김건 / Comment_Analysis

Go to a project
Toggle navigation Toggle navigation pinning
장준영
06b9bee0 1 parent de28eb9d

함수 세부구현(시간대별)

Inline Side-by-side
Showing 2 changed files with 237 additions and 205 deletions
...@@ -28,5 +28,14 @@ ...@@ -28,5 +28,14 @@
28 28
29 * 4차 수정사항 29 * 4차 수정사항
30 30
31 - 기존파일의 분라 관리 시, import관련 오류 문제 해결 완료(하나의 파일로 관리) 31 + 기존파일의 분리 관리 시, import관련 오류 문제 해결 완료(하나의 파일로 관리)
32 사용자 UI의 틀을 구축해놓았고, 곧바로 함수별 추가 세부 구현 예정 32 사용자 UI의 틀을 구축해놓았고, 곧바로 함수별 추가 세부 구현 예정
33 +
34 +* 5차 수정사항
35 +
36 + 1) 네이버 댓글공간엑서 받아온 날짜 정보를 YYYY-MM-DD형식으로 바꿈. ('방금 전, 몇 분 전, 몇 시간 전, 몇 일 전'의 경우를 처리하기 위해 dateTime과 timeDelta 모듈을 활용하여
37 + 현재 날짜를 기준으로 계산하여 YYYY-MM-DD로 저장될 수 있도록
38 + 코드 추가)
39 + 2) 시간대별로 (시작시간, 끝시간)을 입력하여 그 시간에 해당하는 기사를 출력해주는 함수 구현
40 +
41 + 가장 자주 많이 나온 단어 검색과 MATPLOTLIB을 활용한 시각적 표현 구현 예정
...\ No newline at end of file ...\ No newline at end of file
......
1 -{ 1 +from selenium import webdriver
2 - "cells": [ 2 +from selenium.common import exceptions
3 - { 3 +from bs4 import BeautifulSoup
4 - "cell_type": "code", 4 +from datetime import datetime, timedelta
5 - "execution_count": 3, 5 +import time
6 - "metadata": {}, 6 +
7 - "outputs": [ 7 +
8 - { 8 +def getData(url):
9 - "name": "stdout", 9 + ## chrome option걸기 (headless하게 웹 크롤링 수행하기 위해<웹페이지 안보이게 하기>)
10 - "output_type": "stream", 10 + options = webdriver.ChromeOptions()
11 - "text": [ 11 + #options.add_argument('headless')
12 - "******************************\n", 12 + #options.add_argument("disable-gpu")
13 - "\n", 13 + #_url = "https://entertain.naver.com/ranking/comment/list?oid=144&aid=0000642175" # 크롤링할 URL
14 - "\n", 14 + _url = url # 크롤링할 URL
15 - "***< Naver News Crawling >****\n", 15 + webDriver = "C:\\Users\\user\\Desktop\\chromedriver_win32\\chromedriver.exe" # 내 웹드라이버 위치
16 - "\n", 16 + driver = webdriver.Chrome(webDriver,chrome_options=options)
17 - "\n", 17 + #driver = webdriver.Chrome(webDriver)
18 - "******************************\n", 18 + driver.get(_url)
19 - "검색하고자 하는 url을 입력해주세요: \n", 19 + pageCnt = 0
20 - "comment_list를 가져오는 중.....\n" 20 + driver.implicitly_wait(3) # 페이지가 다 로드 될때까지 기다리게함
21 - ] 21 + try:
22 - }, 22 + while True: # 댓글 페이지 끝날때까지 돌림
23 - { 23 + #driver의 find_element_by_css_selector함수로 '네이버 뉴스'의 댓글 '더보기' 버튼을 찾아서 계속 클릭해준다(끝까지)
24 - "name": "stderr", 24 + driver.find_element_by_css_selector(".u_cbox_btn_more").click()
25 - "output_type": "stream", 25 + pageCnt = pageCnt+1
26 - "text": [ 26 +
27 - "C:\\Users\\user\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:14: DeprecationWarning: use options instead of chrome_options\n", 27 + except exceptions.ElementNotVisibleException as e: # 페이지가 끝남
28 - " \n" 28 + pass
29 - ] 29 +
30 - }, 30 + except Exception as e: # 다른 예외 발생시 확인
31 - { 31 + print(e)
32 - "ename": "InvalidArgumentException", 32 +
33 - "evalue": "Message: invalid argument\n (Session info: chrome=78.0.3904.108)\n", 33 + pageSource = driver.page_source # 페이지 소스를 따와서
34 - "output_type": "error", 34 + result = BeautifulSoup(pageSource, "lxml") # 빠르게 뽑아오기 위해 lxml 사용
35 - "traceback": [ 35 +
36 - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", 36 + # nickname, text, time을 raw하게 뽑아온다
37 - "\u001b[1;31mInvalidArgumentException\u001b[0m Traceback (most recent call last)", 37 + comments_raw = result.find_all("span", {"class" : "u_cbox_contents"})
38 - "\u001b[1;32m<ipython-input-3-aa9195667f4b>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 113\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 114\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 115\u001b[1;33m \u001b[0mmain\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", 38 + nicknames_raw = result.find_all("span", {"class" : "u_cbox_nick"})
39 - "\u001b[1;32m<ipython-input-3-aa9195667f4b>\u001b[0m in \u001b[0;36mmain\u001b[1;34m()\u001b[0m\n\u001b[0;32m 97\u001b[0m \u001b[0m_url\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'검색하고자 하는 url을 입력해주세요: '\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 98\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'comment_list를 가져오는 중.....'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 99\u001b[1;33m \u001b[0mcList\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mgetData\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m_url\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 100\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'\\n'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 101\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'comment_list를 다 가져왔습니다!'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", 39 + times_raw = result.find_all("span", {"class" : "u_cbox_date"})
40 - "\u001b[1;32m<ipython-input-3-aa9195667f4b>\u001b[0m in \u001b[0;36mgetData\u001b[1;34m(url)\u001b[0m\n\u001b[0;32m 14\u001b[0m \u001b[0mdriver\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mwebdriver\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mChrome\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mwebDriver\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mchrome_options\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0moptions\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 15\u001b[0m \u001b[1;31m#driver = webdriver.Chrome(webDriver)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 16\u001b[1;33m \u001b[0mdriver\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m_url\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 17\u001b[0m \u001b[0mpageCnt\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 18\u001b[0m \u001b[0mdriver\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mimplicitly_wait\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m3\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;31m# 페이지가 다 로드 될때까지 기다리게함\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", 40 +
41 - "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\selenium\\webdriver\\remote\\webdriver.py\u001b[0m in \u001b[0;36mget\u001b[1;34m(self, url)\u001b[0m\n\u001b[0;32m 331\u001b[0m \u001b[0mLoads\u001b[0m \u001b[0ma\u001b[0m \u001b[0mweb\u001b[0m \u001b[0mpage\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mcurrent\u001b[0m \u001b[0mbrowser\u001b[0m \u001b[0msession\u001b[0m\u001b[1;33m.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 332\u001b[0m \"\"\"\n\u001b[1;32m--> 333\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mCommand\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mGET\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m{\u001b[0m\u001b[1;34m'url'\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m}\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 334\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 335\u001b[0m \u001b[1;33m@\u001b[0m\u001b[0mproperty\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", 41 + # nickname, text, time 값 만을 뽑아내어 리스트로 정리한다
42 - "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\selenium\\webdriver\\remote\\webdriver.py\u001b[0m in \u001b[0;36mexecute\u001b[1;34m(self, driver_command, params)\u001b[0m\n\u001b[0;32m 319\u001b[0m \u001b[0mresponse\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcommand_executor\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdriver_command\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 320\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mresponse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 321\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0merror_handler\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcheck_response\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mresponse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 322\u001b[0m response['value'] = self._unwrap_value(\n\u001b[0;32m 323\u001b[0m response.get('value', None))\n", 42 + comments = [comment.text for comment in comments_raw]
43 - "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\selenium\\webdriver\\remote\\errorhandler.py\u001b[0m in \u001b[0;36mcheck_response\u001b[1;34m(self, response)\u001b[0m\n\u001b[0;32m 240\u001b[0m \u001b[0malert_text\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'alert'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'text'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 241\u001b[0m \u001b[1;32mraise\u001b[0m \u001b[0mexception_class\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmessage\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mscreen\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstacktrace\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0malert_text\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 242\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mexception_class\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmessage\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mscreen\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstacktrace\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 243\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 244\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_value_or_default\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mobj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdefault\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", 43 + nicknames = [nickname.text for nickname in nicknames_raw]
44 - "\u001b[1;31mInvalidArgumentException\u001b[0m: Message: invalid argument\n (Session info: chrome=78.0.3904.108)\n" 44 + times = [time.text for time in times_raw]
45 - ] 45 +
46 - } 46 + naverNewsList = []
47 - ], 47 +
48 - "source": [ 48 + for i in range(len(comments)):
49 - "from selenium import webdriver\n", 49 + info_dic = {'userID' : nicknames[i], 'comment' : comments[i], 'time' : times[i]}
50 - "from selenium.common import exceptions\n", 50 + naverNewsList.append(info_dic)
51 - "from bs4 import BeautifulSoup\n", 51 +
52 - "import time\n", 52 + return naverNewsList
53 - "\n", 53 + #driver.quit()
54 - "def getData(url):\n", 54 +
55 - " ## chrome option걸기 (headless하게 웹 크롤링 수행하기 위해<웹페이지 안보이게 하기>)\n", 55 +from time import sleep
56 - " options = webdriver.ChromeOptions()\n", 56 +
57 - " #options.add_argument('headless')\n", 57 +def print_cList(c_List) :
58 - " #options.add_argument(\"disable-gpu\")\n", 58 + for item in c_List :
59 - " #_url = \"https://entertain.naver.com/ranking/comment/list?oid=144&aid=0000642175\" # 크롤링할 URL\n", 59 + print(item)
60 - " _url = url # 크롤링할 URL\n", 60 +
61 - " webDriver = \"C:\\\\Users\\\\user\\\\Desktop\\\\chromedriver_win32\\\\chromedriver.exe\" # 내 웹드라이버 위치\n", 61 +def search_by_author(c_List,user_ID) :
62 - " driver = webdriver.Chrome(webDriver,chrome_options=options)\n", 62 + result_List = []
63 - " #driver = webdriver.Chrome(webDriver)\n", 63 + for item in c_List :
64 - " driver.get(_url)\n", 64 + #print(item['userID'])
65 - " pageCnt = 0\n", 65 + if ( user_ID in item['userID']) :
66 - " driver.implicitly_wait(3) # 페이지가 다 로드 될때까지 기다리게함\n", 66 + result_List.append(item)
67 - " try:\n", 67 + return result_List
68 - " while True: # 댓글 페이지 끝날때까지 돌림\n", 68 +
69 - " #driver의 find_element_by_css_selector함수로 '네이버 뉴스'의 댓글 '더보기' 버튼을 찾아서 계속 클릭해준다(끝까지)\n", 69 +def search_by_keyword(c_List,keyword) :
70 - " driver.find_element_by_css_selector(\".u_cbox_btn_more\").click() \n", 70 + result_List = []
71 - " pageCnt = pageCnt+1\n", 71 + for item in c_List :
72 - " \n", 72 + #print(item['comment'])
73 - " except exceptions.ElementNotVisibleException as e: # 페이지가 끝남\n", 73 + if ( keyword in item['comment']) :
74 - " pass\n", 74 + result_List.append(item)
75 - " \n", 75 + return result_List
76 - " except Exception as e: # 다른 예외 발생시 확인\n", 76 +
77 - " print(e)\n", 77 +def refine_time(c_List): # 시간에서 몇일 전, 몇 분 전, 방금 전 등의 형태를 YYYY.MM.DD로 바꿔준다
78 - " \n", 78 + now = datetime.now()
79 - " pageSource = driver.page_source # 페이지 소스를 따와서\n", 79 +
80 - " result = BeautifulSoup(pageSource, \"lxml\") # 빠르게 뽑아오기 위해 lxml 사용\n", 80 + for item in c_List:
81 - "\n", 81 + if (item['time'].find('전') != -1): # ~~전이 있으면
82 - " # nickname, text, time을 raw하게 뽑아온다\n", 82 + if (item['time'].find('일 전') != -1): # ~일 전이라면
83 - " comments_raw = result.find_all(\"span\", {\"class\" : \"u_cbox_contents\"})\n", 83 + _day = -(int)(item['time'][0]) # 몇 일전인지에 대한 정수형 변수
84 - " nicknames_raw = result.find_all(\"span\", {\"class\" : \"u_cbox_nick\"})\n", 84 + tempTime = now + timedelta(days=_day)
85 - " times_raw = result.find_all(\"span\", {\"class\" : \"u_cbox_date\"})\n", 85 + item['time'] = str(tempTime)
86 - "\n", 86 + item['time'] = item['time'][0:10]
87 - " # nickname, text, time 값 만을 뽑아내어 리스트로 정리한다\n", 87 + continue
88 - " comments = [comment.text for comment in comments_raw]\n", 88 + elif (item['time'].find('시간 전') != -1):
89 - " nicknames = [nickname.text for nickname in nicknames_raw]\n", 89 + _index = item['time'].index('시')
90 - " times = [time.text for time in times_raw]\n", 90 + _time = -(int)(item['time'][0:_index]) # 몇 시간 전인지에 대한 정수형 변수
91 - " \n", 91 + tempTime = now + timedelta(hours = _time)
92 - " naverNewsList = []\n", 92 + item['time'] = str(tempTime)
93 - " \n", 93 + item['time'] = item['time'][0:10]
94 - " for i in range(len(comments)):\n", 94 + continue
95 - " info_dic = {'userID' : nicknames[i], 'comment' : comments[i], 'time' : times[i]}\n", 95 + elif (item['time'].find('분 전') != -1):
96 - " naverNewsList.append(info_dic)\n", 96 + _index = item['time'].index('분')
97 - " \n", 97 + _minute = -(int)(item['time'][0:_index]) # 몇 분 전인지에 대한 정수형 변수
98 - " return naverNewsList\n", 98 + tempTime = now + timedelta(minutes = _minute)
99 - " #driver.quit()\n", 99 + item['time'] = str(tempTime)
100 - " \n", 100 + item['time'] = item['time'][0:10]
101 - "from time import sleep\n", 101 + continue
102 - "\n", 102 + elif (item['time'].find('방금 전') != -1):
103 - "def print_cList(c_List) :\n", 103 + tempTime = now
104 - " for item in c_List :\n", 104 + item['time'] = str(tempTime)
105 - " print(item)\n", 105 + item['time'] = item['time'][0:10]
106 - "\n", 106 + continue
107 - "def search_by_author(c_List,user_ID) :\n", 107 + else:
108 - " result_List = []\n", 108 + item['time'] = item['time'][0:10]
109 - " for item in c_List :\n", 109 + continue
110 - " print(item['userID'])\n", 110 +
111 - " if ( user_ID in item['userID']) :\n", 111 +
112 - " result_List.append(item)\n", 112 +
113 - " return result_List\n", 113 +
114 - "\n", 114 +
115 - "def search_by_keyword(c_List,keyword) :\n", 115 +def search_by_time(c_List,startTime, endTime) :
116 - " result_List = []\n", 116 + result_List = []
117 - " for item in c_List :\n", 117 +
118 - " print(item['comment'])\n", 118 + startYear = int(startTime[0:4])
119 - " if ( keyword in item['comment']) :\n", 119 +
120 - " result_List.append(item)\n", 120 + if (int(startTime[5]) == 0): # 한자리의 월일 때
121 - " return result_List\n", 121 + startMonth = int(startTime[6])
122 - " \n", 122 + else:
123 - "\n", 123 + startMonth = int(startTime[5:7])
124 - "def search_by_time(c_List,_time) :\n", 124 +
125 - " result_List = []\n", 125 + if (int(startTime[8]) == 0): # 한자리의 일일 때
126 - " for item in c_List :\n", 126 + startDay = int(startTime[9])
127 - " print(item['time'])\n", 127 + else:
128 - " if ( keyword in item['comment']) :\n", 128 + startDay = int(startTime[8:10])
129 - " result_List.append(item)\n", 129 +
130 - " return result_List\n", 130 +
131 - " \n", 131 +
132 - "def main ():\n", 132 + endYear = int(endTime[0:4])
133 - " ## 시작화면\n", 133 +
134 - " \n", 134 + if (int(endTime[5]) == 0): # 한자리의 월일 때
135 - " _star = '*'\n", 135 + endMonth = int(endTime[6])
136 - " print(_star.center(30,'*'))\n", 136 + else:
137 - " print('\\n')\n", 137 + endMonth = int(endTime[5:7])
138 - " headString = '< Naver News Crawling >'\n", 138 +
139 - " print(headString.center(30,'*'))\n", 139 + if (int(endTime[8]) == 0): # 한자리의 일일 때
140 - " print('\\n')\n", 140 + endDay = int(endTime[9])
141 - " print(_star.center(30,'*'))\n", 141 + else:
142 - " \n", 142 + endDay = int(endTime[8:10])
143 - " \n", 143 +
144 - " # 검색하고자 하는 url을 입력받는다\n", 144 + for item in c_List:
145 - " _url = input('검색하고자 하는 url을 입력해주세요: ')\n", 145 + itemYear = int(item['time'][0:4])
146 - " print('comment_list를 가져오는 중.....')\n", 146 +
147 - " cList = getData(_url)\n", 147 + if (int(item['time'][5]) == 0): # 한자리의 월일 때
148 - " print('\\n')\n", 148 + itemMonth = int(item['time'][6])
149 - " print('comment_list를 다 가져왔습니다!')\n", 149 + else:
150 - " \n", 150 + itemMonth = int(item['time'][5:7])
151 - " while(True):\n", 151 +
152 - " print('***********************************')\n", 152 + if (int(item['time'][8]) == 0): # 한자리의 일일 때
153 - " print('1.닉네임 기반 검색')\n", 153 + itemDay = int(item['time'][9])
154 - " print('2.키워드 기반 검색')\n", 154 + else:
155 - " print('3.작성시간 기반 검색')\n", 155 + itemDay = int(item['time'][8:10])
156 - " menu = input('메뉴를 입력해주세요: ')\n", 156 +
157 - " \n", 157 + if (itemYear >= startYear and itemYear <= endYear):
158 - " if(menu == 1):\n", 158 + if (itemMonth >= startMonth and itemMonth <= endMonth):
159 - " print('***********************************')\n", 159 + if(itemDay >= startDay and itemDay <= endDay):
160 - " inputID = input('검색할 닉네임 앞 4자리를 입력해주세요: ')\n", 160 + result_List.append(item)
161 - " search_by_author(cList,inputID)\n", 161 +
162 - " elif(menu == 2):\n", 162 + return result_List
163 - " print('***********************************')\n", 163 +
164 - " inputKW = input('검색할 키워드를 입력해주세요: ')\n", 164 +def printResult(c_List):
165 - " search_by_keyword(cList,inputKW)\n", 165 + for i in range(0,len(c_List)):
166 - " else:\n", 166 + print(c_List[i])
167 - " print('***********************************')\n", 167 +
168 - " inputTime = input('검색할 시간대를 입력해주세요: ')\n", 168 +def main ():
169 - " search_by_time(cList,inputTime)\n", 169 + ## 시작화면
170 - "\n", 170 +
171 - " \n", 171 + _star = '*'
172 - "main()" 172 + print(_star.center(30,'*'))
173 - ] 173 + print('\n')
174 - }, 174 + headString = '< Naver News Crawling >'
175 - { 175 + print(headString.center(30,'*'))
176 - "cell_type": "code", 176 + print('\n')
177 - "execution_count": null, 177 + print(_star.center(30,'*'))
178 - "metadata": {}, 178 +
179 - "outputs": [], 179 +
180 - "source": [] 180 + # 검색하고자 하는 url을 입력받는다
181 - } 181 + _url = input('검색하고자 하는 url을 입력해주세요: ')
182 - ], 182 + print('comment_list를 가져오는 중.....')
183 - "metadata": { 183 + cList = getData(_url)
184 - "kernelspec": { 184 + refine_time(cList)
185 - "display_name": "Python 3", 185 + print('\n')
186 - "language": "python", 186 + print('comment_list를 다 가져왔습니다!')
187 - "name": "python3" 187 +
188 - }, 188 + while(True):
189 - "language_info": { 189 + print('***********************************')
190 - "codemirror_mode": { 190 + print('1.닉네임 기반 검색')
191 - "name": "ipython", 191 + print('2.키워드 기반 검색')
192 - "version": 3 192 + print('3.작성시간 기반 검색')
193 - }, 193 + menu = input('메뉴를 입력해주세요: ')
194 - "file_extension": ".py", 194 +
195 - "mimetype": "text/x-python", 195 + if(menu == str(1)):
196 - "name": "python", 196 + print('***********************************')
197 - "nbconvert_exporter": "python", 197 + inputID = input('검색할 닉네임 앞 4자리를 입력해주세요(전 단계로 가시려면 -1을 입력해주세요): ')
198 - "pygments_lexer": "ipython3", 198 + if(inputID == str(-1)):
199 - "version": "3.7.3" 199 + continue
200 - } 200 + _result = search_by_author(cList,inputID)
201 - }, 201 + printResult(_result)
202 - "nbformat": 4, 202 + print(_result)
203 - "nbformat_minor": 2 203 + elif(menu == str(2)):
204 -} 204 + print('***********************************')
205 + inputKW = input('검색할 키워드를 입력해주세요(전 단계로 가시려면 -1을 입력해주세요): ')
206 + if(inputKW == str(-1)):
207 + continue
208 + _result = search_by_keyword(cList,inputKW)
209 + printResult(_result)
210 + elif(menu == str(3)):
211 + print('***********************************')
212 + print('전 단계로 돌아가시려면 -1을 입력해주세요')
213 + startTime = input('검색할 시간대의 시작일을 입력해주세요(YYYY-MM-DD): ')
214 + endTime = input('검색할 시간대의 마지막 일을 입력해주세요(YYYY-MM-DD): ')
215 +
216 + if(startTime == str(-1) or endTime == str(-1)):
217 + continue
218 +
219 + _result = search_by_time(cList,startTime,endTime)
220 + printResult(_result)
221 + else:
222 + print('잘못된 입력입니다')
223 + continue
224 +
225 +
226 +
227 +main()
......