一.获取数据

import arxiv
import sqlite3
from datetime import datetime, timedelta
import time

conn = sqlite3.connect("spider_arxiv.db")
cursor = conn.cursor()
cursor.execute('''CREATE TABLE IF NOT EXISTS papers
                  (id, dateline, title, authors, abstract,
                  comments, subjects, cite_as, journal_reference)''')

id=0

arxiv_search = arxiv.Search(
query = None,
max_results = 5000,
# max_results = float('inf'),
sort_by=arxiv.SortCriterion.SubmittedDate
)


for result in arxiv_search.results():

    id+=1
    print(id)
    publish_time = result.published.date()
    paper_title = result.title

    paper_author = result.authors
    authors_with_punctuations = ", ".join([author.name for author in paper_author])

    paper_abstract = result.summary
    comments = result.comment

    subjects = result.categories
    subjects_with_punctuations = ", ".join([subject for subject in subjects])

    cite_as = result.entry_id
    journal_reference = result.journal_ref


    cursor.execute("INSERT INTO papers VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)",
                   (id, publish_time, paper_title, authors_with_punctuations, paper_abstract, comments, subjects_with_punctuations, cite_as, journal_reference))



cursor.close()
conn.close()

二.打开数据库

import sqlite3

conn = sqlite3.connect("spider_arxiv.db")
cursor = conn.cursor()
cursor.execute("SELECT * FROM papers")
result = cursor.fetchall()
for row in result:

    print("", row[0])
    print("", row[1])
    print("", row[2])
    print("--------------------")

conn.close()