Created
August 13, 2019 10:42
-
-
Save barrucadu/308365624f515aa125b01a4dbeb27bd5 to your computer and use it in GitHub Desktop.
Python 2 scripts, but they do the job. Variables refer to ES2 because this is a small tweak on the original script (https://gist.github.com/brucebolt/ec211868299b8efbdde7877e9a2d3c10)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import csv | |
import re | |
results_es2 = {} | |
results_es5 = {} | |
with open('results.txt', 'rb') as f: | |
rows = csv.reader(f, delimiter='\t') | |
next(rows, None) | |
for row in rows: | |
for index, value in enumerate(row): | |
row[index] = re.sub(r'\s*$', '', value) | |
if row[0] not in results_es2: | |
results_es2[row[0]] = {} | |
results_es2[row[0]][row[1]] = row[3] | |
if row[0] not in results_es5: | |
results_es5[row[0]] = {} | |
results_es5[row[0]][row[1]] = row[4] | |
for key in results_es2: | |
found = 0 | |
missing = [] | |
for i in results_es2[key].keys(): | |
if results_es2[key][i] in results_es5[key].values(): | |
found += 1 | |
else: | |
missing.append("{} ({})".format(results_es2[key][i], i)) | |
result = 'TRUE' if found == len(results_es2[key]) else 'FALSE' | |
print "{}\t{}\t{}\t{}".format(key, found, result, ";".join(missing)) | |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
import sys | |
import urllib | |
import csv | |
print "Keyword\tPosition\tMatch\tA Result\tB Result" | |
counter = 1 | |
with open('ga_export.csv', 'r') as f: | |
rows = csv.reader(f, delimiter=',') | |
next(rows, None) # skip header | |
for row in rows: | |
keyword = row[0] | |
sys.stderr.write("{}\n".format(str(counter))) | |
keyword = keyword.strip() | |
query = urllib.urlencode({'q': keyword}) | |
try: | |
resp_es2 = requests.get("https://www.gov.uk/api/search.json?ab_tests=search_cluster_query:A&{}".format(query)) | |
data_es2 = resp_es2.json() | |
resp_es5 = requests.get("https://www.gov.uk/api/search.json?ab_tests=search_cluster_query:B&{}".format(query)) | |
data_es5 = resp_es5.json() | |
except: | |
continue | |
max_results = max(len(data_es2['results']), len(data_es5['results'])) | |
num_results = min(10, max_results) | |
if num_results > 0: | |
for i in range(0, num_results): | |
es2_value = data_es2['results'][i]['link'] if i < len(data_es2['results']) else '(no result at this position)' | |
es5_value = data_es5['results'][i]['link'] if i < len(data_es5['results']) else '(no result at this position)' | |
match = 'MATCH' if es2_value == es5_value else '' | |
print keyword,"\t", i+1, "\t", match, "\t", es2_value, "\t", es5_value | |
counter += 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment