24_deb_pkg_gov/non_coding_measures_scrape.py

80 lines
4.3 KiB
Python

import pexpect
import os
import json
import sys
import subprocess
import csv
import ast
import time
#sys.path.append('../octohatrack')
#import octohatrack.__main__ as oh
csv_path = "013024_octo_data.csv"
csv_013024_path = "013024_te_rows.csv"
def main():
wd = os.getcwd()
with open(csv_path, 'w', newline='') as output_file:
keys = ["project_name","underproduction_mean","underproduction_low","underproduction_high","debian_vcs_link","upstream_vcs_link","age_of_project","contributors","collaborators","milestone_count", "api_contrib_count", "issue_contrib_count", "file_contrib_count", "wiki_contrib_count", ]
dict_writer = csv.DictWriter(output_file, keys)
dict_writer.writeheader()
with open(csv_013024_path, 'w', newline='') as output_file:
keys = ["project_name","underproduction_mean","underproduction_low","underproduction_high","debian_vcs_link","upstream_vcs_link","age_of_project","contributors","collaborators","milestone_count"]
dict_writer2 = csv.DictWriter(output_file, keys)
dict_writer2.writeheader()
with open("kk_final_expanded_data_final.csv", "r") as file:
#with open("013024_te_rows.csv", "r") as file:
reader = csv.reader(file)
for i, line in enumerate(reader):
time.sleep(5)
project_dict ={}
if "github" not in line[5]:
continue
repo_name = line[5].strip()[19:]
if repo_name[-4:] == ".git":
repo_name = repo_name[:-4]
print(repo_name)
project_dict["project_name"] = repo_name.split("/")[1]
project_dict['underproduction_mean'] = line[1]
project_dict['underproduction_low'] = line[2]
project_dict['underproduction_high'] = line[3]
project_dict['debian_vcs_link'] = line[4]
project_dict['upstream_vcs_link'] = line[5]
project_dict['age_of_project'] = line[6]
project_dict['contributors'] = line[7]
project_dict['collaborators'] = line[8]
project_dict['milestone_count'] = line[9]
#print(project_dict)
os.chdir(wd)
os.chdir("../octohatrack")
##--- FAILS FOR:
## - archived GitHub things
## - not github hosted
try:
octohatrack_results = subprocess.run(['python3', '-m', 'octohatrack', repo_name], capture_output = True, text=True, timeout=60).stdout
except (subprocess.TimeoutExpired, TypeError) as e:
dict_writer2.writerow(project_dict)
print(e)
continue
os.chdir(wd)
split_results = octohatrack_results.split("\n")
for entry in split_results:
if "{'api_contributors'" in entry:
formatted = ast.literal_eval(entry)
#print(formatted)
project_dict["api_contrib_count"] = len(formatted['api_contributors'])
#project_dict["api_contrib_list"] = formatted['api_contributors']
project_dict["issue_contrib_count"] = len(formatted['issue_pr_contributors'])
#project_dict["issue_contrib_list"] = formatted['issue_pr_contributors']
project_dict["file_contrib_count"] = len(formatted['file_contributors'])
#project_dict["file_contrib_list"] = formatted['file_contributors']
project_dict["wiki_contrib_count"] = len(formatted['wiki_contributors'])
#project_dict["wiki_contrib_list"] = formatted['file_contributors']
print(project_dict)
dict_writer.writerow(project_dict)
with open('/data/users/mgaughan/b_kkex_contrib_uni_013024/' + 'contrib_roster_' + project_dict["project_name"] + '.json', 'w') as data_path:
json.dump(formatted, data_path)
if __name__ == "__main__":
main()