Changeset 35018

Timestamp:

2021-04-04T20:48:30+12:00 (3 years ago)

Author:

davidb

Message:

Code tidy up

Location:

main/trunk/model-sites-dev/eurovision-lod/collect/eurovision/prepare/errata-categories

Files:

• esc-wikipedia-download-and-detect-missing-cat-entries.py (modified) (4 diffs)
• esc-wikipedia-download-and-process-votes.py (modified) (1 diff)

main/trunk/model-sites-dev/eurovision-lod/collect/eurovision/prepare/errata-categories/esc-wikipedia-download-and-detect-missing-cat-entries.py

@@ -1 +1 @@
 #!/usr/bin/env python
 
-# Work out where the gaps are in the Wikipedia ESC Category pages that are meant to
+# Works out where the gaps are in the Wikipedia ESC Category pages that are meant to
 # list all the countries that competed in a given year
 
@@ -8 +8 @@
 import os
 import re
-# import shutil
 
 import argparse
@@ -104 +103 @@
     util.write_text_file_from_template(sparql_values_template_filename,"**missing-country-year-uris**",missing_uri_lines_text,sparql_values_output_filename)
 
-#    problem_category_in_year_filename = "../problem-lod-lists/dbpedia-problem-category-in-year.sparql"    
-#    shutil.copyfile(sparql_values_output_filename,problem_category_in_year_filename)
-                    
-
-
     
 if __name__ == "__main__":
@@ -122 +116 @@
     
     # 2. Download Wikipedia ESC *Category* pages (listscountries in a given year)
-    #    (This appears to be at times incomplete, however is the hook used in the SPARQL query)
+    #    (This appears to be at times incomplete. As it the Category pages that
+    #     are used as the hook used in the SPARQL query produce the list of all ESC entries
+    #     using this approach alone will lead to countries being overloooked)
     
     # 3. Extract list of countries from (1)

main/trunk/model-sites-dev/eurovision-lod/collect/eurovision/prepare/errata-categories/esc-wikipedia-download-and-process-votes.py

@@ -2 +2 @@
 
 ### TODO
+#
 ### Grab image for competition year out of infobox???
+#
+### If hyperlink in table => add in Wikipedia Song URL mapped to DBPedia
+#
+
 
 import json