]> code.communitydata.science - covid19.git/blobdiff - wikipedia/scripts/fetch_enwiki_daily_views.py
Merge pull request #20 from makoshark/master
[covid19.git] / wikipedia / scripts / fetch_enwiki_daily_views.py
index c250bfe94aa23106bc900556b93e142860213532..9f147e07a30cc20e78b27ec1afb71c64be582b1e 100755 (executable)
 ###############################################################################
 
 import sys
 ###############################################################################
 
 import sys
-import subprocess
 import requests
 import argparse
 import json
 import time
 import os.path
 import requests
 import argparse
 import json
 import time
 import os.path
-import argparse
 import datetime
 import logging
 from csv import DictWriter
 import datetime
 import logging
 from csv import DictWriter
+import digobs
 #import feather #TBD
 
 def parse_args():
 #import feather #TBD
 
 def parse_args():
-
     parser = argparse.ArgumentParser(description='Call the views API to collect Wikipedia view 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 = argparse.ArgumentParser(description='Call the views API to collect Wikipedia view 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('-L', '--logging_level', help='Logging level. Options are debug, info, warning, error, critical. Default: info.', default='info', type=digobs.get_loglevel), 
     parser.add_argument('-W', '--logging_destination', help='Logging destination file. (default: standard error)', type=str), 
     args = parser.parse_args()
     return(args)
     parser.add_argument('-W', '--logging_destination', help='Logging destination file. (default: standard error)', type=str), 
     args = parser.parse_args()
     return(args)
@@ -42,45 +40,29 @@ def main():
 
     #handle -d
     if args.query_date:
 
     #handle -d
     if args.query_date:
-        queryDate = args.query_date
+        query_date = args.query_date
     else:
         yesterday = datetime.datetime.today() - datetime.timedelta(days=1)
     else:
         yesterday = datetime.datetime.today() - datetime.timedelta(days=1)
-        queryDate = yesterday.strftime("%Y%m%d")
-
-    queryDate = queryDate + "00" #requires specifying hours
-
-    #handle -L
-    loglevel_mapping = { 'debug' : logging.DEBUG,
-                         'info' : logging.INFO,
-                         'warning' : logging.WARNING,
-                         'error' : logging.ERROR,
-                         'critical' : logging.CRITICAL }
-
-    if args.logging_level in loglevel_mapping:
-        loglevel = loglevel_mapping[args.logging_level]
-    else:
-        print("Choose a valid log level: debug, info, warning, error, or critical") 
-        exit
+        query_date = yesterday.strftime("%Y%m%d")
 
     #handle -W
     if args.logging_destination:
 
     #handle -W
     if args.logging_destination:
-        logging.basicConfig(filename=args.logging_destination, filemode='a', level=loglevel)
+        logging.basicConfig(filename=args.logging_destination, filemode='a', level=args.logging_level)
     else:
     else:
-        logging.basicConfig(level=loglevel)
+        logging.basicConfig(level=args.logging_level)
 
 
-    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_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"Starting run at {export_time}")
-    logging.info(f"Last commit: {export_git_hash}")
+    logging.info(f"Last commit: {digobs.git_hash()}")
 
     #1 Load up the list of article names
 
     #1 Load up the list of article names
-    j_outfilename = os.path.join(outputPath, f"digobs_covid19-wikipedia-enwiki_dailyviews-{queryDate}.json")
-    t_outfilename = os.path.join(outputPath, f"digobs_covid19-wikipedia-enwiki_dailyviews-{queryDate}.tsv")
+    j_outfilename = os.path.join(outputPath, f"digobs_covid19-wikipedia-enwiki_dailyviews-{query_date}.json")
+    t_outfilename = os.path.join(outputPath, f"digobs_covid19-wikipedia-enwiki_dailyviews-{query_date}.tsv")
 
     with open(articleFile, 'r') as infile:
 
     with open(articleFile, 'r') as infile:
-        articleList = list(infile)
+        articleList = list(map(str.strip, infile))
 
     success = 0 #for logging how many work/fail
     failure = 0 
 
     success = 0 #for logging how many work/fail
     failure = 0 
@@ -91,8 +73,7 @@ def main():
 
         #2 Repeatedly call the API with that list of names
         for a in articleList:
 
         #2 Repeatedly call the API with that list of names
         for a in articleList:
-            a = a.strip("\"\n") #destringify
-            url= f"https://wikimedia.org/api/rest_v1/metrics/pageviews/per-article/en.wikipedia/all-access/all-agents/{a}/daily/{queryDate}/{queryDate}"
+            url= f"https://wikimedia.org/api/rest_v1/metrics/pageviews/per-article/en.wikipedia/all-access/all-agents/{a}/daily/{query_date}00/{query_date}00"
 
             response = requests.get(url)
             if response.ok:
 
             response = requests.get(url)
             if response.ok:
@@ -101,6 +82,7 @@ def main():
             else:
                 failure = failure + 1
                 logging.warning(f"Failure: {response.status_code} from {url}")
             else:
                 failure = failure + 1
                 logging.warning(f"Failure: {response.status_code} from {url}")
+                continue
 
             # start writing the CSV File if it doesn't exist yet
             try:
 
             # start writing the CSV File if it doesn't exist yet
             try:
@@ -117,7 +99,7 @@ def main():
             # write out of the csv file
             dw.writerow(jd)
 
             # write out of the csv file
             dw.writerow(jd)
 
-    # f_Out = outputPath + "dailyviews" + queryDate + ".feather"
+    # f_Out = outputPath + "dailyviews" + query_date + ".feather"
     # read the json back in and make a feather file? 
     logging.debug(f"Run complete at {datetime.datetime.now()}")
     logging.info(f"Processed {success} successful URLs and {failure} failures.")
     # read the json back in and make a feather file? 
     logging.debug(f"Run complete at {datetime.datetime.now()}")
     logging.info(f"Processed {success} successful URLs and {failure} failures.")

Community Data Science Collective || Want to submit a patch?