3 ###############################################################################
5 # This script assumes the presence of the COVID-19 repo.
7 # It (1) reads in the article list and then (2) calls the Wikimedia API to
8 # fetch view information for each article. Output is to a (3) TSV file.
11 ###############################################################################
14 #1 Load up the list of article names
16 #2 Repeatedly call the API with that list of names
18 #3 Save results as a TSV
32 parser = argparse.ArgumentParser(description='Call the views API repeatedly.')
33 parser.add_argument('-o', '--output_folder', help='Where to save output', default="", type=str)
34 parser.add_argument('-i', '--article_file', help='File listing article names', default="../resources/articles.txt", type=str)
35 parser.add_argument('-d', '--query_date', help='Date if not yesterday, in YYYYMMDD format please.', type=str)
36 args = parser.parse_args()
45 outputPath = args.output_folder
46 articleFile = args.article_file
48 queryDate = args.query_date
50 queryDate = datetime.datetime.today().strftime("%Y%m%d")
53 with open(articleFile, 'r') as infileHandle:
54 theInfile = csv.reader(infileHandle, quotechar='"')
55 for currentLine in theInfile:
56 articleList.append(currentLine["Article"])
58 with open(outputPath, 'w') as outfile:
61 i = 0 #iterator to deal with end of file
65 url= "https://wikimedia.org/api/rest_v1/metrics/pageviews/per-article/en.wikipedia/all-access/all-agents/"
66 url= url + a + "/daily/" + queryDate + "/" + queryDate #for now, single date at a time
69 response = requests.get(url)
71 with open(outputPath, 'a') as outfile:
72 json.dump(json.loads(ident_response.content), outfile)
81 with open(outputPath, 'a') as outfile:
86 if __name__ == "__main__":