Simple Python script that scrapes the first 200 abstracts (with author list and Arxiv ID) from arxiv.org for a given query string, and renders list in Markdown.

arxiv-abstracts-to-markdown.py

'''
The purpose of this script is to quickly collect a large number of abstracts
from argiv.org so to simplify scanning lots of documents on a single topic
before committing the time to do an in-depth reading of any particular paper.

@author formigone
'''

import requests
import re
from IPython.display import Markdown
from bs4 import BeautifulSoup

def fetch(query):
    args = [
        'query={}'.format(query),
        'searchtype=all',
        'source=header',
        'size=200',
    ]
    url = 'https://arxiv.org/search/?' + '&'.join(args)
    res = requests.get(url).text

    soup = BeautifulSoup(res, 'html.parser')

    doc = []
    for row in soup.find_all(class_='arxiv-result'):
        doc.append('## ' + row.find(class_='title').text.strip())

        authors = [auth.text.strip() for auth in row.find(class_='authors').find_all('a')]
        doc_id = row.find(class_='list-title').find('a').text
        doc.append('[{} | {}]'.format(', '.join(authors), doc_id))

        abstract = row.find(class_='abstract-full').text.strip().replace('△ Less', '').strip()
        re.sub(r'\s\s+', ' ', abstract)
        doc.append('\n{}\n'.format(abstract))

    return '\n'.join(doc)

Markdown(fetch('deep+learning'))

Sample output