&mid=sec&sid1=100'        # 정치속보
,'https://news.naver.com/main/list.nhn?mode=LSD&mid=sec&sid1=101'        # 경제 속보
,'https://news.naver.com/main/list.nhn?mode=LSD&mid=sec&sid1=102'        # 사회 속보
,'https://news.naver.com/main/list.nhn?mode=LSD&mid=sec&sid1=103'        # 생활/문화 속보
,'https://news.naver.com/main/list.nhn?mode=LSD&mid=sec&sid1=104'        # 세계 속보
,'https://news.naver.com/main/list.nhn?mode=LSD&mid=sec&sid1=105'        # IT/과학 속보
,'https://news.naver.com/main/list.nhn?mode=LSD&mid=sec&sid1=110'        # 오피니언 속보             
]

pg_link = [
 '&date='+td+'&page=1'
,'&date='+td+'&page=1'
,'&date='+td+'&page=1'
,'&date='+td+'&page=1'
,'&date='+td+'&page=1'
,'&date='+td+'&page=1'
,'&date='+td+'&page=1'
,'&date='+td+'&page=1'
]
pg_link


lis = []

class testNews:
    def excuteFunc():
        global tg_cnt                                   # 타겟 분야
        global nanugi                                   # 몇 페이지를 돌리고 싶은가 ? 
        global nanugi_bijiao                             
        global rg_cnt                                   # 몇개 분야를 돌리는가 ?         
#         print('분야별 tg_cnt,{}'.format(tg_cnt))
        ## 타이틀 이름 가져오기 
        pdg = pd_link[tg_cnt] + pg_link[tg_cnt]
        driver.get(pdg)
        pdg_src = driver.page_source
        pdg_src = BeautifulSoup(pdg_src, 'html.parser')
        if tg_cnt == 0:
            pdg_src = pdg_src.select('#snb > h2 > a')
            pdg_src = '전체' + pdg_src[0].get_text()
            pdg_src = re.sub("[-=.#/?:$}]",'_', pdg_src)
            pdg_src_title = pdg_src
        else:
            pdg_src = pdg_src.select('#snb > ul > li.on > a')
            pdg_src = pdg_src[0].get_text()
            pdg_src = re.sub("[-=.#/?:$}]",'_', pdg_src)
            pdg_src_title = pdg_src[:-3]
            
        print('pdg_src_title, 분야 ---> {}'.format(pdg_src_title))
            
        ### 링크 마지막 페이지 카운트 가져오기 , 마지막 링크 가져오기
        qianzhui = pd_link[tg_cnt]
        tg_link  = pg_link[tg_cnt]     #  파트별기사 링크 &date=20200613&page=1

        qian = tg_link.find('=')+1
        qian1 = tg_link[:qian] 
        qian2_riqi = tg_date
        qian3 = qian1 + qian2_riqi
        hou = tg_link[len(qian3):]
        hou1 =  hou[:hou.find('=')+1]
        hou2_yeshu = paging
        hou3 = hou1 + hou2_yeshu
        hou4 = hou3[:hou3.find('=')+1]
        houzhui1 = qian3 + hou3
        houzhui = qian3 + hou4
        qh_link1 = qianzhui + houzhui1
        qh_link = qianzhui + houzhui
        
        driver.get(qh_link1)
        html = driver.page_source
        html = BeautifulSoup(html,'html.parser')
        html = html.select('#main_content > div.paging > strong')
        totalPg_cnt = int(html[0].get_text())         # 전체 페이지 갯수
        
#########################################################################################################################
        totalPg_cnt_nanugi = int(totalPg_cnt)              # 해당 페이지수만큼 가져오기 
        nanugi = totalPg_cnt_nanugi
        li00 = []
        li01 = []
        li02 = []
        li03 = []
        li04 = []
        frmNews={} 
        cked = 0
        print('초기화용 frmNews,{}  nanugi_bijiao,{}'.format(len(frmNews), nanugi_bijiao))
        print('nanugi,{} totalPg_cnt, {} totalPg_cnt_nanugi, {}'.format(nanugi, totalPg_cnt , totalPg_cnt_nanugi))
#########################################################################################################################        
        ### 원하는 페이지 만큼 돌려서 리스트에 담기 
        naljiBreak = True         
        for j in range(totalPg_cnt_nanugi):
            if naljiBreak == False:
                break
            url = qh_link + str(j+1)
            driver.get(url)
            html = driver.page_source
            html = BeautifulSoup(html,'html.parser')
            html_body = html.body
            ht_header = html_body.select('#main_content > div.list_body.newsflash_body > ul.type06_headline')
            ht_header = str(ht_header)
            ht_header = BeautifulSoup(ht_header,'html.parser')
            ht_ul     =ht_header.find_all('a')
            
            ht_headerb = html_body.select('#main_content > div.list_body.newsflash_body > ul.type06')
            ht_headerb = str(ht_headerb)
            ht_headerb = BeautifulSoup(ht_headerb,'html.parser')
            ht_ulb     =ht_headerb.find_all('a')

            llsa = []
            for i in ht_ul:
                tt = i.get('href')
                llsa.append(tt)
                
            for i in ht_ulb:
                tt = i.get('href')
                llsa.append(tt)
            llsb = list(set(llsa))

            llsc = llsb
            # # complete ways02
            for u3 in llsc:
                lst_html = driver.get(u3)
                lst_html = driver.page_source
                lst_html = BeautifulSoup(lst_html,'html.parser')
                lst_html = lst_html.body
                click_yoyag = driver.find_elements_by_css_selector(slc_yoyag)
                if len(click_yoyag) > 0 and click_yoyag[0].is_displayed():
                    _logo   = lst_html(class_="press_logo")[0].find('img').get('alt')
                    _title  = lst_html.select('#articleTitle')[0].get_text()
                    _content= lst_html.select('#articleBodyContents')[0].get_text().strip()
###############################################
                    li00.append(pdg_src_title)  ###################### df 값 입력하기 
                    li01.append(_logo) 
                    li02.append(_title)
                    li03.append(_content)
                    
                    click_yoyag[0].click()
                    time.sleep(1)
                    html = driver.page_source
                    html = BeautifulSoup(html,'html.parser')
                    html = html.body.select(slc_yoyag_text)
                    for i in html:
                        _press_yoyag = i.get_text()
                        li04.append(_press_yoyag)
                    cked = cked + 1
                    print(" j {} cked={}".format(j,cked) , end= ',')    
#########################################################################################################################
                    # 전체 돌릴때 적용 되는 범위지정 ,  nanugi_bijiao
                    if nanugi_bijiao > 500:
                        pass 
                    else:  # 지정하여 사용 갯수 출력 할때 
                        if cked >= nanugi_bijiao:  
                            naljiBreak = False
                            break
#########################################################################################################################                        
                else:
                    continue
        frmNews = {'subMenu':li00, 'newsFrom':li01, 'title':li02, 'content':li03 , 'yoyag':li04}
        df = pd.DataFrame(frmNews)
        df['content']=df['content'].str.replace("// flash 오류를 우회하기 위한 함수 추가\n","").str.replace("function _flash_removeCallback()","")
        df['content']=df['content'].str[3:].str.replace("\n","").str.replace("\t","").str.replace("{}","").str.strip()
        excel_nm = tdnow+'_'+str(tg_cnt)+'_'+str(nanugi)+ '.xlsx'
        df.to_excel(creatFolder_in +excel_nm)
        print('리스트용 frmNews,{}'.format(len(frmNews)))
        print('-'*50)

############################################################################
## 분야 
# 0  전체              # 1  정치속보        # 2  경제 속보        # 3  사회 속보     
# 4  생활/문화 속보    # 5  세계 속보       # 6  IT/과학 속보     # 7  오피니언 속보        
############################################################################
## 일부분 돌리기
    def start_switch():
        for z in range(rg_cnt):
            if z == 0 : 
                continue
            global tg_cnt
            tg_cnt   =  z            # 분야별
            print('start_switch tg_cnt, {}'.format(tg_cnt))
            testNews.excuteFunc()
        second_run()
############################################################################
##  전체 돌리기
    def start_all():
        for z in range(rg_cnt):
# #             if z < 7: 
            if z == 0: 
                continue
            global nanugi_bijiao
            global tg_cnt
            tg_cnt   =  z       
            print('start_all tg_cnt, {}'.format(tg_cnt))
            testNews.excuteFunc()
        second_all()
############################################################################
## 한번 돌릴때 
    def start_switch1():
        print('start_switch1 ')
        testNews.excuteFunc()
        select_First()
In [3]:
############################################################################
print("#"*50)
time.sleep(2)
sheet_reNm = []
path = creatFolder_in

###########################################################################
##  결측치 값 행 빼기     
def drop_naValue():      
    os.getcwd()
    os_list = os.listdir(creatFolder_out01)
    os_list.sort(reverse = True)  # 내림차순 
    filename = os_list[0]
    path1 = creatFolder_out01
    path2= path1 + filename
    sheet_name = 6  #  6까지 있음 

    print(path2)
    print('-'*50)
#     dfs_list = [pd.read_excel(path2 , sheet_name = x).drop_duplicates('content').dropna(axis=0) for x in range(rg_cnt-1)]               # 결측값 행 빼기    # 엑셀 파일 읽기 
    dfs_list = [pd.read_excel(path2 , sheet_name = x).drop_duplicates('content').dropna(axis=0).head(100) for x in range(rg_cnt-1)]               # 결측값 행 빼기    # 엑셀 파일 읽기 

    sheet_reNms = []                                                                              # 시트명 정하기 
    for i,j in enumerate(dfs_list):
        sheet_reNms.append(j['subMenu'][0])
    excel_reNm = creatFolder_out01+'/'+tdnow +'_Replace'+'_quanbu_nv.xlsx'                       # 경로 설정 
    writer = pd.ExcelWriter(excel_reNm, engine = 'xlsxwriter')
    ############ 메뉴명 정의
    for i,j in enumerate(dfs_list):
        j = j[['subMenu','newsFrom','title','content','yoyag']]                                        
        j.to_excel(writer, sheet_name = sheet_reNms[i])
    writer.save()
    writer.close()
    print("success_writer_Replace")
    
####################################################################################################
    time.sleep(2)
    ddf = pd.concat([pd.read_excel(excel_reNm, sheet_name = x) for x in range(6)])
#     ddf = pd.concat([pd.read_excel('./news002/quanbu/20200625082044_Replace_quanbu_nv.xlsx', sheet_name = x).head(20) for x in range(6)])
    ddf = ddf[['subMenu','title','content','yoyag']]
    sample_list = []
    ss = ddf['yoyag'].tolist()
    for i in ss:
        ts = i.replace('.','._').split('_')
        ts = list(filter(bool, ts))
        sample_list.append(ts)

    sample_listcnt = [len(sample_list[x]) for x in range(len(sample_list))]

    ddf['yoyag_cnt'] = sample_listcnt

    ddf = ddf[ddf['yoyag_cnt'] >= 3][['subMenu','title','content','yoyag','yoyag_cnt']]
    ddf = ddf[ddf['yoyag_cnt'] < 4][['subMenu','title','content','yoyag','yoyag_cnt']]
    ddf
    ddf.to_excel('./news002/quanbu/news_100.xlsx',sheet_name='통합')

    path=creatFolder_out01  # creatFolder_out01 , excel_reNm
    path=os.path.realpath(path)
    os.startfile(path)
###########################################################################
## 한번 돌릴때 , 지정된 분야 , 
def select_First():
    excel_nm = tdnow+'_'+str(tg_cnt)+'_'+str(nanugi)+'_select_First' +  '.xlsx'
    print(type(excel_nm))
    df00 = pd.read_excel(path+excel_nm)
    sheet_reNm.append(df00['subMenu'][0])
    excel_wrNm = './news002/'+str(excel_nm)
    print('sheet_reNm,{}'.format(sheet_reNm)) 
    print('excel_wrNm,{}'.format(excel_wrNm)) 
    
    writer = pd.ExcelWriter(excel_wrNm, engine = 'xlsxwriter')
    df00['subMenu'] = sheet_reNm[0]
    df00.to_excel(writer, sheet_name = sheet_reNm[0])    
    writer.save()
    writer.close() 
    print("success_writer")
    
##################################################
#     ## 일부분 돌릴때 , 성공    
def second_run():
##################################################
    ex_nm = os.listdir(path)
    dfs = [pd.read_excel(path+x) for x in ex_nm]                                             # 엑셀 파일 읽기 
    sheet_reNms = []                                                                    # 시트명 정하기 
    for i,j in enumerate(dfs):
        sheet_reNms.append(j['subMenu'][0])
    excel_reNm = './news002/yibufen/'+tdnow +'_yibufen_nv.xlsx'                       # 경로 설정 
    writer = pd.ExcelWriter(excel_reNm, engine = 'xlsxwriter')
    for i,j in enumerate(dfs):
        j.to_excel(writer, sheet_name = sheet_reNms[i])
    writer.save()
    writer.close()
    print("success_writer")
##################################################
#     ##  전체 돌리기  excel_nm = td+'_'+str(nanugi)+'_'+str(tg_cnt)+ '.xlsx'
def second_all():
    ex_nm = os.listdir(path)
    dfs = [pd.read_excel(path+x) for x in ex_nm]                                             # 엑셀 파일 읽기 
    sheet_reNms = []                                                                    # 시트명 정하기 
    for i,j in enumerate(dfs):
        sheet_reNms.append(j['subMenu'][0])
    excel_reNm = creatFolder_out01+'/'+tdnow +'_MeiQingKong_quanbu.xlsx'                       # 경로 설정 
    writer = pd.ExcelWriter(excel_reNm, engine = 'xlsxwriter')
    for i,j in enumerate(dfs):
        j.to_excel(writer, sheet_name = sheet_reNms[i])
    writer.save()
    writer.close()
    print("success_writer")
    time.sleep(2)
    drop_naValue()

# second_all()    

##################################################
In [ ]:
## 디폴트값 
# td = datetime.today().strftime("%Y%m%d")
# tdnow = now.strftime('%Y%m%d%H%M%S')

tg_date       =  td                     # 날짜 
paging        = '601'                   # 랜덤 테스트 페이지 
tg_cnt        =  1                      # 분야
nanugi        =  1                      # 추출 페이지수 지정  , 2 페이지 이상 
nanugi_bijiao =  120                     # 출력 갯수 , # 전체 돌릴때 적용 되는 범위지정 , nanugi_bijiao > 500: pass 
rg_cnt        =  7                    # 분야별 for 문 돌리려는 갯수
############################################################################
start_now = int(time.time())             # 시작 시간 저장
# testNews.start_switch()                # 일부분 돌리기 
# testNews.start_all()                   # 전체 돌리기 
# testNews.start_switch1()               # 하나 돌리기 


pool = Pool(processes=3) # 4개의 프로세스를 사용합니다.
pool.map(testNews.start_all(), '') # 실제 돌리려고 하는 함수를 넣어 줍니다.



############################################################################
ends = int(time.time()) - start_now

print('start_now, {} 초'.format(start_now))
print('end_now, {} 초'.format(ends))
driver.quit()
print('driver.quit() 되었습니다.')

start_all tg_cnt, 1
pdg_src_title, 분야 ---> 정치 
초기화용 frmNews,0  nanugi_bijiao,120
nanugi,16 totalPg_cnt, 16 totalPg_cnt_nanugi, 16
 j 0 cked=1, j 0 cked=2, j 0 cked=3, j 0 cked=4, j 0 cked=5, j 0 cked=6, j 1 cked=7, j 1 cked=8, j 1 cked=9, j 1 cked=10, j 1 cked=11, j 1 cked=12, j 1 cked=13, j 1 cked=14, j 1 cked=15, j 1 cked=16, j 1 cked=17, j 1 cked=18, j 2 cked=19, j 2 cked=20, j 2 cked=21, j 2 cked=22, j 2 cked=23, j 2 cked=24, j 2 cked=25, j 2 cked=26, j 2 cked=27, j 2 cked=28, j 2 cked=29, j 2 cked=30, j 2 cked=31, j 3 cked=32, j 3 cked=33, j 3 cked=34, j 3 cked=35, j 3 cked=36, j 3 cked=37, j 3 cked=38, j 3 cked=39, j 3 cked=40, j 3 cked=41, j 3 cked=42, j 3 cked=43, j 3 cked=44, j 3 cked=45, j 3 cked=46, j 3 cked=47, j 4 cked=48, j 4 cked=49, j 4 cked=50, j 4 cked=51, j 4 cked=52, j 4 cked=53, j 4 cked=54, j 4 cked=55, j 4 cked=56, j 4 cked=57, j 4 cked=58, j 5 cked=59, j 5 cked=60, j 5 cked=61, j 5 cked=62, j 5 cked=63, j 5 cked=64, j 5 cked=65, j 5 cked=66, j 5 cked=67, j 5 cked=68, j 5 cked=69, j 5 cked=70, j 5 cked=71, j 5 cked=72, j 5 cked=73, j 5 cked=74, j 6 cked=75, j 6 cked=76, j 6 cked=77, j 6 cked=78, j 6 cked=79, j 6 cked=80, j 6 cked=81, j 6 cked=82, j 6 cked=83, j 6 cked=84, j 6 cked=85, j 6 cked=86, j 6 cked=87, j 6 cked=88, j 6 cked=89, j 7 cked=90, j 7 cked=91, j 7 cked=92, j 7 cked=93, j 7 cked=94, j 7 cked=95, j 7 cked=96, j 7 cked=97, j 7 cked=98, j 7 cked=99, j 7 cked=100, j 7 cked=101, j 7 cked=102, j 7 cked=103, j 7 cked=104, j 7 cked=105, j 7 cked=106, j 7 cked=107, j 7 cked=108, j 7 cked=109, j 8 cked=110, j 8 cked=111, j 8 cked=112, j 8 cked=113, j 8 cked=114, j 8 cked=115, j 8 cked=116, j 8 cked=117, j 8 cked=118, j 8 cked=119, j 8 cked=120,리스트용 frmNews,5
--------------------------------------------------
start_all tg_cnt, 2
pdg_src_title, 분야 ---> 경제 
초기화용 frmNews,0  nanugi_bijiao,120
nanugi,34 totalPg_cnt, 34 totalPg_cnt_nanugi, 34
 j 0 cked=1, j 0 cked=2, j 0 cked=3, j 0 cked=4, j 0 cked=5, j 0 cked=6, j 0 cked=7, j 0 cked=8, j 0 cked=9, j 0 cked=10, j 0 cked=11, j 0 cked=12, j 0 cked=13, j 0 cked=14, j 0 cked=15, j 0 cked=16, j 0 cked=17, j 0 cked=18, j 0 cked=19, j 0 cked=20, j 1 cked=21, j 1 cked=22, j 1 cked=23, j 1 cked=24, j 1 cked=25, j 1 cked=26, j 1 cked=27, j 1 cked=28, j 1 cked=29, j 1 cked=30, j 1 cked=31, j 1 cked=32, j 1 cked=33, j 1 cked=34, j 1 cked=35, j 1 cked=36, j 1 cked=37, j 1 cked=38, j 1 cked=39, j 1 cked=40, j 2 cked=41, j 2 cked=42, j 2 cked=43, j 2 cked=44, j 2 cked=45, j 2 cked=46, j 2 cked=47, j 2 cked=48, j 2 cked=49, j 2 cked=50, j 2 cked=51, j 2 cked=52, j 2 cked=53, j 2 cked=54, j 2 cked=55, j 2 cked=56, j 2 cked=57, j 3 cked=58, j 3 cked=59, j 3 cked=60, j 3 cked=61, j 3 cked=62, j 3 cked=63, j 3 cked=64, j 3 cked=65, j 3 cked=66, j 3 cked=67, j 3 cked=68, j 3 cked=69, j 3 cked=70, j 4 cked=71, j 4 cked=72, j 4 cked=73, j 4 cked=74, j 4 cked=75, j 4 cked=76, j 4 cked=77, j 4 cked=78, j 4 cked=79, j 4 cked=80, j 4 cked=81, j 5 cked=82, j 5 cked=83, j 5 cked=84, j 5 cked=85, j 5 cked=86, j 5 cked=87, j 6 cked=88, j 6 cked=89, j 6 cked=90, j 6 cked=91, j 6 cked=92, j 6 cked=93, j 6 cked=94, j 6 cked=95, j 6 cked=96, j 6 cked=97, j 7 cked=98, j 7 cked=99, j 7 cked=100, j 7 cked=101, j 7 cked=102, j 7 cked=103, j 7 cked=104, j 7 cked=105, j 7 cked=106, j 7 cked=107, j 7 cked=108, j 7 cked=109, j 7 cked=110, j 7 cked=111, j 7 cked=112, j 7 cked=113, j 8 cked=114, j 8 cked=115, j 8 cked=116, j 8 cked=117, j 8 cked=118, j 8 cked=119, j 8 cked=120,리스트용 frmNews,5
--------------------------------------------------
start_all tg_cnt, 3
pdg_src_title, 분야 ---> 사회 
초기화용 frmNews,0  nanugi_bijiao,120
nanugi,49 totalPg_cnt, 49 totalPg_cnt_nanugi, 49
 j 0 cked=1, j 0 cked=2, j 0 cked=3, j 0 cked=4, j 0 cked=5, j 0 cked=6, j 0 cked=7, j 0 cked=8, j 0 cked=9, j 0 cked=10, j 0 cked=11, j 0 cked=12, j 0 cked=13, j 0 cked=14, j 0 cked=15, j 0 cked=16, j 0 cked=17, j 0 cked=18, j 1 cked=19, j 1 cked=20, j 1 cked=21, j 1 cked=22, j 1 cked=23, j 1 cked=24, j 1 cked=25, j 1 cked=26, j 1 cked=27, j 1 cked=28, j 1 cked=29, j 1 cked=30, j 1 cked=31, j 2 cked=32, j 2 cked=33, j 2 cked=34, j 2 cked=35, j 2 cked=36, j 2 cked=37, j 2 cked=38, j 2 cked=39, j 2 cked=40, j 2 cked=41, j 3 cked=42, j 3 cked=43, j 3 cked=44, j 3 cked=45, j 3 cked=46, j 3 cked=47, j 3 cked=48, j 3 cked=49, j 3 cked=50, j 3 cked=51, j 3 cked=52, j 3 cked=53, j 3 cked=54, j 3 cked=55, j 4 cked=56, j 4 cked=57, j 4 cked=58, j 4 cked=59, j 4 cked=60, j 4 cked=61, j 4 cked=62, j 4 cked=63, j 4 cked=64, j 4 cked=65, j 4 cked=66, j 4 cked=67, j 4 cked=68, j 5 cked=69, j 5 cked=70, j 5 cked=71, j 5 cked=72, j 5 cked=73, j 5 cked=74, j 5 cked=75, j 5 cked=76, j 5 cked=77, j 5 cked=78, j 5 cked=79, j 5 cked=80, j 6 cked=81, j 6 cked=82, j 6 cked=83, j 6 cked=84, j 6 cked=85, j 6 cked=86, j 7 cked=87, j 7 cked=88, j 7 cked=89, j 7 cked=90, j 7 cked=91, j 7 cked=92, j 7 cked=93, j 7 cked=94, j 7 cked=95, j 7 cked=96, j 7 cked=97, j 8 cked=98, j 8 cked=99, j 8 cked=100, j 8 cked=101, j 8 cked=102, j 8 cked=103, j 8 cked=104, j 8 cked=105, j 8 cked=106, j 8 cked=107, j 8 cked=108, j 8 cked=109, j 8 cked=110, j 8 cked=111, j 8 cked=112, j 9 cked=113, j 9 cked=114, j 9 cked=115, j 9 cked=116, j 9 cked=117, j 9 cked=118, j 10 cked=119, j 10 cked=120,리스트용 frmNews,5
--------------------------------------------------
start_all tg_cnt, 4
pdg_src_title, 분야 ---> 생활_문화 
초기화용 frmNews,0  nanugi_bijiao,120
nanugi,13 totalPg_cnt, 13 totalPg_cnt_nanugi, 13
 j 0 cked=1, j 0 cked=2, j 0 cked=3, j 0 cked=4, j 0 cked=5, j 0 cked=6, j 0 cked=7, j 0 cked=8, j 0 cked=9, j 0 cked=10, j 0 cked=11, j 0 cked=12, j 1 cked=13, j 1 cked=14, j 1 cked=15, j 1 cked=16, j 1 cked=17, j 1 cked=18, j 1 cked=19, j 1 cked=20, j 1 cked=21, j 1 cked=22, j 1 cked=23, j 1 cked=24, j 1 cked=25, j 1 cked=26, j 1 cked=27, j 1 cked=28, j 2 cked=29, j 2 cked=30, j 2 cked=31, j 2 cked=32, j 2 cked=33, j 2 cked=34, j 2 cked=35, j 2 cked=36, j 2 cked=37, j 2 cked=38, j 2 cked=39, j 2 cked=40, j 3 cked=41, j 3 cked=42, j 3 cked=43, j 3 cked=44, j 3 cked=45, j 3 cked=46, j 3 cked=47, j 3 cked=48, j 3 cked=49, j 3 cked=50, j 3 cked=51, j 3 cked=52, j 3 cked=53, j 3 cked=54, j 3 cked=55, j 3 cked=56, j 3 cked=57, j 3 cked=58, j 4 cked=59, j 4 cked=60, j 4 cked=61, j 4 cked=62, j 4 cked=63, j 4 cked=64, j 4 cked=65, j 4 cked=66, j 4 cked=67, j 4 cked=68, j 4 cked=69, j 5 cked=70, j 5 cked=71, j 5 cked=72, j 5 cked=73, j 5 cked=74, j 5 cked=75, j 5 cked=76, j 5 cked=77, j 5 cked=78, j 5 cked=79, j 5 cked=80, j 5 cked=81, j 5 cked=82, j 5 cked=83, j 5 cked=84, j 5 cked=85, j 6 cked=86, j 6 cked=87, j 6 cked=88, j 6 cked=89, j 6 cked=90, j 6 cked=91, j 6 cked=92, j 6 cked=93, j 6 cked=94, j 6 cked=95, j 6 cked=96, j 6 cked=97, j 6 cked=98, j 6 cked=99, j 6 cked=100, j 6 cked=101, j 6 cked=102, j 7 cked=103, j 7 cked=104, j 7 cked=105, j 7 cked=106, j 7 cked=107, j 7 cked=108, j 7 cked=109, j 7 cked=110, j 7 cked=111, j 7 cked=112, j 7 cked=113, j 7 cked=114, j 7 cked=115, j 7 cked=116, j 7 cked=117, j 7 cked=118, j 7 cked=119, j 7 cked=120,리스트용 frmNews,5
--------------------------------------------------
start_all tg_cnt, 5
pdg_src_title, 분야 ---> 세계 
초기화용 frmNews,0  nanugi_bijiao,120
nanugi,77 totalPg_cnt, 77 totalPg_cnt_nanugi, 77
 j 0 cked=1, j 0 cked=2, j 0 cked=3, j 0 cked=4, j 0 cked=5, j 0 cked=6, j 0 cked=7, j 0 cked=8, j 0 cked=9, j 0 cked=10, j 0 cked=11, j 1 cked=12, j 1 cked=13, j 1 cked=14, j 1 cked=15, j 1 cked=16, j 1 cked=17, j 1 cked=18, j 1 cked=19, j 1 cked=20, j 1 cked=21, j 1 cked=22, j 2 cked=23, j 2 cked=24, j 2 cked=25, j 2 cked=26, j 2 cked=27, j 2 cked=28, j 2 cked=29, j 2 cked=30, j 3 cked=31, j 3 cked=32, j 3 cked=33, j 3 cked=34, j 3 cked=35, j 3 cked=36, j 3 cked=37, j 3 cked=38, j 4 cked=39, j 4 cked=40, j 4 cked=41, j 4 cked=42, j 4 cked=43, j 4 cked=44, j 4 cked=45, j 4 cked=46, j 4 cked=47, j 4 cked=48, j 4 cked=49, j 4 cked=50, j 4 cked=51, j 4 cked=52, j 4 cked=53, j 5 cked=54, j 5 cked=55, j 5 cked=56, j 5 cked=57, j 5 cked=58, j 5 cked=59, j 5 cked=60, j 5 cked=61, j 5 cked=62, j 5 cked=63, j 5 cked=64, j 6 cked=65, j 6 cked=66, j 6 cked=67, j 6 cked=68, j 6 cked=69, j 6 cked=70, j 6 cked=71, j 6 cked=72, j 6 cked=73, j 6 cked=74, j 7 cked=75, j 7 cked=76, j 7 cked=77, j 7 cked=78, j 8 cked=79, j 8 cked=80, j 8 cked=81, j 8 cked=82, j 8 cked=83, j 8 cked=84, j 8 cked=85, j 8 cked=86, j 8 cked=87, j 9 cked=88, j 9 cked=89, j 9 cked=90, j 9 cked=91, j 10 cked=92, j 10 cked=93, j 10 cked=94, j 10 cked=95, j 10 cked=96, j 10 cked=97, j 10 cked=98, j 10 cked=99, j 11 cked=100, j 11 cked=101, j 11 cked=102, j 11 cked=103, j 12 cked=104, j 12 cked=105, j 12 cked=106, j 12 cked=107, j 12 cked=108, j 12 cked=109, j 12 cked=110, j 13 cked=111, j 13 cked=112, j 13 cked=113, j 14 cked=114, j 14 cked=115, j 14 cked=116, j 15 cked=117, j 15 cked=118, j 15 cked=119, j 15 cked=120,리스트용 frmNews,5
--------------------------------------------------
start_all tg_cnt, 6
pdg_src_title, 분야 ---> IT_과학 
초기화용 frmNews,0  nanugi_bijiao,120
nanugi,4 totalPg_cnt, 4 totalPg_cnt_nanugi, 4
 j 0 cked=1, j 0 cked=2, j 0 cked=3, j 0 cked=4, j 0 cked=5, j 0 cked=6, j 0 cked=7, j 0 cked=8, j 0 cked=9, j 0 cked=10, j 0 cked=11, j 0 cked=12, j 0 cked=13, j 0 cked=14, j 0 cked=15, j 1 cked=16, j 1 cked=17, j 1 cked=18, j 1 cked=19, j 1 cked=20, j 1 cked=21, j 1 cked=22, j 1 cked=23, j 1 cked=24, j 1 cked=25, j 1 cked=26, j 1 cked=27, j 1 cked=28, j 1 cked=29, j 1 cked=30, j 1 cked=31, j 1 cked=32, j 1 cked=33, j 1 cked=34, j 2 cked=35, j 2 cked=36, j 2 cked=37, j 2 cked=38, j 2 cked=39, j 2 cked=40, j 2 cked=41, j 2 cked=42, j 2 cked=43, j 2 cked=44, j 2 cked=45, j 2 cked=46, j 2 cked=47, j 2 cked=48, j 2 cked=49,
저작자표시 비영리 변경금지

'Python' 카테고리의 다른 글

200701-summarize_test_gensim,모듈화,test,bm25test  (0) 2020.07.02
200701-yoyag_test_010, 요약뉴스처리,파이썬, 전처리  (0) 2020.07.01
python: 200629-gensim_bm25-Copy1, BM25Okapi  (0) 2020.06.30
200625-yoyag_test_008-006.002, 젠심 요약본뉴스  (0) 2020.06.25
python: # python 200623-yoyag_test_008-005  (0) 2020.06.24
'Python' Related Articles more
Comments