from collect import crawler
from analysis import analizer
from visualize import visualizer
pagename = "chosun"
from_date = "2018-05-22"
to_date = "2018-05-24"
if __name__ == "__main__":
# #수집
# postList = crawler.fb_get_post_list(pagename,from_date,to_date)
# print(postList)
#분석
dataString = analizer.json_to_str("D:/JavaStudy/imformation/chosun.json",
"message_str")
count_data = analizer.count_wordfreq(dataString)
print(count_data)
dictword = dict(count_data.most_common(20))
# 그래프
visualizer.show_graph_bar(dictword, pagename)
# 워드클라우드
visualizer.wordcloud(dictword, pagename)
from collect import crawler
from analysis import analizer
from visualize import visualizer
pagename = "jtbcnews"
from_date = "2018-05-01"
to_date = "2018-05-24"
if __name__ == "__main__":
# postList = crawler.fb_get_post_list(pagename, from_date, to_date)
# print(postList)
dataString = analizer.json_to_str("D:/fb/jtbcnews.json", 'comments_str')
count_data = analizer.count_wordfreq(dataString)
print(count_data.most_common(20)) # most_common(20) 상위 20위까지만 표시하게끔 해줌
# dictWords = dict(count_data.most_common(20))
# visualizer.show_graph_bar(dictWords, pagename)
dictWords = dict(count_data.most_common(20))
visualizer.wordcloud(dictWords, pagename)
from collect import crawler as cr
from analysis import analizer as an
from visualize import visualizer as vi
import simplejson
pagename = "TheHeraldBusiness"
from_date = "2018-04-01"
to_date = "2018-05-29"
if __name__ == "__main__":
#수집
postList = cr.fb_get_post_list(pagename, from_date, to_date)
print(postList)
#분석
dataString = an.json_to_str(
"/Users/WOOSEUNGMI/Desktop/2018/javaStudy/facebook/TheHeraldBusiness.json",
"message_str") # 파일경로+경로명, key값(dic의)
count_data = an.count_wordfreq(dataString)
print(count_data) #어떤 단어를 몇번 이용했는지 출력
#리스트를 딕셔너리 형태로 변경
dictWord = dict(count_data.most_common(20)) #단어 상위 몇개만 지정
#그래프
vi.show_graph_bar(dictWord, pagename) #폰트네임알아내기
# 워드크라우드
vi.wordcloud(dictWord, pagename)