From 3f72bb3c8b9a10ec2fda81098b7998c264befd8d Mon Sep 17 00:00:00 2001
From: Miykaelxxm <xiongjiamu@gmail.com>
Date: Thu, 13 Oct 2022 14:47:48 +0800
Subject: [PATCH] add repo info crawler python script

---
 src/repoinfo.py | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)
 create mode 100644 src/repoinfo.py

diff --git a/src/repoinfo.py b/src/repoinfo.py
new file mode 100644
index 0000000..376f611
--- /dev/null
+++ b/src/repoinfo.py
@@ -0,0 +1,43 @@
+# -*- coding: utf-8 -*-
+from os import link
+import requests
+import json
+import time
+import re
+
+# 读取json文件
+with open("dataset/repo-list.json", 'r') as f:
+    data = json.load(f)
+
+with open('dataset/result.txt', 'r+') as file:
+    file.truncate(0)
+
+for list_item in data:
+    # print(list_item["full_name"])
+    a = list_item["full_name"]
+    
+    url = "https://api.github.com/repos/" + a
+    # url2 = "https://api.github.com/repos/" + a + "/contributors?per_page=1&anon=true"
+
+    payload={}
+    headers = {
+        'Authorization': '' # 这里填入你自己的 GitHub Personal Access Token
+        }
+    
+    response = requests.request("GET", url, headers=headers, data=payload)
+
+    # response2 = requests.request("GET", url2, headers=headers, data=payload)
+    
+    # headers2 = requests.get(url2).headers
+    # print(headers2)
+    # pagesize = [int(s) for s in re.findall(r'\b\d+\b',headers2['Link'])]
+    
+    # print(str(response.json()["id"])+ ',' + response.json()["owner"]["login"] + ',' + response.json()["full_name"] + ',' + str(response.json()["stargazers_count"]) + ',' + str(response.json()["forks_count"]) + ',' + str(response.json()["open_issues"]) + ',' + str(pagesize[-1]))
+    # with open('dataset/result.txt', 'a') as f:
+    #     f.write(str(response.json()["id"])+ ',' + response.json()["owner"]["login"] + ',' + response.json()["full_name"] + ',' + str(response.json()["stargazers_count"]) + ',' + str(response.json()["forks_count"]) + ',' + str(pagesize[-1]) + "\n")
+    # time.sleep(4) # Sleep for 2 seconds
+
+    # print(str(response.json()["id"])+ ',' + response.json()["owner"]["login"] + ',' + response.json()["full_name"] + ',' + str(response.json()["stargazers_count"]) + ',' + str(response.json()["forks_count"]) + ',' + str(response.json()["open_issues"]))
+    with open('dataset/result.txt', 'a') as f:
+        f.write(str(response.json()["id"])+ ',' + response.json()["owner"]["login"] + ',' + response.json()["full_name"] + ',' + str(response.json()["stargazers_count"]) + ',' + str(response.json()["forks_count"]) + "\n")
+    time.sleep(2) # Sleep for 2 seconds
\ No newline at end of file
-- 
GitLab