Skip to content

harden: use yaml.safe_load in daily_crawl_arxiv.py (gitlab.bandit.B506) #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
anupamme wants to merge 1 commit into
base: master
Choose a base branch
from
Open

harden: use yaml.safe_load in daily_crawl_arxiv.py (gitlab.bandit.B506) #2

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 4 additions & 10 deletions daily_crawl_arxiv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,12 @@
#!/usr/bin/env python
# -*- encoding: utf-8 -*-
import urllib.request as libreq
from xml.dom.minidom import parseString
from defusedxml.minidom import parseString
import datetime
import requests
import json
import os
import shutil
import yaml
try:
from yaml import CLoader as Loader
except ImportError:
from yaml import Loader

# paperWithCode API
base_url = "https://arxiv.paperswithcode.com/api/v0/papers/"
Expand All @@ -37,7 +32,7 @@ def sort_papers(papers):

def get_yaml_data(yaml_file: str):
fs = open(yaml_file)
data = yaml.load(fs, Loader=Loader)
data = yaml.safe_load(fs)
print(data)
return data

Expand All @@ -46,8 +41,7 @@ def getResult(search_query='all:fake+news+OR+all:rumour', start=0, max_results=5
search_query, start, max_results, sortBy, sortOrder
)
print(url)
data = libreq.urlopen(url)
xml_data = data.read()
xml_data = requests.get(url, timeout=30).content
DOMTree = parseString(xml_data)

collection = DOMTree.documentElement
Expand Down Expand Up @@ -131,7 +125,7 @@ def get_daily_papers(topic: str, query: str = "fake news", max_results=2):
paper_key = paper_id[0: ver_pos]

try:
r = requests.get(code_url).json()
r = requests.get(code_url, timeout=30).json()
# source code link
if "official" in r and r["official"]:
cnt += 1
Expand Down