if "" in img_url_res_checked:
img_url_res_checked.remove("")
# print(img_url_res_checked, len(img_url_res_checked))
return img_url_res_checked
def output_to_file(results):
with open("../poem_img_url_test.txt", "a") as file_object:
for item in results:
file_object.write(item)
file_object.write("\n")
if __name__ == '__main__':
translator = Translator()
poem_file = formator.input_from_file("../poem_with_keyword.txt")
count = 0
for line in poem_file:
poem, keyword = poem_keyword_split(line)
cn_text = keyword_format(keyword)
en_text = translate(translator, cn_text, "zh-cn", "en")
uns_url_cn = generate_url(cn_text, "unsplash")
uns_url_en = generate_url(en_text, "unsplash")
uns_cn_html = unsplash_get(uns_url_cn)
uns_en_html = unsplash_get(uns_url_en)
img_url_to_display_cn = parser(uns_cn_html)
img_url_to_display_en = parser(uns_en_html)
img_url = img_url_to_display_cn + img_url_to_display_en
text_rank_unzip_list = list(zip(*text_rank))
text_rank_word = text_rank_unzip_list[0]
text_rank_score = text_rank_unzip_list[1]
return tf_idf_word, tf_idf_score, text_rank_word, text_rank_score
def output_to_file(results):
with open("poem_with_keyword.txt", "a") as file_object:
for item in results:
file_object.write(item)
file_object.write("\n")
if __name__ == '__main__':
jieba.enable_parallel(4)
poem_file = formator.input_from_file("poem_new.txt")
for poem in poem_file:
tf_idf_word, tf_idf_score, text_rank_word, text_rank_score = calculate_scores(
)
repeat_words = list(
set.intersection(set(tf_idf_word), set(text_rank_word)))
words = tf_idf_word + text_rank_word
scores = tf_idf_score + text_rank_score
final_words = list(set(words) - set(repeat_words))
final_lst = []
# not repeat words
for final_word in final_words:
index = words.index(final_word)
score = scores[index]
from src import formator
def output_to_file(results):
with open("../ready_2_db_v33.txt", "a", encoding="UTF-8") as file_object:
for item in results:
file_object.write(item)
file_object.write("\n")
if __name__ == '__main__':
url_file = formator.input_from_file("../ready_2_db_v3.txt")
count = 120570
for line in url_file:
# if count == 120570:
# count += 1
# output_to_file(line.strip())
# continue
# else:
infos = (str(line).strip()).split("\t")
# print(infos[0])
number = "\"" + str(count) + "\""
print(number)
infos[0] = number
res = "\t".join(infos)
# print(res)
output_to_file(res)
count += 1
from src import formator
def output_to_file(results):
with open("../ready_2_db_v3.txt", "a", encoding="UTF-8") as file_object:
for item in results:
file_object.write(item)
file_object.write("\n")
if __name__ == '__main__':
url_file = formator.input_from_file("../poem_img_url_3.txt")
count = 0
temp = []
for line in url_file:
infos = (str(line).strip()).split("@")
if count % 2 != 0:
del infos[0]
number = int((count + 1) / 2)
temp.append(infos[0])
temp.append("")
temp.append(str(number))
res = "\"" + "\"\t\"".join(temp) + "\""
print(res)
output_to_file(res)
temp = []
else:
number = int((count / 2) + 1)
temp = [str(number), infos[0], infos[1]]
count += 1