mirror of
https://github.com/zots0127/paper_dataset.git
synced 2026-09-08 05:19:53 +00:00
4.3 KiB
4.3 KiB
In [2]:
import requests
from xml.etree import ElementTree
def get_arxiv_paper_info(arxiv_id):
# 构建请求URL
url = f'http://export.arxiv.org/api/query?id_list={arxiv_id}'
# 发送GET请求
response = requests.get(url)
# 解析返回的XML数据
root = ElementTree.fromstring(response.content)
# 初始化结果字典
paper_info = {'title': '', 'summary': '', 'pdf_url': ''}
# 提取文章信息
for entry in root.findall('{http://www.w3.org/2005/Atom}entry'):
paper_info['title'] = entry.find('{http://www.w3.org/2005/Atom}title').text
paper_info['summary'] = entry.find('{http://www.w3.org/2005/Atom}summary').text
# 查找并提取PDF链接
for link in entry.findall('{http://www.w3.org/2005/Atom}link'):
if link.attrib.get('title') == 'pdf':
paper_info['pdf_url'] = link.attrib.get('href') + '.pdf'
return paper_info
# 示例:使用arXiv ID获取文章信息
arxiv_id = '2104.00001' # 这里替换成实际的arXiv ID
paper_info = get_arxiv_paper_info(arxiv_id)
print(paper_info)
{'title': 'Constraining effective equation of state in $f(Q,T)$ gravity', 'summary': " New high-precision observations are now possible to constrain different\ngravity theories. To examine the accelerated expansion of the Universe, we used\nthe newly proposed $f(Q,T)$ gravity, where $Q$ is the non-metricity, and $T$ is\nthe trace of the energy-momentum tensor. The investigation is carried out using\na parameterized effective equation of state with two parameters, $m$ and $n$.\nWe have also considered the linear form of $f(Q,T)= Q+bT$, where $b$ is\nconstant. By constraining the model with the recently published 1048 Pantheon\nsample, we were able to find the best fitting values for the parameters $b$,\n$m$, and $n$. The model appears to be in good agreement with the observations.\nFinally, we analyzed the behavior of the deceleration parameter and equation of\nstate parameter. The results support the feasibility of $f(Q,T)$ as a promising\ntheory of gravity, illuminating a new direction towards explaining the\nUniverse's dark sector.\n", 'pdf_url': 'http://arxiv.org/pdf/2104.00001v2.pdf'}
In [ ]:
import requests
import fitz # PyMuPDF
def download_pdf(url, filename):
response = requests.get(url)
with open(filename, 'wb') as f:
f.write(response.content)
def parse_pdf(filename):
# 打开PDF文件
doc = fitz.open(filename)
# 遍历每一页
for page_num in range(len(doc)):
page = doc.load_page(page_num)
print(page.get_text())
# 使用上面获得的PDF URL下载PDF
pdf_url = paper_info['pdf_url']
filename = 'downloaded_paper.pdf'
download_pdf(pdf_url, filename)
# 解析并打印PDF内容
parse_pdf(filename)