jspeed-meyers

➜  ~ syft nvcr.io/nvidia/pytorch:24.02-py3
 ✔ Pulled image                    
 ✔ Loaded image                                                                                     nvcr.io/nvidia/pytorch:24.02-py3
 ✔ Parsed image                                              sha256:43fcc1b74fd54c3598c3c3d569c7ec4f6e93dc78adad06e38783c95e1bfd5c94
 ✔ Cataloged contents                                               57fd547447043b585ed68a43a7f1dfd3d01ea25c821df0b032b9da79ab82a385
   ├── ✔ Packages                        [892 packages]  
   ├── ✔ File digests                    [14,449 files]  
   ├── ✔ File metadata                   [14,449 locations]  
   └── ✔ Executables                     [2,759 executables]  
[0432]  WARN cataloger failed cataloger=javascript-package-cataloger error=failed to parse package.json file: json: cannot unmarshal s

jspeed-meyers

 syft --platform linux/amd64 cgr.dev/chainguard/pytorch-cuda12
 ✔ Pulled image                    
 ✔ Loaded image                                                                             cgr.dev/chainguard/pytorch-cuda12:latest
 ✔ Parsed image                                              sha256:fde1b4b832c4dd0008ba8a49ac886ada4b3bbf3248b438f893e42664d29c9e07
 ✔ Cataloged contents                                               efb7865bb45355ec5582bd8e02f1b14792c03cfdade52b6b1214e8eaf88ac99c
   ├── ✔ Packages                        [69 packages]  
   ├── ✔ File digests                    [19,193 files]  
   ├── ✔ File metadata                   [19,193 locations]  
   └── ✔ Executables                     [432 executables]  
NAME                      VERSION           TYPE                    

jspeed-meyers

import json

import pandas as pd
import requests

YOUR_SHEET_ID = "1ifFaQyNfgC-V0AnubYm9P3btkNwN9rXJNAHiauflHV4"
CSV_URL = f"https://docs.google.com/spreadsheet/ccc?key={YOUR_SHEET_ID}&output=csv"

res = requests.get(url=CSV_URL)
with open("image-names.csv", "wb") as data:

jspeed-meyers

import json
import pandas as pd

pd.options.display.float_format = '{:.4f}'.format

with open("funder_finder_results.jsonl") as f:
    df = pd.DataFrame(json.loads(line) for line in f)
    #print(df.info())
    #print(df.type.value_counts())
    #print(pd.crosstab(df.type, df.funding_type))

jspeed-meyers

import json
import pandas as pd

with open("funder_finder_results.jsonl") as f:
    df = pd.DataFrame(json.loads(line) for line in f)

jspeed-meyers

# find number of top 1000 python packages that have one or more CVEs

import json

# find all packages with a CVE

# Open the JSON file
with open("pyup_io_safety_db_python_cve.json") as file:
    # Load the JSON data
    data = json.load(file)

jspeed-meyers

# collect data from multiple repos into a CSV. Each line is one type of a contribution to
# one particular repo

import json
import os

def run_python_command(command):
    # Execute the command and capture the output
    output = os.popen(command).read().strip()

jspeed-meyers

{"funding_type": "individual", "type": "Github Sponsors", "is_funded": true, "date_of_data_collection": "2023-05-28", "repo_name": "https://github.com/pytest-dev/execnet"}
{"funding_type": "organizational", "num_contributors": 5, "type": "Github Sponsors", "is_funded": true, "date_of_data_collection": "2023-05-28", "repo_name": "https://github.com/ipython/comm"}
{"funding_type": "individual", "type": "Github Sponsors", "is_funded": true, "date_of_data_collection": "2023-05-28", "repo_name": "https://github.com/scrapy/cssselect"}
{"funding_type": "individual", "type": "Github Sponsors", "is_funded": true, "date_of_data_collection": "2023-05-28", "repo_name": "https://github.com/horejsek/python-fastjsonschema"}
{"funding_type": "individual", "type": "Github Sponsors", "is_funded": true, "date_of_data_collection": "2023-05-28", "repo_name": "https://github.com/pytest-dev/py"}
{"funding_type": "individual", "type": "Github Sponsors", "is_funded": true, "date_of_data_collection": "2023-05-28", "repo_name": "https:

jspeed-meyers

https://github.com/pytest-dev/execnet
https://github.com/ipython/comm
https://github.com/scrapy/cssselect
https://github.com/confluentinc/confluent-kafka-python
https://github.com/explosion/cymem
https://github.com/sighingnow/libclang
https://github.com/rbarrois/python-semanticversion
https://github.com/horejsek/python-fastjsonschema
https://github.com/pytest-dev/py
https://github.com/html5lib/html5lib-python

jspeed-meyers

"""Filter deps2repos output for top python package GitHub URLs"""

input_filename = "pypi_repo_deps2repos_output.txt"
output_filename = "deps2repos_output_post_filtering.txt"

# read in output of deps2repos
with open(input_filename, "r") as file:
    # only start collecting data on the 79th line because
    # the early information is about repos lacking GitHub
    # repos