From: Benjamin Mako Hill Date: Wed, 1 Apr 2020 22:16:34 +0000 (-0500) Subject: changes in response to code review by nate X-Git-Url: https://code.communitydata.science/covid19.git/commitdiff_plain/070d23f71854b43c22f11d3e26bceca8b2a1de3c changes in response to code review by nate - moved some common functions into files - other smaller changes --- diff --git a/wikipedia/scripts/digobs.py b/wikipedia/scripts/digobs.py new file mode 100644 index 0000000..0bce250 --- /dev/null +++ b/wikipedia/scripts/digobs.py @@ -0,0 +1,27 @@ +#!/usr/bin/env python3 + +import sys +import subprocess +import logging + +def git_hash(short=False): + if short: + return subprocess.check_output(['git', 'rev-parse', '--short', 'HEAD']).decode().strip() + else: + subprocess.check_output(['git', 'rev-parse', 'HEAD']).decode().strip() + +def get_loglevel(arg_loglevel): + loglevel_mapping = { 'debug' : logging.DEBUG, + 'info' : logging.INFO, + 'warning' : logging.WARNING, + 'error' : logging.ERROR, + 'critical' : logging.CRITICAL } + + if arg_loglevel in loglevel_mapping: + loglevel = loglevel_mapping[arg_loglevel] + return loglevel + else: + print("Choose a valid log level: debug, info, warning, error, or critical", file=sys.stderr) + return logging.INFO + + diff --git a/wikipedia/scripts/fetch_enwiki_daily_views.py b/wikipedia/scripts/fetch_enwiki_daily_views.py index f766ed8..7015a3b 100755 --- a/wikipedia/scripts/fetch_enwiki_daily_views.py +++ b/wikipedia/scripts/fetch_enwiki_daily_views.py @@ -10,16 +10,15 @@ ############################################################################### import sys -import subprocess import requests import argparse import json import time import os.path -import argparse import datetime import logging from csv import DictWriter +import digobs #import feather #TBD def parse_args(): @@ -47,17 +46,7 @@ def main(): query_date = yesterday.strftime("%Y%m%d") #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 + loglevel = digobs.get_loglevel(args.logging_level) #handle -W if args.logging_destination: @@ -65,20 +54,18 @@ def main(): else: logging.basicConfig(level=loglevel) - 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}") + logging.info(f"Last commit: {digobs.git_hash()}") #1 Load up the list of article names j_outfilename = os.path.join(outputPath, f"digobs_covid19-wikipedia-enwiki_dailyviews-{export_date}.json") t_outfilename = os.path.join(outputPath, f"digobs_covid19-wikipedia-enwiki_dailyviews-{export_date}.tsv") 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 @@ -89,7 +76,6 @@ def main(): #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/{query_date}00/{query_date}00" response = requests.get(url) diff --git a/wikipedia/scripts/fetch_enwiki_revisions.py b/wikipedia/scripts/fetch_enwiki_revisions.py index 6a3563f..2c0ef7a 100755 --- a/wikipedia/scripts/fetch_enwiki_revisions.py +++ b/wikipedia/scripts/fetch_enwiki_revisions.py @@ -13,12 +13,12 @@ import argparse import logging import os.path import json -import subprocess import datetime from requests import Request from csv import DictWriter from mw import api +import digobs def parse_args(): @@ -38,17 +38,7 @@ def main(): article_filename = args.article_file #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 + loglevel = digobs.get_loglevel(args.logging_level) #handle -W if args.logging_destination: @@ -56,13 +46,11 @@ def main(): else: logging.basicConfig(level=loglevel) - 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}") + logging.info(f"Last commit: {digobs.git_hash()}") 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") @@ -88,7 +76,7 @@ def main(): # load the list of articles with open(article_filename, 'r') as infile: - article_list = [art.strip() for art in list(infile)] + article_list= list(map(str.strip, infile)) def get_revisions_for_page(title): return api_session.revisions.query(properties=rv_props.values(), @@ -104,7 +92,7 @@ def main(): # add special export fields tsv_fields = tsv_fields + ['anon', 'minor', 'url', 'export_timestamp', 'export_commit'] - export_info = { 'git_commit' : export_git_hash, + export_info = { 'git_commit' : digobs.git_hash(), 'timestamp' : export_time } with open(json_output_filename, 'w') as json_output, \ @@ -155,7 +143,7 @@ def main(): 'oldid' : rev['revid']}).prepare().url rev['export_timestamp'] = export_time - rev['export_commit'] = export_git_short_hash + rev['export_commit'] = digobs.git_hash(short=True) tsv_writer.writerow({k: rev[k] for k in tsv_fields})