[MNT] - Fix check_articles

lisc/collect/words.py

@@ -241,7 +241,7 @@ def get_article_info(arts, article):
 
     # Extract reference list, if present
     #   Otherwise, tags within this can interfere with collected data
-    refs = extract_tag(article, 'ReferenceList')
+    refs = extract_tag(article, 'ReferenceList', 'all')
 
     arts.add_data('ids', process_ids(get_info(article, 'ArticleId', 'all'), 'pubmed'))
     arts.add_data('titles', get_info(article, 'ArticleTitle', 'str'))

lisc/objects/words.py

@@ -143,15 +143,22 @@ def check_data(self):
             print("\t{:{twd}} \t\t  {}".format(label, data.n_articles, twd=twd))
 
 
-    def check_articles(self):
-        """Prints out the articles collected for each term."""
+    def check_articles(self, header=None):
+        """Print out a brief description of the articles collected for each term."""
 
         for results in self.results:
-            print('\nLabel: {}\n'.format(results.label))
+            print('\nLabel: {} ({} articles)\n'.format(results.label, results.n_articles))
             for cres in results:
-                author = cres['authors'][0][0] + (' et al' if len(cres['authors']) > 1 else '')
-                doi = 'https://dx.doi.org/' + cres['doi'] if cres['doi'] else ''
+                if cres['authors']:
+                    author = cres['authors'][0][0] + (' et al' if len(cres['authors']) > 1 else '')
+                else:
+                    author = 'unknown author'
+                if cres['doi']:
+                    doi = 'https://dx.doi.org/' + cres['doi']
+                else:
+                    doi = ''
                 print(author + ',', str(cres['year']) + ':', cres['title'], doi)
+        print('\n')
 
 
     def drop_data(self, n_articles):

lisc/version.py

@@ -1 +1 @@
-__version__ = '0.5.0-dev'
+__version__ = '0.4.1-dev'

tutorials/plot_01-WordsCollection.py

@@ -76,7 +76,12 @@
 
 ###################################################################################################
 
-# Check the collected words data
+# Check the number of collected articles
+words.check_data()
+
+###################################################################################################
+
+# Check the collected words results
 print(words.results)
 
 ###################################################################################################

tutorials/plot_02-WordsAnalysis.py

@@ -84,6 +84,8 @@
 #
 # The `results` attribute contains a list of :class:`~.Articles` objects, one for each term.
 #
+# Note that the reloaded data is the raw data from the data collection.
+#
 
 ###################################################################################################
 
@@ -92,7 +94,18 @@
 
 ###################################################################################################
 #
-# Note that the reloaded data is the raw data from the data collection.
+# The :meth:`~.Words.check_articles` method can be used to print out a summary of the articles
+# that have been collected under each search term.
+#
+
+###################################################################################################
+
+# Check the collected articles
+words.check_articles()
+
+###################################################################################################
+# Processing Collected Data
+# ~~~~~~~~~~~~~~~~~~~~~~~~~
 #
 # The :meth:`~.Words.process_articles` method can be used to do some preprocessing on the
 # collected data.

tutorials/plot_06-CollectAcrossTime.py

@@ -219,11 +219,10 @@
 
 ###################################################################################################
 
-# Check the titles found across different time ranges
+# Check the articles found across different time ranges
 for time_period, results in word_results.items():
-    print(str(time_period) + 's:')
-    for res_title in results.results[0].titles:
-        print('\t', res_title)
+    print('---- {} ----'.format(time_period))
+    results.check_articles()
 
 ###################################################################################################
 #