Add results

README.md

 # Github-Crawler
 
+>This branch corresponds to the results of the crawler for the study linked with [BioFlow-Insight](https://gitlab.liris.cnrs.fr/sharefair/bioflow-insight)
 
 [![MIT licensed](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE) 
 

download_corpus.py

+import json
+import os
+
+with open("./wf_crawl_nextflow.json") as json_file:
+    crawler = json.load(json_file)
+
+crawler.pop("last_date")
+
+#These are the licenses that we are keeping
+LICENSE = ["Apache License 2.0", "GNU General Public License v3.0", "MIT License"]
+
+#Code for downloading the files 
+index = 1
+downloaded = 0
+for project in crawler:
+    print(f'* {index}/{len(crawler)}')
+    if(crawler[project]["license"] in LICENSE):
+        print(f"Downloading...'{project}'")
+        downloaded+=1
+        os.system(f"mkdir -p ")
+        os.system(f'git clone https://github.com/{project}.git ../../../Workflow-Corpus-Open-License/{project}')
+    index+=1
+    print('\n\n')
+print(downloaded)
+    
\ No newline at end of file