updatesucesspara

huixiangdou/service/findarticles.py

@@ -60,7 +60,7 @@ class ArticleRetrieval:
         if not os.path.exists(self.repo_dir):
             os.makedirs(self.repo_dir)
         print(f"Saving articles to {self.repo_dir}.")
-        success = 0
+        self.success = 0
         for id in tqdm(self.pmc_ids, desc="Fetching full texts", unit="article"):
             base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi"
             params = {
@@ -71,19 +71,20 @@ class ArticleRetrieval:
             }
             response = requests.get(base_url, params=params)
             full_text = self._clean_xml(response.text)
-            if full_text == '':
+            if full_text.strip() == '':
                 continue
             else:
+                logger.info(full_text[:1000])
                 with open(os.path.join(self.repo_dir,f'PMC{id}.txt'), 'w') as f:
                     f.write(full_text)
-                success += 1
+                self.success += 1
 
     def save_config(self):
         config = {
             'keywords': self.keywords,
             'repo_dir': self.repo_dir,
             'pmc_ids': self.pmc_ids,
-            'len': success,
+            'len': self.success,
             'retmax': self.retmax
         }
         with open(os.path.join(self.repo_dir, 'config.json'), 'w') as f: