def add_books_by_title(self, bookdate) :
titlelist = self.get_orititle_list()
f = open("Naver Book Search Log_{} {}h{}m{}s.txt".
format(self.curt.date(), self.curt.hour, self.curt.minute, self.curt.second), "w", encoding='utf-8')
self.searcher.f = f
for idx in range(len(bookdate)) :
btlist = bookdate[idx][1]
dt = bookdate[idx][0]
for bt in btlist :
if bt in titlelist :
print('{}가 갱신됨'.format(bt))
bidx = titlelist.index(bt)
b = book_data.BookData()
self.searcher.book = b
self.searcher.from_title(bt)
self.book_list[bidx] = b
dtitle = [x.ori_title for x in self.date_to_book[dt]]
if bt in dtitle :
bdidx = dtitle.index(bt)
self.date_to_book[dt][bdidx] = self.book_list[bidx]
else :
print('왜 {}는 책 리스트에는 있는데 {} 출판 책 리스트에는 없는거지?'.format(bt, dt))
self.date_to_book[dt].append(self.book_list[bidx])
else :
b = book_data.BookData()
self.searcher.book = b
self.searcher.from_title(bt)
self.add_book(b, dt)
self.searcher.search_finished()
def import_data(self) :
self.book_list = list()
self.date_to_book = defaultdict(list)
book_path = pathlib.Path('book_data.json')
if book_path.exists() :
temp = book_path.read_text(encoding='utf-16')
book_list = json.loads(temp, encoding='utf-16', strict=False)
for book in book_list :
new_book = book_data.BookData()
new_book.from_json_dict(book)
self.book_list.append(new_book)
book_path = pathlib.Path('date_to_book.json')
if book_path.exists() :
temp = book_path.read_text(encoding='utf-16')
book_dict = json.loads(temp, encoding='utf-16', strict=False)
for key in book_dict.keys():
new_list = list()
book_list = book_dict[key]
for book in book_list :
new_book = book_data.BookData()
new_book.from_json_dict(book)
new_list.append(new_book)
self.date_to_book[key] = new_list
'''
def add_by_tl_td(self, title_list, title_to_date):
self.date_to_book = defaultdict(list)
for idx in range(len(title_list)):
title = title_list[idx]
print("{}/{}".format(idx, len(title_list)))
book = book_data.BookData()
self.searcher.book = book
self.searcher.from_title(title)
self.book_list.append(book)
self.date_to_book[title_to_date[book.ori_title]].append(book)
self.searcher.search_finished()
def add_by_tl_td(self, title_list, title_to_date) :
self.date_to_book = defaultdict(list)
f = open("Naver Book Search Log_{} {}h{}m{}s.txt".
format(self.curt.date(), self.curt.hour, self.curt.minute, self.curt.second), "w", encoding='utf-8')
self.searcher.f = f
for idx in range(len(title_list)) :
title = title_list[idx]
print("{}/{}".format(idx, len(title_list)))
book = book_data.BookData()
self.searcher.book = book
self.searcher.from_title(title)
self.book_list.append(book)
self.date_to_book[title_to_date[book.ori_title]].append(book)
self.searcher.search_finished()
def crawl_search_sample():
book = book_data.BookData()
sr = exins.get_instance().get_searcher_naver_instance()
sr.book = book
sr.from_title('시원찮은 그녀를 위한 육성방법 GS 2권')
ax.set_xlim(xmin=0.0, xmax=1.0)
ax.set_ylim(ymin=0.0, ymax=1.0)
ax.scatter([x[1] for x in ap_xy], [x[2] for x in ap_xy])
plt.show()
if __name__ == "__main__":
training_set = []
tra_path = pathlib.Path("../training_set.json")
if tra_path.exists():
temp = tra_path.read_text(encoding='utf-16')
book_dict = json.loads(temp, strict=False)
for dic in book_dict:
new_book = book_data.BookData()
new_book.from_json_dict(dic["book"])
dic["book"] = new_book
training_set = book_dict
t_json = []
for t in training_set:
data = t["book"].title
pos = json_file.list_to_json([{
"segment": n,
"tag": t
} for n, t in nlp_module.pos_Twitter(data)], json_file.data_to_json)
t_json.append({"string": data, "pos": pos})
data = t["book"].description