convert to dict before csv

1 files changed, 10 insertions, 11 deletions

diff --git a/megapixels/commands/datasets/citations_to_csv.py b/megapixels/commands/datasets/citations_to_csv.py
index cda879aa..c6a04bd4 100644
--- a/megapixels/commands/datasets/citations_to_csv.py
+++ b/megapixels/commands/datasets/citations_to_csv.py
@@ -49,13 +49,8 @@ def cli(ctx, opt_fp_in, opt_dir_out):
     papers += papers_main
     papers_citations = get_citations(dataset_key, dataset_name, json_data)
     papers += papers_citations
-    #papers = [p.to_dict() for p in papers]
-    for p in papers:
-      try:
-        p.to_dict()
-      except:
-        print(p)
-
+    papers = [p.to_dict() for p in papers]
+    
     # save
     if not opt_dir_out:
       # save to same directory replacing ext
@@ -81,12 +76,14 @@ def get_citations(dataset_key, dataset_name, json_data):
     addresses = p.get('addresses', '')
     if addresses:
       for a in addresses:
+        pdf_url = '' if not p['pdf'] else p['pdf'][0]
         paper = Paper(dataset_key, dataset_name, p['id'], p['title'], d_type,
-                  year,  p['pdf'],
+                  year, pdf_url,
                   a['name'], a['type'], a['lat'], a['lng'], a['country'])  
         papers.append(paper)
     else:
-      paper = Paper(p['key'], p['name'], d['id'], p['title'], 'main', year, p['pdf'])
+      pdf_url = '' if not p['pdf'] else p['pdf'][0]
+      paper = Paper(p['key'], p['name'], d['id'], p['title'], 'main', year, pdf_url)
       papers.append(paper)
   return papers
 
@@ -101,11 +98,13 @@ def get_orig_paper(json_data):
     for a in addresses:
       if type(a) == str or a is None:
         continue
+      pdf_url = '' if not p['pdf'] else p['pdf'][0]
       paper = Paper(p['key'], p['name'], p['paper_id'], p['title'], d_type, year,
-                  p['pdf'],
+                  pdf_url,
                   a['name'], a['type'], a['lat'], a['lng'], a['country'])
       papers.append(paper)
   else:
-    paper = Paper(p['key'], p['name'], p['paper_id'], p['title'], d_type, year, p['pdf'])
+    pdf_url = '' if not p['pdf'] else p['pdf'][0]
+    paper = Paper(p['key'], p['name'], p['paper_id'], p['title'], d_type, year, pdf_url)
     papers.append(paper)
   return papers