Update app.py

app.py

@@ -13,6 +13,8 @@ from newspaper import Article
 from newspaper import fulltext
 import requests
 import itertools
+import os
+
 
 from nltk.tokenize import word_tokenize
 from sentence_transformers import SentenceTransformer
@@ -53,7 +55,7 @@ nlp = en_core_sci_lg.load()
 sp = en_core_sci_lg.load()
 all_stopwords = sp.Defaults.stop_words
 
-
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
 
 def remove_stopwords(sen):
     sen_new = " ".join([i for i in sen if i not in stop_words])
@@ -109,7 +111,7 @@ def keyphrase_generator(article_link, model_1, model_2, max_num_keywords, model_
        count_dict[l]=0
   for sent, score in count_dict.items():
     score_list.append(score)
-  clean_sentences_new = pd.Series(corpus).str.replace("[^a-zA-Z]", " ").tolist()
+  clean_sentences_new = pd.Series(corpus).str.replace("[^a-zA-Z]", " ", regex = True).tolist()
   corpus_embeddings = model_1.encode(clean_sentences_new)
   sim_mat = np.zeros([len(clean_sentences_new), len(clean_sentences_new)])
   for i in range(len(clean_sentences_new)):
@@ -212,8 +214,7 @@ def keyphrase_generator(article_link, model_1, model_2, max_num_keywords, model_
   ncbi_url='https://eutils.ncbi.nlm.nih.gov/entrez/eutils/'
 
   last_url='esearch.fcgi?db=pubmed'+'&term='+f_1
-  search_rettype = '&rettype=json'
-  overall_url=ncbi_url+last_url+search_rettype+'&sort=relevance'
+  overall_url=ncbi_url+last_url+'&rettype=json'+'&sort=relevance'
   pubmed_search_request = requests.get(overall_url)
   
   root = ET.fromstring(pubmed_search_request.text)
@@ -225,11 +226,7 @@ def keyphrase_generator(article_link, model_1, model_2, max_num_keywords, model_
   all_search_ids = ','.join(search_id_list)
   fetch_url='efetch.fcgi?db=pubmed'
   search_id='&id='+all_search_ids
-  ret_type='&rettype=text'
-  ret_mode='&retmode=xml'
-  ret_max='&retmax=500'
-  ret_sort='&sort=relevance'
-  return_url=ncbi_url+fetch_url+search_id+ret_type+ret_mode+ret_max+ret_sort
+  return_url=ncbi_url+fetch_url+search_id+'&rettype=text'+'&retmode=xml'+'&retmax=500'+'&sort=relevance'
   pubmed_abstract_request = requests.get(return_url)
   root_1 = ET.fromstring(pubmed_abstract_request.text)
   article_title = root_1.findall('.//ArticleTitle')