move to opensource

src/kr/co/swh/lecture/mathorithm/crawler.py

@@ -1,75 +0,0 @@
-import requests
-from bs4 import BeautifulSoup  # BeautifulSoup import
-
-class Movie:
-    def __init__(self, n, u, rank, reples):
-        self.name = n
-        self.url = u
-        self.ranking = rank
-        self.reples = reples
-    def __str__(self):
-        return str(self.ranking) + "위\t제목:" + self.name + "\t주소:" + self.url + "\n리플:" + str(self.reples)
-
-class Naver:
-
-    # 기본 정보
-    naverHomeUrl = 'https://www.naver.com/'
-    movieHomeUrl = 'https://movie.naver.com'
-    movieRankingHomeUrl = 'https://movie.naver.com/movie/sdb/rank/rmovie.nhn'
-    soupHtmlParser = 'html.parser'
-
-    # 영화 태그패턴
-    moviePattern = 'div[class=tit3]'
-    replePattern = 'div[class=score_reple]'
-
-    def __init__(self):
-        naverResponse = requests.get(self.naverHomeUrl)
-        naverHtml = naverResponse.text
-        self.naverSoup = BeautifulSoup(naverHtml, self.soupHtmlParser)
-
-        movieResponse = requests.get(self.movieRankingHomeUrl)
-        movieHtml = movieResponse.text
-        self.movieSoup = BeautifulSoup(movieHtml, self.soupHtmlParser)
-
-    def getMovieReple(self, url):
-        movieReples = []
-        repleText = requests.get(self.movieHomeUrl + url).text
-        repleSoup = BeautifulSoup(repleText, self.soupHtmlParser)
-        for tag in repleSoup.select(self.replePattern):
-            rep = tag.select('p').pop(0).text
-            movieReples.append(rep)
-        return movieReples
-
-    def getTitles(self):
-        titles = []
-        for tag in self.movieSoup.select(self.moviePattern):
-            titles.append(tag.text.strip().replace("\n", ""))
-        return titles
-
-    def getAlls(self):
-        movies = []
-        ranking = 1
-        for tag in self.movieSoup.select(self.moviePattern):
-            n = tag.text.strip().replace("\n", "")
-            u = tag.find('a').get('href')
-            t = n, u, ranking, self.getMovieReple(u)                #   튜플
-            print(t)
-            m = Movie(n, u, ranking, self.getMovieReple(u))         #   Movie 클래스
-            movies.append(m)
-            ranking = ranking + 1
-        return movies
-
-
-    def realTimeSearchWord(self):
-        words = []
-        ranking = 1
-        realTimeWords = self.naverSoup.select('ul[class=ah_l] li[class=ah_item] a')
-        for tag in realTimeWords:
-            if tag.get('data-ssl'):
-                relatedWord = requests.get(tag.get('href')).text
-                relatedSoup = BeautifulSoup(relatedWord, self.soupHtmlParser)
-                relatedWords = []
-                for relatedTag in relatedSoup.select('ul[class=_related_keyword_ul] li a'):
-                    relatedWords.append(relatedTag.text)
-                words.append((tag.select('span[class=ah_r]')[0].text, tag.select('span[class=ah_k]')[0].text, tag.get('href'), relatedWords))
-        return words

src/kr/co/swh/lecture/mathorithm/naverMovieClass_step1.py

@@ -1,65 +0,0 @@
-import requests
-from bs4 import BeautifulSoup  # BeautifulSoup import
-
-class Movie:
-    def __init__(self, n, u, rank, reples):
-        self.name = n
-        self.url = u
-        self.ranking = rank
-        self.reples = reples
-
-    def __str__(self):
-        return str(self.ranking) + "위\t제목:" + self.name + "\t주소:" + self.url + "\n리플:" + str(self.reples)
-
-class Naver:
-
-    # 기본 정보
-    movieHomeUrl = 'https://movie.naver.com'
-    movieRankingHomeUrl = 'https://movie.naver.com/movie/sdb/rank/rmovie.nhn'
-    soupHtmlParser = 'html.parser'
-
-    # 영화 태그패턴
-    moviePattern = 'div[class=tit3]'
-    replePattern = 'div[class=score_reple]'
-
-    def __init__(self):
-        movieResponse = requests.get(self.movieRankingHomeUrl)
-        movieHtml = movieResponse.text
-        self.movieSoup = BeautifulSoup(movieHtml, self.soupHtmlParser)
-
-    def getMovieReple(self, url):
-        movieReples = []
-        repleText = requests.get(self.movieHomeUrl + url).text
-        repleSoup = BeautifulSoup(repleText, self.soupHtmlParser)
-        for tag in repleSoup.select(self.replePattern):
-            rep = tag.select('p').pop().text
-            movieReples.append(rep)
-        return movieReples
-
-    def getTitles(self):
-        titles = []
-        for tag in self.movieSoup.select(self.moviePattern):
-            titles.append(tag.text.strip().replace("\n", ""))
-        return titles
-
-    def getAlls(self):
-        movies = []
-        ranking = 1
-        for tag in self.movieSoup.select(self.moviePattern):
-            n = tag.text.strip().replace("\n", "")
-            u = tag.find('a').get('href')
-            repless = self.getMovieReple(u)
-            t = n, u, ranking, repless                #   튜플
-            print(t)
-            m = Movie(n, u, ranking, repless)         #   Movie 클래스
-            movies.append(m)
-            ranking = ranking + 1
-        return movies
-
-
-# 클래스 사용
-naver = Naver()
-print(naver.getTitles())
-
-for b in naver.getAlls():
-    print(b)

src/kr/co/swh/lecture/mathorithm/naverMovieClass_step2.py

@@ -1,85 +0,0 @@
-import requests
-from bs4 import BeautifulSoup  # BeautifulSoup import
-
-class Movie:
-    def __init__(self, n, u, rank, reples):
-        self.name = n
-        self.url = u
-        self.ranking = rank
-        self.reples = reples
-    def __str__(self):
-        return str(self.ranking) + "위\t제목:" + self.name + "\t주소:" + self.url + "\n리플:" + str(self.reples)
-
-class Naver:
-
-    # 기본 정보
-    naverHomeUrl = 'https://www.naver.com/'
-    movieHomeUrl = 'https://movie.naver.com'
-    movieRankingHomeUrl = 'https://movie.naver.com/movie/sdb/rank/rmovie.nhn'
-    soupHtmlParser = 'html.parser'
-
-    # 영화 태그패턴
-    moviePattern = 'div[class=tit3]'
-    replePattern = 'div[class=score_reple]'
-
-    def __init__(self):
-        naverResponse = requests.get(self.naverHomeUrl)
-        naverHtml = naverResponse.text
-        self.naverSoup = BeautifulSoup(naverHtml, self.soupHtmlParser)
-
-        movieResponse = requests.get(self.movieRankingHomeUrl)
-        movieHtml = movieResponse.text
-        self.movieSoup = BeautifulSoup(movieHtml, self.soupHtmlParser)
-
-    def getMovieReple(self, url):
-        movieReples = []
-        repleText = requests.get(self.movieHomeUrl + url).text
-        repleSoup = BeautifulSoup(repleText, self.soupHtmlParser)
-        for tag in repleSoup.select(self.replePattern):
-            rep = tag.select('p').pop(0).text
-            movieReples.append(rep)
-        return movieReples
-
-    def getTitles(self):
-        titles = []
-        for tag in self.movieSoup.select(self.moviePattern):
-            titles.append(tag.text.strip().replace("\n", ""))
-        return titles
-
-    def getAlls(self):
-        movies = []
-        ranking = 1
-        for tag in self.movieSoup.select(self.moviePattern):
-            n = tag.text.strip().replace("\n", "")
-            u = tag.find('a').get('href')
-            t = n, u, ranking, self.getMovieReple(u)                #   튜플
-            print(t)
-            m = Movie(n, u, ranking, self.getMovieReple(u))         #   Movie 클래스
-            movies.append(m)
-            ranking = ranking + 1
-        return movies
-
-
-    def realTimeSearchWord(self):
-        words = []
-        ranking = 1
-        realTimeWords = self.naverSoup.select('ul[class=ah_l] li[class=ah_item] a')
-        for tag in realTimeWords:
-            if tag.get('data-ssl'):
-                relatedWord = requests.get(tag.get('href')).text
-                relatedSoup = BeautifulSoup(relatedWord, self.soupHtmlParser)
-                relatedWords = []
-                for relatedTag in relatedSoup.select('ul[class=_related_keyword_ul] li a'):
-                    relatedWords.append(relatedTag.text)
-                words.append((tag.select('span[class=ah_r]')[0].text, tag.select('span[class=ah_k]')[0].text, tag.get('href'), relatedWords))
-        return words
-
-
-# 클래스 사용
-naver = Naver()
-print(naver.getTitles())
-for b in naver.realTimeSearchWord():
-    print(b)
-
-for b in naver.getAlls():
-    print(b)

src/kr/co/swh/lecture/mathorithm/naverMovieClass_step3.py

@@ -1,26 +0,0 @@
-import schedule
-import time
-import requests
-from bs4 import BeautifulSoup  # BeautifulSoup import
-
-def getTitles():
-    response = requests.get('https://movie.naver.com/movie/sdb/rank/rmovie.nhn')
-    html = response.text
-    soup = BeautifulSoup(html, 'html.parser')  # html.parser를 사용해서 soup에 넣겠다
-    ranking = 1
-    for tag in soup.select('div[class=tit3]'):
-        url = tag.get('href')
-        print(str(ranking) + '위 : ' + tag.text.strip().replace("\n", ""))
-        ranking = ranking + 1
-
-schedule.every(1).seconds.do(getTitles)
-# schedule.every(10).minutes.do(getTitles)
-# schedule.every().hour.do(getTitles)
-# schedule.every().day.at("10:30").do(getTitles)
-# schedule.every(5).to(10).minutes.do(getTitles)
-# schedule.every().monday.do(getTitles)
-# schedule.every().wednesday.at("13:15").do(getTitles)
-
-while True:
-    schedule.run_pending()
-    time.sleep(1)

src/kr/co/swh/lecture/mathorithm/naverMovieClass_step4.py

@@ -1,13 +0,0 @@
-import schedule
-import time
-import requests
-import crawler
-
-# 클래스 사용
-naver = crawler.Naver()
-print(naver.getTitles())
-for b in naver.realTimeSearchWord():
-    print(b)
-
-for b in naver.getAlls():
-    print(b)

src/kr/co/swh/lecture/mathorithm/naverMovieClass_step5.py

@@ -1,21 +0,0 @@
-import schedule
-import time
-import requests
-import crawler
-
-# 클래스 사용
-naver = crawler.Naver()
-def result():
-    print(naver.getTitles())
-    
-schedule.every(1).seconds.do(result)
-# schedule.every(10).minutes.do(getTitles)
-# schedule.every().hour.do(getTitles)
-# schedule.every().day.at("10:30").do(getTitles)
-# schedule.every(5).to(10).minutes.do(getTitles)
-# schedule.every().monday.do(getTitles)
-# schedule.every().wednesday.at("13:15").do(getTitles)
-
-while True:
-    schedule.run_pending()
-    time.sleep(1)

src/kr/co/swh/lecture/mathorithm/naverMovieCrawler.py

@@ -1,70 +0,0 @@
-import requests
-from bs4 import BeautifulSoup  # BeautifulSoup import
-
-class Movie:
-    def __init__(self, n, u, rank, reples):
-        self.name = n
-        self.url = u
-        self.ranking = rank
-        self.reples = reples
-    def __str__(self):
-        return str(self.ranking) + "위\t제목:" + self.name + "\t주소:" + self.url + "\n리플:" + str(self.reples)
-
-class Naver:
-
-    # 기본 정보
-    naverHomeUrl = 'https://www.naver.com/'
-    movieHomeUrl = 'https://movie.naver.com'
-    movieRankingHomeUrl = 'https://movie.naver.com/movie/sdb/rank/rmovie.nhn'
-    soupHtmlParser = 'html.parser'
-
-    # 영화 태그패턴
-    moviePattern = 'div[class=tit3]'
-    replePattern = 'div[class=score_reple]'
-
-    def __init__(self):
-        naverResponse = requests.get(self.naverHomeUrl)
-        naverHtml = naverResponse.text
-        self.naverSoup = BeautifulSoup(naverHtml, self.soupHtmlParser)
-
-        movieResponse = requests.get(self.movieRankingHomeUrl)
-        movieHtml = movieResponse.text
-        self.movieSoup = BeautifulSoup(movieHtml, self.soupHtmlParser)
-
-    def getMovieReple(self, url):
-        movieReples = []
-        repleText = requests.get(self.movieHomeUrl + url).text
-        repleSoup = BeautifulSoup(repleText, self.soupHtmlParser)
-        for tag in repleSoup.select(self.replePattern):
-            rep = tag.select('p').pop(0).text
-            movieReples.append(rep)
-        return movieReples
-
-    def getTitles(self):
-        titles = []
-        for tag in self.movieSoup.select(self.moviePattern):
-            titles.append(tag.text.strip().replace("\n", ""))
-        return titles
-
-    def getAlls(self):
-        movies = []
-        ranking = 1
-        for tag in self.movieSoup.select(self.moviePattern):
-            n = tag.text.strip().replace("\n", "")
-            u = tag.find('a').get('href')
-            t = n, u, ranking, self.getMovieReple(u)                #   튜플
-            print(t)
-            m = Movie(n, u, ranking, self.getMovieReple(u))         #   Movie 클래스
-            movies.append(m)
-            ranking = ranking + 1
-        return movies
-
-
-
-
-# 클래스 사용
-naver = Naver()
-print(naver.getTitles())
-
-for b in naver.getAlls():
-    print(b)

src/kr/co/swh/lecture/mathorithm/naverMovieReple.py

@@ -1,21 +0,0 @@
-import requests
-from bs4 import BeautifulSoup  # BeautifulSoup import
-
-def reple(url):
-    repleText = requests.get('https://movie.naver.com' + url).text
-    soup = BeautifulSoup(repleText, 'html.parser')
-    print('[리플]')
-    for tag in soup.select('div[class=score_reple]'):
-        rep = tag.select('p').pop(0).text
-        print(rep)
-
-response = requests.get('https://movie.naver.com/movie/sdb/rank/rmovie.nhn')
-html = response.text
-soup = BeautifulSoup(html, 'html.parser')  # html.parser를 사용해서 soup에 넣겠다
-ranking = 1
-for tag in soup.select('div[class=tit3]'):
-    url = tag.find('a').get('href')
-    print(url)
-    print("\n" + str(ranking) + '위 : ' + tag.text.strip())
-    reple(url)
-    ranking = ranking + 1

src/kr/co/swh/lecture/mathorithm/naverMovieTitle.py

@@ -1,11 +0,0 @@
-import requests
-from bs4 import BeautifulSoup  # BeautifulSoup import
-
-response = requests.get('https://movie.naver.com/movie/sdb/rank/rmovie.nhn')
-html = response.text
-soup = BeautifulSoup(html, 'html.parser')  # html.parser를 사용해서 soup에 넣겠다
-ranking = 1
-for tag in soup.select('div[class=tit3]'):
-    url = tag.get('href')
-    print("\n" + str(ranking) + '위 : ' + tag.text.strip())
-    ranking = ranking + 1