Merge branch 'master' of github.com:makoshark/COVID-19_Digital_Observatory

diff --combined wikipedia/scripts/fetch_enwiki_revisions.py
index e8f177db93aa6fb950a3e5a3c568e81a05469e19,fdd4ad536a3d720c5afbdd52fe9b2d790fd0b498..44528e8757e04141b1af2e67740fbe316362f455
--- 1/wikipedia/scripts/fetch_enwiki_revisions.py
--- 2/wikipedia/scripts/fetch_enwiki_revisions.py
+++ b/wikipedia/scripts/fetch_enwiki_revisions.py
@@@ -26,6 -26,7 +26,6 @@@ def parse_args()
      parser = argparse.ArgumentParser(description='Call the views API to collect Wikipedia revision data.')
      parser.add_argument('-o', '--output_folder', help='Where to save output', default="wikipedia/data", type=str)
      parser.add_argument('-i', '--article_file', help='File listing article names', default="wikipedia/resources/enwp_wikiproject_covid19_articles.txt", type=str)
 -    parser.add_argument('-d', '--query_date', help='Date if not yesterday, in YYYYMMDD format.', type=str)
      parser.add_argument('-L', '--logging_level', help='Logging level. Options are debug, info, warning, error, critical. Default: info.', default='info', type=str), 
      parser.add_argument('-W', '--logging_destination', help='Logging destination file. (default: standard error)', type=str), 
      args = parser.parse_args()
@@@ -36,6 -37,14 +36,6 @@@ def main()
  
      output_path = args.output_folder
      article_filename = args.article_file
 -    #handle -d
 -    if args.query_date:
 -        query_date = args.query_date
 -    else:
 -        yesterday = datetime.datetime.today() - datetime.timedelta(days=1)
 -        query_date = yesterday.strftime("%Y%m%d")
 -
 -    query_data  = query_date + "00" #requires specifying hours
  
      #handle -L
      loglevel_mapping = { 'debug' : logging.DEBUG,
@@@ -59,13 -68,12 +59,13 @@@
      export_git_hash = subprocess.check_output(['git', 'rev-parse', 'HEAD']).decode().strip()
      export_git_short_hash = subprocess.check_output(['git', 'rev-parse', '--short', 'HEAD']).decode().strip()
      export_time = str(datetime.datetime.now())
 +    export_date = datetime.datetime.today().strftime("%Y%m%d")
  
      logging.info(f"Starting run at {export_time}")
      logging.info(f"Last commit: {export_git_hash}")
  
 -    json_output_filename = os.path.join(output_path, f"digobs_covid19-wikipedia-enwiki_revisions-{query_date}.json")
 -    tsv_output_filename =  os.path.join(output_path, f"digobs_covid19-wikipedia-enwiki_revisions-{query_data}.tsv")
 +    json_output_filename = os.path.join(output_path, f"digobs_covid19-wikipedia-enwiki_revisions-{export_date}.json")
 +    tsv_output_filename =  os.path.join(output_path, f"digobs_covid19-wikipedia-enwiki_revisions-{export_date}.tsv")
      
      api_session = api.Session("https://en.wikipedia.org/w/api.php")
  
@@@ -113,7 -121,7 +113,7 @@@
          tsv_writer.writeheader()
  
          for article in article_list:
-             logging.info(f"pulling revisiosn for: {article}")
+             logging.info(f"pulling revisions for: {article}")
              for rev in get_revisions_for_page(article):
                  logging.debug(f"processing raw revision: {rev}")